Deep Learning for Wildlife Monitoring: Near-Infrared Bat Detection Using YOLO Frameworks
Abstract
1. Introduction
2. Materials and Methods
2.1. Multisensor Platform Description
- Stereo NIR images;
- Depth information produced by Intel RealSense D435i;
- High-frequency audio signals.
- 1.
- Main Imaging Unit
- Equipped with two Arducam IR cameras (60 FPS) mounted 8 cm apart using a custom 3D-printed frame for stereo image acquisition.
- Includes an array of NIR LED lights (wavelength: 890 nm).
- Features an 8x11-inch touchscreen interface.
- Captures high-frequency audio signals.
- Raspberry Pi 4 Model B+ (8GB RAM), which serves as the onboard computer. The Raspberry Pi facilitates the implementation of lightweight, low-cost, and low-power multisensor platforms [29].
- The Active Infrared (IR) stereo camera, Intel RealSense D435i, is a compact and lightweight device. It projects IR patterns onto the scene and uses a pair of global shutter sensors to compute depth information via stereo triangulation, enabling robust performance even in low-texture or low-light conditions.
- 2.
- Power and Regulation Unit
- Powered by two lithium-polymer (LiPo) batteries (9.6 V and 5 V).
- –
- 5 V for the Raspberry Pi.
- –
- 9.6 V for IR LED illuminators.
- One battery powers the Raspberry Pi + Arducam cameras, touchscreen, and Intel RealSense D435i, while the second battery exclusively powers the IR LED array.
Algorithm 1 Stereo image acquisition for bat counting. |
|
2.2. Semi-Automatic Labeling of Images
2.3. Algorithms for Detecting Bats
- 1.
- Grid-based prediction. The input image I is divided into an grid. Each grid cell is responsible for detecting objects whose center falls within it.
- 2.
- Bounding box regression. The model uses a regression approach to estimate bounding boxes, which are rectangles enclosing detected objects. The output vector for each prediction is defined as
- p is the confidence score (range: 0–1) indicating the presence of an object in the cell;
- are the coordinates of the center of the bounding box relative to the grid cell;
- denotes the height and width of the bounding box;
- c is the class label among n predefined categories.
- 3.
- Non-Maximum Suppression (NMS). Since multiple overlapping boxes may be predicted for the same object, NMS is applied to retain only the most confident detection, eliminating redundant predictions.
2.4. Evaluation Metrics
3. Results
3.1. NIR Camera Sensitivity
3.2. Semi-Automatic Labeling of Images
3.3. Detection Using YOLO Frameworks
4. Discussion
5. Conclusions and Future Work
- Ecological Monitoring and Biodiversity Assessment: Our approach provides an unbiased tool for surveying flying bats, including species that evade traditional methods such as mist-netting or do not emit detectable echolocation calls. It enhances assessments of species richness, community composition, and temporal activity patterns across diverse landscapes.
- Conservation: By enabling safe, continuous, and non-invasive observation of bat colonies and behaviors, the method supports long-term monitoring and conservation planning. It facilitates population size estimation, behavioral studies, and habitat use analysis, key to addressing threats such as habitat loss, climate change, and emerging diseases.
- Zoonosis Risk Assessment: The elimination of direct bat handling reduces the risk of zoonotic disease transmission, making this method particularly suitable for surveillance programs targeting potential disease reservoirs while ensuring the safety of both wildlife and researchers.
- Behavioral Ecology and Fundamental Research: Combining visual and acoustic data allows the study of complex behaviors such as flight maneuvers, social interactions, and echolocation in natural settings. It opens new avenues for investigating species-specific traits, resolving taxonomic ambiguities, and analyzing collective movement patterns.
- Agricultural Pest Management: The ability to map bat foraging activity across landscapes can help identify areas of high ecological service potential, such as pest control in crop fields. This has implications for reducing pesticide use and promoting sustainable agricultural practices.
- Engineering and Technological Innovation: Insights into bat navigation and group flight behavior can inform the development of bio-inspired algorithms for autonomous vehicles, swarm robotics, and artificial intelligence systems focused on coordinated group behavior.
- Broader Biological Applications: The methodology can be adapted to monitor other flying animal aggregations, including migratory birds and insect swarms. It offers a flexible platform for ecological studies, biodiversity monitoring, and conservation efforts beyond bat populations.
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
Appendix A
Appendix A.1. Full Set of Pairwise Comparisons
Comparison | (mean) | 95% CI | Effect | |
---|---|---|---|---|
mAP@75 | ||||
YOLOv10-l vs YOLOv10-n | −0.0192 | [−0.1155, 0.0712] | 1.0000 | r = −0.050 |
YOLOv10-l vs YOLOv10-s | −0.0524 | [−0.1473, 0.0424] | 1.0000 | r = −0.227 |
YOLOv10-l vs YOLOv10-x | 0.0084 | [−0.0756, 0.0917] | 1.0000 | r = 0.143 |
YOLOv10-l vs YOLOv11-l | 0.0000 | [−0.0825, 0.0818] | 1.0000 | r = −0.030 |
YOLOv10-l vs YOLOv11-m | −0.0190 | [−0.1139, 0.0738] | 1.0000 | r = −0.048 |
YOLOv10-l vs YOLOv11-n | −0.0061 | [−0.0970, 0.0840] | 1.0000 | r = −0.053 |
YOLOv10-l vs YOLOv11-s | 0.0091 | [−0.0887, 0.1046] | 1.0000 | r = 0.048 |
YOLOv10-l vs YOLOv11-x | 0.0611 | [−0.0351, 0.1550] | 1.0000 | r = 0.190 |
YOLOv10-l vs YOLOv12-l | −0.0083 | [−0.0946, 0.0773] | 1.0000 | r = −0.059 |
YOLOv10-l vs YOLOv12-m | 0.0053 | [−0.0825, 0.0902] | 1.0000 | r = 0.000 |
YOLOv10-l vs YOLOv12-n | 0.0218 | [−0.0666, 0.1104] | 1.0000 | r = 0.050 |
YOLOv10-l vs YOLOv12-s | 0.0220 | [−0.0818, 0.1258] | 1.0000 | r = 0.130 |
YOLOv10-l vs YOLOv12-x | −0.0187 | [−0.1163, 0.0774] | 1.0000 | r = −0.048 |
YOLOv10-m vs YOLOv10-n | −0.0563 | [−0.1347, 0.0262] | 1.0000 | r = −0.226 |
YOLOv10-m vs YOLOv10-s | −0.0895 | [−0.1681, −0.0113] | 1.0000 | r = −0.400 |
YOLOv10-m vs YOLOv10-x | −0.0287 | [−0.1211, 0.0623] | 1.0000 | r = 0.026 |
YOLOv10-m vs YOLOv11-l | −0.0371 | [−0.1296, 0.0539] | 1.0000 | r = −0.176 |
YOLOv10-m vs YOLOv11-m | −0.0561 | [−0.1481, 0.0350] | 1.0000 | r = −0.200 |
YOLOv10-m vs YOLOv11-n | −0.0432 | [−0.1250, 0.0387] | 1.0000 | r = −0.185 |
YOLOv10-m vs YOLOv11-s | −0.0280 | [−0.1236, 0.0675] | 1.0000 | r = −0.053 |
YOLOv10-m vs YOLOv11-x | 0.0240 | [−0.0564, 0.1061] | 1.0000 | r = 0.097 |
YOLOv10-m vs YOLOv12-l | −0.0454 | [−0.1242, 0.0312] | 1.0000 | r = −0.185 |
YOLOv10-m vs YOLOv12-m | −0.0318 | [−0.1227, 0.0636] | 1.0000 | r = −0.125 |
YOLOv10-m vs YOLOv12-n | −0.0153 | [−0.1072, 0.0759] | 1.0000 | r = −0.100 |
YOLOv10-m vs YOLOv12-s | −0.0151 | [−0.1076, 0.0781] | 1.0000 | r = 0.000 |
YOLOv10-m vs YOLOv12-x | −0.0559 | [−0.1454, 0.0375] | 1.0000 | r = −0.143 |
YOLOv10-n vs YOLOv10-s | −0.0332 | [−0.1152, 0.0489] | 1.0000 | r = −0.212 |
YOLOv10-n vs YOLOv10-x | 0.0276 | [−0.0621, 0.1188] | 1.0000 | r = 0.135 |
YOLOv10-n vs YOLOv11-l | 0.0192 | [−0.0718, 0.1136] | 1.0000 | r = −0.029 |
YOLOv10-n vs YOLOv11-m | 0.0002 | [−0.0886, 0.0868] | 1.0000 | r = −0.059 |
YOLOv10-n vs YOLOv11-n | 0.0131 | [−0.0778, 0.1046] | 1.0000 | r = −0.029 |
YOLOv10-n vs YOLOv11-s | 0.0283 | [−0.0652, 0.1192] | 1.0000 | r = 0.056 |
YOLOv10-n vs YOLOv11-x | 0.0803 | [−0.0098, 0.1712] | 1.0000 | r = 0.200 |
YOLOv10-n vs YOLOv12-l | 0.0109 | [−0.0701, 0.0919] | 1.0000 | r = 0.000 |
YOLOv10-n vs YOLOv12-m | 0.0245 | [−0.0749, 0.1273] | 1.0000 | r = 0.050 |
YOLOv10-n vs YOLOv12-n | 0.0410 | [−0.0455, 0.1305] | 1.0000 | r = 0.000 |
YOLOv10-n vs YOLOv12-s | 0.0412 | [−0.0497, 0.1311] | 1.0000 | r = 0.118 |
YOLOv10-n vs YOLOv12-x | 0.0004 | [−0.0792, 0.0796] | 1.0000 | r = −0.037 |
YOLOv10-s vs YOLOv10-x | 0.0608 | [−0.0316, 0.1515] | 1.0000 | r = 0.317 |
YOLOv10-s vs YOLOv11-l | 0.0524 | [−0.0338, 0.1431] | 1.0000 | r = 0.294 |
YOLOv10-s vs YOLOv11-m | 0.0334 | [−0.0540, 0.1191] | 1.0000 | r = 0.118 |
YOLOv10-s vs YOLOv11-n | 0.0463 | [−0.0459, 0.1387] | 1.0000 | r = 0.135 |
YOLOv10-s vs YOLOv11-s | 0.0616 | [−0.0241, 0.1486] | 1.0000 | r = 0.200 |
YOLOv10-s vs YOLOv11-x | 0.1135 | [0.0202, 0.2070] | 1.0000 | r = 0.381 |
YOLOv10-s vs YOLOv12-l | 0.0441 | [−0.0301, 0.1214] | 1.0000 | r = 0.241 |
YOLOv10-s vs YOLOv12-m | 0.0578 | [−0.0341, 0.1509] | 1.0000 | r = 0.243 |
YOLOv10-s vs YOLOv12-n | 0.0742 | [−0.0199, 0.1672] | 1.0000 | r = 0.143 |
YOLOv10-s vs YOLOv12-s | 0.0744 | [−0.0075, 0.1584] | 1.0000 | r = 0.375 |
YOLOv10-s vs YOLOv12-x | 0.0337 | [−0.0500, 0.1182] | 1.0000 | r = 0.187 |
YOLOv10-x vs YOLOv11-l | −0.0084 | [−0.1038, 0.0865] | 1.0000 | r = −0.128 |
YOLOv10-x vs YOLOv11-m | −0.0274 | [−0.1202, 0.0662] | 1.0000 | r = −0.135 |
YOLOv10-x vs YOLOv11-n | −0.0145 | [−0.1084, 0.0786] | 1.0000 | r = −0.135 |
YOLOv10-x vs YOLOv11-s | 0.0007 | [−0.0910, 0.0938] | 1.0000 | r = −0.027 |
YOLOv10-x vs YOLOv11-x | 0.0527 | [−0.0436, 0.1492] | 1.0000 | r = 0.073 |
YOLOv10-x vs YOLOv12-l | −0.0167 | [−0.1152, 0.0803] | 1.0000 | r = −0.128 |
Comparison | (mean) | 95% CI | Effect | |
---|---|---|---|---|
YOLOv10-x vs YOLOv12-m | −0.0031 | [−0.0962, 0.0916] | 1.0000 | r = −0.111 |
YOLOv10-x vs YOLOv12-n | 0.0134 | [−0.0818, 0.1079] | 1.0000 | r = −0.100 |
YOLOv10-x vs YOLOv12-s | 0.0136 | [−0.0842, 0.1121] | 1.0000 | r = 0.000 |
YOLOv10-x vs YOLOv12-x | −0.0272 | [−0.1196, 0.0645] | 1.0000 | r = −0.111 |
YOLOv11-l vs YOLOv11-m | −0.0190 | [−0.0975, 0.0578] | 1.0000 | r = −0.111 |
YOLOv11-l vs YOLOv11-n | −0.0061 | [−0.1031, 0.0893] | 1.0000 | r = −0.030 |
YOLOv11-l vs YOLOv11-s | 0.0091 | [−0.0812, 0.0985] | 1.0000 | r = 0.059 |
YOLOv11-l vs YOLOv11-x | 0.0611 | [−0.0238, 0.1452] | 1.0000 | r = 0.226 |
YOLOv11-l vs YOLOv12-l | −0.0083 | [−0.0780, 0.0598] | 1.0000 | r = 0.000 |
YOLOv11-l vs YOLOv12-m | 0.0053 | [−0.0757, 0.0833] | 1.0000 | r = 0.091 |
YOLOv11-l vs YOLOv12-n | 0.0218 | [−0.0621, 0.1049] | 1.0000 | r = 0.125 |
YOLOv11-l vs YOLOv12-s | 0.0220 | [−0.0736, 0.1152] | 1.0000 | r = 0.059 |
YOLOv11-l vs YOLOv12-x | −0.0188 | [−0.1080, 0.0716] | 1.0000 | r = −0.103 |
YOLOv11-m vs YOLOv11-n | 0.0129 | [−0.0729, 0.1017] | 1.0000 | r = 0.000 |
YOLOv11-m vs YOLOv11-s | 0.0281 | [−0.0523, 0.1108] | 1.0000 | r = 0.154 |
YOLOv11-m vs YOLOv11-x | 0.0801 | [−0.0068, 0.1695] | 1.0000 | r = 0.257 |
YOLOv11-m vs YOLOv12-l | 0.0107 | [−0.0622, 0.0827] | 1.0000 | r = 0.130 |
YOLOv11-m vs YOLOv12-m | 0.0243 | [−0.0730, 0.1238] | 1.0000 | r = 0.105 |
YOLOv11-m vs YOLOv12-n | 0.0408 | [−0.0417, 0.1228] | 1.0000 | r = 0.097 |
YOLOv11-m vs YOLOv12-s | 0.0410 | [−0.0489, 0.1306] | 1.0000 | r = 0.200 |
YOLOv11-m vs YOLOv12-x | 0.0002 | [−0.0825, 0.0827] | 1.0000 | r = 0.000 |
YOLOv11-n vs YOLOv11-s | 0.0152 | [−0.0704, 0.1008] | 1.0000 | r = 0.071 |
YOLOv11-n vs YOLOv11-x | 0.0672 | [−0.0216, 0.1575] | 1.0000 | r = 0.294 |
YOLOv11-n vs YOLOv12-l | −0.0022 | [−0.0871, 0.0841] | 1.0000 | r = 0.071 |
YOLOv11-n vs YOLOv12-m | 0.0114 | [−0.0794, 0.1023] | 1.0000 | r = 0.034 |
YOLOv11-n vs YOLOv12-n | 0.0279 | [−0.0526, 0.1100] | 1.0000 | r = 0.067 |
YOLOv11-n vs YOLOv12-s | 0.0281 | [−0.0719, 0.1257] | 1.0000 | r = 0.111 |
YOLOv11-n vs YOLOv12-x | −0.0127 | [−0.1014, 0.0750] | 1.0000 | r = 0.032 |
YOLOv11-s vs YOLOv11-x | 0.0519 | [−0.0385, 0.1417] | 1.0000 | r = 0.176 |
YOLOv11-s vs YOLOv12-l | −0.0174 | [−0.0901, 0.0522] | 1.0000 | r = −0.043 |
YOLOv11-s vs YOLOv12-m | −0.0038 | [−0.0926, 0.0855] | 1.0000 | r = −0.091 |
YOLOv11-s vs YOLOv12-n | 0.0126 | [−0.0704, 0.0967] | 1.0000 | r = −0.032 |
YOLOv11-s vs YOLOv12-s | 0.0129 | [−0.0668, 0.0924] | 1.0000 | r = 0.083 |
YOLOv11-s vs YOLOv12-x | −0.0279 | [−0.1047, 0.0494] | 1.0000 | r = −0.154 |
YOLOv11-x vs YOLOv12-l | −0.0694 | [−0.1462, 0.0047] | 1.0000 | r = −0.333 |
YOLOv11-x vs YOLOv12-m | −0.0557 | [−0.1478, 0.0351] | 1.0000 | r = −0.143 |
YOLOv11-x vs YOLOv12-n | −0.0393 | [−0.1310, 0.0507] | 1.0000 | r = −0.189 |
YOLOv11-x vs YOLOv12-s | −0.0391 | [−0.1300, 0.0486] | 1.0000 | r = −0.086 |
YOLOv11-x vs YOLOv12-x | −0.0798 | [−0.1576, −0.0043] | 1.0000 | r = −0.286 |
YOLOv12-l vs YOLOv12-m | 0.0137 | [−0.0682, 0.0955] | 1.0000 | r = 0.077 |
YOLOv12-l vs YOLOv12-n | 0.0301 | [−0.0516, 0.1119] | 1.0000 | r = 0.032 |
YOLOv12-l vs YOLOv12-s | 0.0303 | [−0.0560, 0.1158] | 1.0000 | r = 0.103 |
YOLOv12-l vs YOLOv12-x | −0.0104 | [−0.0898, 0.0671] | 1.0000 | r = −0.077 |
YOLOv12-m vs YOLOv12-n | 0.0164 | [−0.0803, 0.1122] | 1.0000 | r = 0.026 |
YOLOv12-m vs YOLOv12-s | 0.0167 | [−0.0788, 0.1122] | 1.0000 | r = 0.059 |
YOLOv12-m vs YOLOv12-x | −0.0241 | [−0.1106, 0.0623] | 1.0000 | r = −0.143 |
YOLOv12-n vs YOLOv12-s | 0.0002 | [−0.0956, 0.0951] | 1.0000 | r = 0.027 |
YOLOv12-n vs YOLOv12-x | −0.0405 | [−0.1254, 0.0440] | 1.0000 | r = 0.000 |
YOLOv12-s vs YOLOv12-x | −0.0407 | [−0.1190, 0.0386] | 1.0000 | r = −0.154 |
YOLOv10-b vs YOLOv11-n | −0.0326 | [−0.1242, 0.0605] | 1.0000 | r = −0.135 |
YOLOv10-b vs YOLOv11-m | −0.0455 | [−0.1243, 0.0335] | 1.0000 | r = −0.187 |
YOLOv10-b vs YOLOv11-l | −0.0265 | [−0.1106, 0.0569] | 1.0000 | r = −0.176 |
YOLOv10-b vs YOLOv10-x | −0.0181 | [−0.1121, 0.0758] | 1.0000 | r = 0.026 |
YOLOv10-b vs YOLOv10-s | −0.0790 | [−0.1653, 0.0104] | 1.0000 | r = −0.366 |
YOLOv10-b vs YOLOv10-n | −0.0457 | [−0.1356, 0.0464] | 1.0000 | r = −0.158 |
YOLOv10-b vs YOLOv10-m | 0.0106 | [−0.0760, 0.0976] | 1.0000 | r = −0.029 |
YOLOv10-b vs YOLOv10-l | −0.0265 | [−0.1137, 0.0621] | 1.0000 | r = −0.081 |
YOLOv10-l vs YOLOv10-m | 0.0371 | [−0.0622, 0.1341] | 1.0000 | r = 0.073 |
YOLOv10-b vs YOLOv12-x | −0.0453 | [−0.1288, 0.0373] | 1.0000 | r = −0.176 |
YOLOv10-b vs YOLOv12-s | −0.0045 | [−0.0962, 0.0878] | 1.0000 | r = 0.027 |
YOLOv10-b vs YOLOv12-n | −0.0048 | [−0.0932, 0.0839] | 1.0000 | r = −0.100 |
YOLOv10-b vs YOLOv12-m | −0.0212 | [−0.1099, 0.0674] | 1.0000 | r = −0.086 |
YOLOv10-b vs YOLOv12-l | −0.0348 | [−0.1122, 0.0439] | 1.0000 | r = −0.103 |
Comparison | (mean) | 95% CI | Effect | |
---|---|---|---|---|
YOLOv10-b vs YOLOv11-x | 0.0345 | [−0.0574, 0.1264] | 1.0000 | r = 0.150 |
YOLOv10-b vs YOLOv11-s | −0.0174 | [−0.1075, 0.0720] | 1.0000 | r = −0.056 |
F1 | ||||
YOLOv10-b vs YOLOv10-l | 0.0383 | [−0.0285, 0.1049] | 1.0000 | r = 0.270 |
YOLOv10-b vs YOLOv10-m | −0.0032 | [−0.0774, 0.0695] | 1.0000 | r = 0.036 |
YOLOv10-b vs YOLOv10-n | 0.0279 | [−0.0327, 0.0872] | 1.0000 | r = 0.265 |
YOLOv10-b vs YOLOv10-s | −0.0396 | [−0.1137, 0.0332] | 1.0000 | r = −0.151 |
YOLOv10-b vs YOLOv10-x | 0.0674 | [−0.0060, 0.1396] | 1.0000 | r = 0.297 |
YOLOv10-b vs YOLOv11-l | −0.0982 | [−0.1749, −0.0214] | 1.0000 | r = −0.424 |
YOLOv10-b vs YOLOv11-m | −0.1152 | [−0.1886, −0.0414] | 0.6416 | r = −0.429 |
YOLOv10-b vs YOLOv11-n | −0.0735 | [−0.1495, 0.0023] | 1.0000 | r = −0.231 |
YOLOv10-l vs YOLOv11-x | 0.0084 | [−0.0643, 0.0800] | 1.0000 | r = 0.127 |
YOLOv10-l vs YOLOv11-s | −0.1383 | [−0.2233, −0.0533] | 1.0000 | r = −0.351 |
YOLOv10-l vs YOLOv11-n | −0.1118 | [−0.1889, −0.0353] | 1.0000 | r = −0.412 |
YOLOv10-l vs YOLOv11-m | −0.1535 | [−0.2315, −0.0781] | 0.1555 | r = −0.472 |
YOLOv10-l vs YOLOv11-l | −0.1365 | [−0.2036, −0.0694] | 0.0923 | r = −0.449 |
YOLOv10-l vs YOLOv10-x | 0.0292 | [−0.0335, 0.0910] | 1.0000 | r = 0.086 |
YOLOv10-l vs YOLOv10-s | −0.0778 | [−0.1515, −0.0074] | 1.0000 | r = −0.342 |
YOLOv10-l vs YOLOv10-n | −0.0103 | [−0.0742, 0.0538] | 1.0000 | r = 0.000 |
YOLOv10-l vs YOLOv10-m | −0.0414 | [−0.1155, 0.0302] | 1.0000 | r = −0.143 |
YOLOv10-b vs YOLOv12-x | −0.0767 | [−0.1513, −0.0032] | 1.0000 | r = −0.312 |
YOLOv10-b vs YOLOv12-s | −0.0490 | [−0.1241, 0.0292] | 1.0000 | r = −0.302 |
YOLOv10-b vs YOLOv12-n | 0.0126 | [−0.0548, 0.0802] | 1.0000 | r = −0.015 |
YOLOv10-b vs YOLOv12-m | −0.0670 | [−0.1406, 0.0056] | 1.0000 | r = −0.290 |
YOLOv10-b vs YOLOv12-l | −0.0504 | [−0.1206, 0.0184] | 1.0000 | r = −0.207 |
YOLOv10-b vs YOLOv11-x | 0.0466 | [−0.0314, 0.1245] | 1.0000 | r = 0.159 |
YOLOv10-b vs YOLOv11-s | −0.1000 | [−0.1866, −0.0138] | 1.0000 | r = −0.361 |
YOLOv10-l vs YOLOv12-l | −0.0886 | [−0.1596, −0.0167] | 1.0000 | r = −0.333 |
YOLOv10-l vs YOLOv12-m | −0.1053 | [−0.1733, −0.0365] | 1.0000 | r = −0.403 |
YOLOv10-l vs YOLOv12-n | −0.0257 | [−0.0973, 0.0461] | 1.0000 | r = −0.127 |
YOLOv10-l vs YOLOv12-s | −0.0872 | [−0.1705, −0.0058] | 1.0000 | r = −0.165 |
YOLOv10-l vs YOLOv12-x | −0.1149 | [−0.1933, −0.0384] | 1.0000 | r = −0.359 |
YOLOv10-m vs YOLOv10-n | 0.0311 | [−0.0241, 0.0890] | 1.0000 | r = 0.258 |
YOLOv10-m vs YOLOv10-s | −0.0364 | [−0.1016, 0.0282] | 1.0000 | r = −0.079 |
YOLOv10-m vs YOLOv10-x | 0.0706 | [0.0051, 0.1339] | 1.0000 | r = 0.343 |
YOLOv10-m vs YOLOv11-l | −0.0950 | [−0.1771, −0.0108] | 1.0000 | r = −0.460 |
YOLOv10-m vs YOLOv11-m | −0.1120 | [−0.1899, −0.0334] | 1.0000 | r = −0.433 |
YOLOv10-m vs YOLOv11-n | −0.0704 | [−0.1402, −0.0006] | 1.0000 | r = −0.283 |
YOLOv10-m vs YOLOv11-s | −0.0968 | [−0.1846, −0.0111] | 1.0000 | r = −0.267 |
YOLOv10-m vs YOLOv11-x | 0.0498 | [−0.0182, 0.1196] | 1.0000 | r = 0.200 |
YOLOv10-m vs YOLOv12-l | −0.0472 | [−0.1116, 0.0180] | 1.0000 | r = −0.200 |
YOLOv10-m vs YOLOv12-m | −0.0638 | [−0.1408, 0.0134] | 1.0000 | r = −0.258 |
YOLOv10-m vs YOLOv12-n | 0.0158 | [−0.0559, 0.0876] | 1.0000 | r = −0.079 |
YOLOv10-s vs YOLOv11-m | −0.0756 | [−0.1509, −0.0005] | 1.0000 | r = −0.324 |
YOLOv10-s vs YOLOv11-n | −0.0340 | [−0.1104, 0.0447] | 1.0000 | r = −0.303 |
YOLOv10-s vs YOLOv11-s | −0.0604 | [−0.1444, 0.0250] | 1.0000 | r = −0.324 |
YOLOv10-s vs YOLOv11-x | 0.0862 | [0.0131, 0.1609] | 1.0000 | r = 0.195 |
YOLOv10-s vs YOLOv12-l | −0.0108 | [−0.0785, 0.0588] | 1.0000 | r = −0.175 |
YOLOv10-s vs YOLOv12-m | −0.0274 | [−0.1035, 0.0521] | 1.0000 | r = −0.224 |
YOLOv10-s vs YOLOv12-n | 0.0522 | [−0.0215, 0.1275] | 1.0000 | r = 0.015 |
YOLOv10-s vs YOLOv12-s | −0.0094 | [−0.0812, 0.0644] | 1.0000 | r = −0.114 |
YOLOv10-s vs YOLOv12-x | −0.0371 | [−0.1121, 0.0401] | 1.0000 | r = −0.233 |
YOLOv10-x vs YOLOv11-l | −0.1656 | [−0.2397, −0.0902] | 0.0649 | r = −0.472 |
YOLOv10-x vs YOLOv11-m | −0.1826 | [−0.2618, −0.1024] | 0.0276 | r = −0.514 |
YOLOv10-x vs YOLOv11-n | −0.1410 | [−0.2150, −0.0667] | 0.4517 | r = −0.463 |
YOLOv10-x vs YOLOv11-s | −0.1675 | [−0.2457, −0.0854] | 0.1412 | r = −0.541 |
YOLOv10-x vs YOLOv11-x | −0.0208 | [−0.0902, 0.0472] | 1.0000 | r = −0.086 |
YOLOv10-x vs YOLOv12-l | −0.1178 | [−0.1931, −0.0426] | 1.0000 | r = −0.397 |
YOLOv10-x vs YOLOv12-m | −0.1344 | [−0.1975, −0.0718] | 0.0475 | r = −0.429 |
YOLOv10-m vs YOLOv12-s | −0.0458 | [−0.1268, 0.0364] | 1.0000 | r = −0.242 |
Comparison | (mean) | 95% CI | Effect | |
---|---|---|---|---|
YOLOv10-m vs YOLOv12-x | −0.0735 | [−0.1477, 0.0021] | 1.0000 | r = −0.258 |
YOLOv10-n vs YOLOv10-s | −0.0675 | [−0.1275, −0.0092] | 1.0000 | r = −0.333 |
YOLOv10-n vs YOLOv10-x | 0.0395 | [−0.0221, 0.1006] | 1.0000 | r = 0.206 |
YOLOv10-n vs YOLOv11-l | −0.1261 | [−0.2004, −0.0516] | 1.0000 | r = −0.493 |
YOLOv10-n vs YOLOv11-m | −0.1431 | [−0.2155, −0.0717] | 0.1640 | r = −0.493 |
YOLOv10-n vs YOLOv11-n | −0.1015 | [−0.1691, −0.0325] | 1.0000 | r = −0.417 |
YOLOv10-n vs YOLOv11-s | −0.1279 | [−0.2086, −0.0481] | 1.0000 | r = −0.444 |
YOLOv10-n vs YOLOv11-x | 0.0187 | [−0.0445, 0.0829] | 1.0000 | r = 0.000 |
YOLOv10-n vs YOLOv12-l | −0.0783 | [−0.1382, −0.0179] | 1.0000 | r = −0.355 |
YOLOv10-n vs YOLOv12-m | −0.0949 | [−0.1687, −0.0194] | 1.0000 | r = −0.333 |
YOLOv10-n vs YOLOv12-n | −0.0153 | [−0.0749, 0.0447] | 1.0000 | r = −0.182 |
YOLOv10-n vs YOLOv12-s | −0.0769 | [−0.1568, 0.0005] | 1.0000 | r = −0.342 |
YOLOv10-n vs YOLOv12-x | −0.1046 | [−0.1677, −0.0401] | 0.7348 | r = −0.507 |
YOLOv10-s vs YOLOv10-x | 0.1070 | [0.0414, 0.1732] | 1.0000 | r = 0.361 |
YOLOv10-s vs YOLOv11-l | −0.0586 | [−0.1382, 0.0248] | 1.0000 | r = −0.353 |
YOLOv11-m vs YOLOv12-l | 0.0648 | [0.0000, 0.1300] | 1.0000 | r = 0.440 |
YOLOv11-m vs YOLOv11-x | 0.1618 | [0.0871, 0.2388] | 0.0565 | r = 0.484 |
YOLOv11-m vs YOLOv11-s | 0.0152 | [−0.0615, 0.0946] | 1.0000 | r = 0.040 |
YOLOv11-m vs YOLOv11-n | 0.0417 | [−0.0339, 0.1180] | 1.0000 | r = 0.115 |
YOLOv11-l vs YOLOv12-x | 0.0215 | [−0.0641, 0.1078] | 1.0000 | r = 0.120 |
YOLOv11-l vs YOLOv12-s | 0.0492 | [−0.0345, 0.1297] | 1.0000 | r = 0.214 |
YOLOv11-l vs YOLOv12-n | 0.1108 | [0.0371, 0.1829] | 1.0000 | r = 0.439 |
YOLOv11-l vs YOLOv12-m | 0.0312 | [−0.0385, 0.1006] | 1.0000 | r = 0.149 |
YOLOv11-l vs YOLOv12-l | 0.0478 | [−0.0145, 0.1090] | 1.0000 | r = 0.395 |
YOLOv11-l vs YOLOv11-x | 0.1448 | [0.0670, 0.2228] | 0.3603 | r = 0.429 |
YOLOv11-l vs YOLOv11-s | −0.0018 | [−0.0807, 0.0778] | 1.0000 | r = −0.083 |
YOLOv11-l vs YOLOv11-n | 0.0247 | [−0.0586, 0.1070] | 1.0000 | r = 0.074 |
YOLOv11-l vs YOLOv11-m | −0.0170 | [−0.0919, 0.0564] | 1.0000 | r = −0.020 |
YOLOv10-x vs YOLOv12-x | −0.1441 | [−0.2206, −0.0681] | 0.1637 | r = −0.507 |
YOLOv10-x vs YOLOv12-s | −0.1164 | [−0.1950, −0.0367] | 1.0000 | r = −0.351 |
YOLOv10-x vs YOLOv12-n | −0.0548 | [−0.1255, 0.0172] | 1.0000 | r = −0.205 |
YOLOv11-m vs YOLOv12-m | 0.0482 | [−0.0330, 0.1304] | 1.0000 | r = 0.143 |
YOLOv11-m vs YOLOv12-n | 0.1278 | [0.0524, 0.2023] | 0.4057 | r = 0.400 |
YOLOv11-m vs YOLOv12-s | 0.0662 | [−0.0091, 0.1428] | 1.0000 | r = 0.296 |
YOLOv11-m vs YOLOv12-x | 0.0385 | [−0.0343, 0.1126] | 1.0000 | r = 0.240 |
YOLOv11-n vs YOLOv11-s | −0.0265 | [−0.1047, 0.0530] | 1.0000 | r = −0.222 |
YOLOv11-n vs YOLOv11-x | 0.1202 | [0.0504, 0.1892] | 0.4186 | r = 0.483 |
YOLOv11-n vs YOLOv12-l | 0.0232 | [−0.0457, 0.0920] | 1.0000 | r = 0.200 |
YOLOv11-n vs YOLOv12-m | 0.0065 | [−0.0704, 0.0835] | 1.0000 | r = 0.094 |
YOLOv11-n vs YOLOv12-n | 0.0861 | [0.0109, 0.1622] | 1.0000 | r = 0.276 |
YOLOv11-n vs YOLOv12-s | 0.0246 | [−0.0620, 0.1113] | 1.0000 | r = 0.129 |
YOLOv11-n vs YOLOv12-x | −0.0032 | [−0.0784, 0.0718] | 1.0000 | r = 0.034 |
YOLOv11-s vs YOLOv11-x | 0.1467 | [0.0708, 0.2244] | 0.1271 | r = 0.410 |
YOLOv11-s vs YOLOv12-l | 0.0496 | [−0.0217, 0.1202] | 1.0000 | r = 0.400 |
YOLOv11-s vs YOLOv12-m | 0.0330 | [−0.0459, 0.1112] | 1.0000 | r = 0.216 |
YOLOv11-s vs YOLOv12-n | 0.1126 | [0.0356, 0.1911] | 1.0000 | r = 0.298 |
YOLOv11-s vs YOLOv12-s | 0.0511 | [−0.0271, 0.1285] | 1.0000 | r = 0.265 |
YOLOv12-s vs YOLOv12-x | −0.0277 | [−0.1024, 0.0472] | 1.0000 | r = −0.102 |
YOLOv12-n vs YOLOv12-x | −0.0893 | [−0.1663, −0.0157] | 1.0000 | r = −0.238 |
YOLOv12-n vs YOLOv12-s | −0.0616 | [−0.1420, 0.0169] | 1.0000 | r = −0.061 |
YOLOv12-m vs YOLOv12-x | −0.0097 | [−0.0849, 0.0644] | 1.0000 | r = 0.018 |
YOLOv12-m vs YOLOv12-s | 0.0180 | [−0.0603, 0.0965] | 1.0000 | r = 0.164 |
YOLOv12-m vs YOLOv12-n | 0.0796 | [0.0070, 0.1534] | 1.0000 | r = 0.200 |
YOLOv12-l vs YOLOv12-x | −0.0263 | [−0.0958, 0.0417] | 1.0000 | r = −0.057 |
YOLOv12-l vs YOLOv12-s | 0.0014 | [−0.0696, 0.0718] | 1.0000 | r = −0.074 |
YOLOv12-l vs YOLOv12-n | 0.0630 | [−0.0069, 0.1334] | 1.0000 | r = 0.220 |
YOLOv12-l vs YOLOv12-m | −0.0166 | [−0.0879, 0.0565] | 1.0000 | r = −0.069 |
YOLOv11-x vs YOLOv12-x | −0.1233 | [−0.1904, −0.0580] | 0.1348 | r = −0.458 |
YOLOv11-x vs YOLOv12-s | −0.0956 | [−0.1717, −0.0205] | 1.0000 | r = −0.311 |
Comparison | (mean) | 95% CI | Effect | |
---|---|---|---|---|
YOLOv11-x vs YOLOv12-n | −0.0340 | [−0.1039, 0.0356] | 1.0000 | r = −0.171 |
YOLOv11-x vs YOLOv12-m | −0.1136 | [−0.1880, −0.0389] | 0.8720 | r = −0.377 |
YOLOv11-x vs YOLOv12-l | −0.0970 | [−0.1649, −0.0305] | 1.0000 | r = −0.368 |
YOLOv11-s vs YOLOv12-x | 0.0233 | [−0.0458, 0.0923] | 1.0000 | r = 0.083 |
precision | ||||
YOLOv10-l vs YOLOv10-n | −0.0006 | [−0.0657, 0.0638] | 1.0000 | r = 0.000 |
YOLOv10-l vs YOLOv10-s | −0.0705 | [−0.1417, −0.0010] | 1.0000 | r = −0.342 |
YOLOv10-l vs YOLOv10-x | 0.0337 | [−0.0270, 0.0950] | 1.0000 | r = 0.086 |
YOLOv10-l vs YOLOv11-l | −0.1689 | [−0.2357, −0.1018] | 0.0023 | r = −0.449 |
YOLOv10-l vs YOLOv11-m | −0.1945 | [−0.2711, −0.1214] | 0.0019 | r = −0.472 |
YOLOv10-l vs YOLOv11-n | −0.1380 | [−0.2146, −0.0640] | 0.3564 | r = −0.412 |
YOLOv10-l vs YOLOv11-s | −0.1754 | [−0.2594, −0.0932] | 0.0361 | r = −0.351 |
YOLOv10-l vs YOLOv11-x | −0.0114 | [−0.0842, 0.0597] | 1.0000 | r = 0.127 |
YOLOv10-l vs YOLOv12-l | −0.1062 | [−0.1764, −0.0359] | 1.0000 | r = −0.333 |
YOLOv10-l vs YOLOv12-m | −0.1344 | [−0.2042, −0.0660] | 0.0855 | r = −0.403 |
YOLOv10-l vs YOLOv12-n | −0.0337 | [−0.1020, 0.0346] | 1.0000 | r = −0.127 |
YOLOv10-l vs YOLOv12-s | −0.1243 | [−0.2075, −0.0432] | 1.0000 | r = −0.165 |
YOLOv10-l vs YOLOv12-x | −0.1457 | [−0.2242, −0.0686] | 0.2337 | r = −0.359 |
YOLOv10-m vs YOLOv10-n | 0.0577 | [0.0026, 0.1151] | 1.0000 | r = 0.258 |
YOLOv10-m vs YOLOv10-s | −0.0122 | [−0.0777, 0.0521] | 1.0000 | r = −0.062 |
YOLOv10-m vs YOLOv10-x | 0.0920 | [0.0294, 0.1533] | 1.0000 | r = 0.343 |
YOLOv10-m vs YOLOv11-l | −0.1106 | [−0.1926, −0.0277] | 1.0000 | r = −0.460 |
YOLOv10-m vs YOLOv11-m | −0.1362 | [−0.2154, −0.0556] | 0.4671 | r = −0.458 |
YOLOv10-m vs YOLOv11-n | −0.0797 | [−0.1509, −0.0093] | 1.0000 | r = −0.283 |
YOLOv10-m vs YOLOv11-s | −0.1171 | [−0.2043, −0.0321] | 1.0000 | r = −0.267 |
YOLOv10-m vs YOLOv11-x | 0.0469 | [−0.0231, 0.1171] | 1.0000 | r = 0.186 |
YOLOv10-m vs YOLOv12-l | −0.0479 | [−0.1138, 0.0186] | 1.0000 | r = −0.200 |
YOLOv10-m vs YOLOv12-m | −0.0761 | [−0.1530, 0.0024] | 1.0000 | r = −0.258 |
YOLOv10-m vs YOLOv12-n | 0.0246 | [−0.0448, 0.0947] | 1.0000 | r = −0.079 |
YOLOv10-m vs YOLOv12-s | −0.0660 | [−0.1493, 0.0182] | 1.0000 | r = −0.262 |
YOLOv10-m vs YOLOv12-x | −0.0874 | [−0.1629, −0.0123] | 1.0000 | r = −0.279 |
YOLOv10-n vs YOLOv10-s | −0.0698 | [−0.1290, −0.0122] | 1.0000 | r = −0.333 |
YOLOv10-n vs YOLOv10-x | 0.0343 | [−0.0233, 0.0918] | 1.0000 | r = 0.206 |
YOLOv10-n vs YOLOv11-l | −0.1683 | [−0.2418, −0.0953] | 0.0183 | r = −0.493 |
YOLOv10-n vs YOLOv11-m | −0.1938 | [−0.2689, −0.1212] | 0.0009 | r = −0.493 |
YOLOv10-n vs YOLOv11-n | −0.1374 | [−0.2071, −0.0671] | 0.0917 | r = −0.417 |
YOLOv10-n vs YOLOv11-s | −0.1747 | [−0.2561, −0.0942] | 0.0232 | r = −0.444 |
YOLOv10-s vs YOLOv12-s | −0.0539 | [−0.1281, 0.0233] | 1.0000 | r = −0.143 |
YOLOv10-s vs YOLOv12-n | 0.0368 | [−0.0338, 0.1095] | 1.0000 | r = 0.029 |
YOLOv10-s vs YOLOv12-m | −0.0639 | [−0.1386, 0.0141] | 1.0000 | r = −0.235 |
YOLOv10-s vs YOLOv12-l | −0.0358 | [−0.1034, 0.0349] | 1.0000 | r = −0.175 |
YOLOv10-s vs YOLOv11-x | 0.0591 | [−0.0154, 0.1356] | 1.0000 | r = 0.184 |
YOLOv10-s vs YOLOv11-s | −0.1049 | [−0.1909, −0.0172] | 1.0000 | r = −0.324 |
YOLOv10-s vs YOLOv11-n | −0.0676 | [−0.1436, 0.0099] | 1.0000 | r = −0.313 |
YOLOv10-s vs YOLOv11-m | −0.1240 | [−0.2024, −0.0460] | 0.8329 | r = −0.353 |
YOLOv10-s vs YOLOv11-l | −0.0985 | [−0.1779, −0.0172] | 1.0000 | r = −0.353 |
YOLOv10-s vs YOLOv10-x | 0.1041 | [0.0424, 0.1682] | 1.0000 | r = 0.361 |
YOLOv10-n vs YOLOv12-x | −0.1450 | [−0.2114, −0.0790] | 0.0268 | r = −0.507 |
YOLOv10-n vs YOLOv12-s | −0.1237 | [−0.2062, −0.0442] | 1.0000 | r = −0.342 |
YOLOv10-n vs YOLOv12-n | −0.0330 | [−0.0900, 0.0229] | 1.0000 | r = −0.182 |
YOLOv10-n vs YOLOv12-m | −0.1337 | [−0.2057, −0.0591] | 0.2575 | r = −0.333 |
YOLOv10-n vs YOLOv12-l | −0.1056 | [−0.1669, −0.0447] | 0.6134 | r = −0.355 |
YOLOv10-n vs YOLOv11-x | −0.0107 | [−0.0718, 0.0523] | 1.0000 | r = 0.000 |
YOLOv10-s vs YOLOv12-x | −0.0752 | [−0.1539, 0.0057] | 1.0000 | r = −0.260 |
YOLOv10-x vs YOLOv11-l | −0.2026 | [−0.2758, −0.1287] | 0.0004 | r = −0.472 |
YOLOv10-x vs YOLOv11-m | −0.2282 | [−0.3096, −0.1451] | 0.0004 | r = −0.514 |
YOLOv10-x vs YOLOv11-n | −0.1717 | [−0.2458, −0.0985] | 0.0145 | r = −0.463 |
YOLOv10-x vs YOLOv11-s | −0.2090 | [−0.2885, −0.1285] | 0.0011 | r = −0.541 |
YOLOv10-x vs YOLOv11-x | −0.0451 | [−0.1094, 0.0178] | 1.0000 | r = −0.086 |
YOLOv10-x vs YOLOv12-l | −0.1399 | [−0.2156, −0.0658] | 0.2277 | r = −0.397 |
Comparison | (mean) | 95% CI | Effect | |
---|---|---|---|---|
YOLOv10-x vs YOLOv12-m | −0.1680 | [−0.2310, −0.1059] | 0.0009 | r = −0.429 |
YOLOv10-x vs YOLOv12-n | −0.0673 | [−0.1374, 0.0033] | 1.0000 | r = −0.205 |
YOLOv10-x vs YOLOv12-s | −0.1580 | [−0.2356, −0.0802] | 0.1132 | r = −0.351 |
YOLOv10-x vs YOLOv12-x | −0.1794 | [−0.2569, −0.1027] | 0.0065 | r = −0.507 |
YOLOv11-l vs YOLOv11-m | −0.0256 | [−0.1024, 0.0499] | 1.0000 | r = −0.020 |
YOLOv11-l vs YOLOv11-n | 0.0309 | [−0.0514, 0.1137] | 1.0000 | r = 0.074 |
YOLOv11-l vs YOLOv11-s | −0.0064 | [−0.0845, 0.0727] | 1.0000 | r = −0.083 |
YOLOv11-l vs YOLOv11-x | 0.1575 | [0.0774, 0.2375] | 0.1262 | r = 0.452 |
YOLOv11-l vs YOLOv12-l | 0.0627 | [0.0009, 0.1235] | 1.0000 | r = 0.395 |
YOLOv12-l vs YOLOv12-n | 0.0726 | [0.0020, 0.1450] | 1.0000 | r = 0.233 |
YOLOv12-l vs YOLOv12-m | −0.0281 | [−0.1020, 0.0477] | 1.0000 | r = −0.069 |
YOLOv11-x vs YOLOv12-x | −0.1343 | [−0.2046, −0.0672] | 0.0864 | r = −0.483 |
YOLOv11-x vs YOLOv12-s | −0.1129 | [−0.1889, −0.0363] | 1.0000 | r = −0.311 |
YOLOv11-x vs YOLOv12-n | −0.0223 | [−0.0941, 0.0499] | 1.0000 | r = −0.171 |
YOLOv11-x vs YOLOv12-m | −0.1230 | [−0.1961, −0.0489] | 0.3365 | r = −0.400 |
YOLOv11-x vs YOLOv12-l | −0.0948 | [−0.1654, −0.0249] | 1.0000 | r = −0.393 |
YOLOv11-s vs YOLOv12-x | 0.0297 | [−0.0433, 0.1032] | 1.0000 | r = 0.083 |
YOLOv11-s vs YOLOv12-s | 0.0510 | [−0.0307, 0.1317] | 1.0000 | r = 0.265 |
YOLOv11-s vs YOLOv12-n | 0.1417 | [0.0647, 0.2194] | 0.2674 | r = 0.310 |
YOLOv11-s vs YOLOv12-m | 0.0410 | [−0.0385, 0.1191] | 1.0000 | r = 0.216 |
YOLOv11-s vs YOLOv12-l | 0.0691 | [−0.0065, 0.1438] | 1.0000 | r = 0.400 |
YOLOv11-s vs YOLOv11-x | 0.1640 | [0.0860, 0.2435] | 0.0477 | r = 0.433 |
YOLOv11-n vs YOLOv12-x | −0.0077 | [−0.0853, 0.0690] | 1.0000 | r = 0.034 |
YOLOv11-n vs YOLOv12-s | 0.0137 | [−0.0750, 0.1019] | 1.0000 | r = 0.129 |
YOLOv11-n vs YOLOv12-n | 0.1044 | [0.0289, 0.1814] | 1.0000 | r = 0.276 |
YOLOv11-n vs YOLOv12-m | 0.0037 | [−0.0751, 0.0835] | 1.0000 | r = 0.094 |
YOLOv11-n vs YOLOv12-l | 0.0318 | [−0.0367, 0.1023] | 1.0000 | r = 0.200 |
YOLOv11-n vs YOLOv11-x | 0.1266 | [0.0565, 0.1963] | 0.1529 | r = 0.483 |
YOLOv11-n vs YOLOv11-s | −0.0373 | [−0.1159, 0.0442] | 1.0000 | r = −0.222 |
YOLOv11-m vs YOLOv12-x | 0.0488 | [−0.0244, 0.1229] | 1.0000 | r = 0.280 |
YOLOv11-m vs YOLOv12-s | 0.0702 | [−0.0075, 0.1489] | 1.0000 | r = 0.296 |
YOLOv11-m vs YOLOv12-n | 0.1608 | [0.0833, 0.2384] | 0.0394 | r = 0.410 |
YOLOv11-m vs YOLOv12-m | 0.0601 | [−0.0194, 0.1408] | 1.0000 | r = 0.143 |
YOLOv11-m vs YOLOv12-l | 0.0883 | [0.0205, 0.1565] | 1.0000 | r = 0.440 |
YOLOv11-m vs YOLOv11-x | 0.1831 | [0.1073, 0.2620] | 0.0090 | r = 0.508 |
YOLOv11-m vs YOLOv11-s | 0.0191 | [−0.0596, 0.0999] | 1.0000 | r = 0.040 |
YOLOv11-m vs YOLOv11-n | 0.0565 | [−0.0221, 0.1345] | 1.0000 | r = 0.115 |
YOLOv11-l vs YOLOv12-x | 0.0232 | [−0.0635, 0.1102] | 1.0000 | r = 0.120 |
YOLOv11-l vs YOLOv12-s | 0.0446 | [−0.0409, 0.1268] | 1.0000 | r = 0.214 |
YOLOv11-l vs YOLOv12-n | 0.1353 | [0.0608, 0.2080] | 0.1882 | r = 0.448 |
YOLOv11-l vs YOLOv12-m | 0.0346 | [−0.0352, 0.1046] | 1.0000 | r = 0.149 |
YOLOv12-l vs YOLOv12-s | −0.0181 | [−0.0910, 0.0537] | 1.0000 | r = −0.074 |
YOLOv12-l vs YOLOv12-x | −0.0395 | [−0.1115, 0.0315] | 1.0000 | r = −0.057 |
YOLOv12-m vs YOLOv12-n | 0.1007 | [0.0309, 0.1712] | 1.0000 | r = 0.212 |
YOLOv12-m vs YOLOv12-s | 0.0100 | [−0.0672, 0.0875] | 1.0000 | r = 0.164 |
YOLOv12-m vs YOLOv12-x | −0.0113 | [−0.0863, 0.0643] | 1.0000 | r = 0.018 |
YOLOv12-n vs YOLOv12-s | −0.0907 | [−0.1717, −0.0109] | 1.0000 | r = −0.108 |
YOLOv12-n vs YOLOv12-x | −0.1120 | [−0.1918, −0.0365] | 1.0000 | r = −0.250 |
YOLOv12-s vs YOLOv12-x | −0.0214 | [−0.1005, 0.0566] | 1.0000 | r = −0.102 |
YOLOv10-b vs YOLOv11-s | −0.1290 | [−0.2172, −0.0415] | 1.0000 | r = −0.361 |
YOLOv10-b vs YOLOv11-x | 0.0350 | [−0.0439, 0.1133] | 1.0000 | r = 0.159 |
YOLOv10-b vs YOLOv12-l | −0.0598 | [−0.1303, 0.0096] | 1.0000 | r = −0.207 |
YOLOv10-b vs YOLOv12-m | −0.0880 | [−0.1620, −0.0152] | 1.0000 | r = −0.290 |
YOLOv10-b vs YOLOv12-n | 0.0127 | [−0.0524, 0.0773] | 1.0000 | r = 0.000 |
YOLOv10-b vs YOLOv12-s | −0.0779 | [−0.1528, 0.0006] | 1.0000 | r = −0.302 |
YOLOv10-b vs YOLOv12-x | −0.0993 | [−0.1734, −0.0264] | 1.0000 | r = −0.312 |
YOLOv10-l vs YOLOv10-m | −0.0583 | [−0.1296, 0.0115] | 1.0000 | r = −0.143 |
YOLOv10-b vs YOLOv10-l | 0.0464 | [−0.0192, 0.1126] | 1.0000 | r = 0.238 |
YOLOv10-b vs YOLOv10-m | −0.0119 | [−0.0849, 0.0596] | 1.0000 | r = 0.036 |
Comparison | (mean) | 95% CI | Effect | |
---|---|---|---|---|
YOLOv10-b vs YOLOv10-n | 0.0458 | [−0.0134, 0.1048] | 1.0000 | r = 0.265 |
YOLOv10-b vs YOLOv10-s | −0.0241 | [−0.0976, 0.0476] | 1.0000 | r = −0.151 |
YOLOv10-b vs YOLOv10-x | 0.0801 | [0.0090, 0.1514] | 1.0000 | r = 0.297 |
YOLOv10-b vs YOLOv11-l | −0.1225 | [−0.1997, −0.0425] | 1.0000 | r = −0.424 |
YOLOv10-b vs YOLOv11-m | −0.1481 | [−0.2233, −0.0735] | 0.0838 | r = −0.429 |
YOLOv10-b vs YOLOv11-n | −0.0916 | [−0.1672, −0.0161] | 1.0000 | r = −0.262 |
recall | ||||
YOLOv12-l vs YOLOv12-s | 0.0409 | [−0.0455, 0.1227] | 1.0000 | r = 0.200 |
YOLOv12-l vs YOLOv12-x | −0.0136 | [−0.0955, 0.0682] | 1.0000 | r = −0.040 |
YOLOv12-m vs YOLOv12-n | −0.0182 | [−0.1227, 0.0818] | 1.0000 | r = −0.056 |
YOLOv12-m vs YOLOv12-s | 0.0182 | [−0.0773, 0.1091] | 1.0000 | r = 0.097 |
YOLOv12-m vs YOLOv12-x | −0.0364 | [−0.1273, 0.0545] | 1.0000 | r = −0.111 |
YOLOv12-n vs YOLOv12-s | 0.0364 | [−0.0591, 0.1318] | 1.0000 | r = 0.152 |
YOLOv12-n vs YOLOv12-x | −0.0182 | [−0.1091, 0.0727] | 1.0000 | r = −0.071 |
YOLOv12-s vs YOLOv12-x | −0.0545 | [−0.1364, 0.0273] | 1.0000 | r = −0.273 |
YOLOv10-b vs YOLOv11-n | 0.0091 | [−0.0864, 0.1091] | 1.0000 | r = 0.030 |
YOLOv10-b vs YOLOv11-m | −0.0227 | [−0.1045, 0.0636] | 1.0000 | r = −0.083 |
YOLOv10-b vs YOLOv11-l | 0.0000 | [−0.0909, 0.0909] | 1.0000 | r = −0.037 |
YOLOv10-b vs YOLOv10-x | −0.0091 | [−0.1045, 0.0864] | 1.0000 | r = 0.032 |
YOLOv10-b vs YOLOv10-s | −0.0818 | [−0.1773, 0.0136] | 1.0000 | r = −0.312 |
YOLOv10-b vs YOLOv10-n | −0.0318 | [−0.1227, 0.0545] | 1.0000 | r = −0.111 |
YOLOv10-b vs YOLOv10-m | 0.0364 | [−0.0545, 0.1273] | 1.0000 | r = 0.143 |
YOLOv10-b vs YOLOv10-l | −0.0409 | [−0.1273, 0.0456] | 1.0000 | r = −0.154 |
YOLOv12-l vs YOLOv12-n | 0.0045 | [−0.0818, 0.0909] | 1.0000 | r = 0.000 |
YOLOv12-l vs YOLOv12-m | 0.0227 | [−0.0636, 0.1091] | 1.0000 | r = 0.077 |
YOLOv11-x vs YOLOv12-x | −0.0682 | [−0.1500, 0.0136] | 1.0000 | r = −0.280 |
YOLOv11-x vs YOLOv12-s | −0.0136 | [−0.1091, 0.0818] | 1.0000 | r = −0.032 |
YOLOv11-x vs YOLOv12-n | −0.0500 | [−0.1409, 0.0455] | 1.0000 | r = −0.200 |
YOLOv11-x vs YOLOv12-m | −0.0318 | [−0.1273, 0.0636] | 1.0000 | r = −0.118 |
YOLOv11-x vs YOLOv12-l | −0.0545 | [−0.1364, 0.0273] | 1.0000 | r = −0.273 |
YOLOv11-s vs YOLOv12-x | −0.0364 | [−0.1182, 0.0455] | 1.0000 | r = −0.238 |
YOLOv10-l vs YOLOv11-x | 0.0864 | [−0.0182, 0.1909] | 1.0000 | r = 0.243 |
YOLOv10-l vs YOLOv11-s | 0.0545 | [−0.0500, 0.1545] | 1.0000 | r = 0.167 |
YOLOv10-l vs YOLOv11-n | 0.0500 | [−0.0455, 0.1455] | 1.0000 | r = 0.161 |
YOLOv10-l vs YOLOv11-m | 0.0182 | [−0.0773, 0.1136] | 1.0000 | r = 0.062 |
YOLOv10-l vs YOLOv11-l | 0.0409 | [−0.0500, 0.1318] | 1.0000 | r = 0.103 |
YOLOv10-l vs YOLOv10-x | 0.0318 | [−0.0591, 0.1227] | 1.0000 | r = 0.185 |
YOLOv10-l vs YOLOv10-s | −0.0409 | [−0.1409, 0.0591] | 1.0000 | r = −0.176 |
YOLOv10-l vs YOLOv10-n | 0.0091 | [−0.0864, 0.1000] | 1.0000 | r = 0.034 |
YOLOv10-l vs YOLOv10-m | 0.0773 | [−0.0227, 0.1727] | 1.0000 | r = 0.250 |
YOLOv10-b vs YOLOv12-x | −0.0227 | [−0.1182, 0.0727] | 1.0000 | r = −0.071 |
YOLOv10-b vs YOLOv12-s | 0.0318 | [−0.0591, 0.1273] | 1.0000 | r = 0.133 |
YOLOv10-b vs YOLOv12-n | −0.0045 | [−0.1000, 0.0909] | 1.0000 | r = −0.030 |
YOLOv10-b vs YOLOv12-m | 0.0136 | [−0.0818, 0.1091] | 1.0000 | r = 0.034 |
YOLOv10-b vs YOLOv12-l | −0.0091 | [−0.0909, 0.0727] | 1.0000 | r = −0.043 |
YOLOv10-b vs YOLOv11-x | 0.0455 | [−0.0545, 0.1455] | 1.0000 | r = 0.143 |
YOLOv10-b vs YOLOv11-s | 0.0136 | [−0.0818, 0.1091] | 1.0000 | r = 0.067 |
YOLOv10-s vs YOLOv11-l | 0.0818 | [−0.0136, 0.1818] | 1.0000 | r = 0.290 |
YOLOv10-s vs YOLOv10-x | 0.0727 | [−0.0273, 0.1682] | 1.0000 | r = 0.294 |
YOLOv10-n vs YOLOv12-x | 0.0091 | [−0.0727, 0.0909] | 1.0000 | r = 0.043 |
YOLOv10-n vs YOLOv12-s | 0.0636 | [−0.0273, 0.1545] | 1.0000 | r = 0.259 |
YOLOv10-n vs YOLOv12-n | 0.0273 | [−0.0591, 0.1182] | 1.0000 | r = 0.071 |
YOLOv10-n vs YOLOv12-m | 0.0455 | [−0.0545, 0.1500] | 1.0000 | r = 0.111 |
YOLOv10-n vs YOLOv12-l | 0.0227 | [−0.0591, 0.1045] | 1.0000 | r = 0.091 |
YOLOv10-n vs YOLOv11-x | 0.0773 | [−0.0136, 0.1682] | 1.0000 | r = 0.267 |
YOLOv10-n vs YOLOv11-s | 0.0455 | [−0.0500, 0.1365] | 1.0000 | r = 0.172 |
YOLOv10-n vs YOLOv11-n | 0.0409 | [−0.0500, 0.1318] | 1.0000 | r = 0.143 |
YOLOv10-n vs YOLOv11-m | 0.0091 | [−0.0818, 0.0955] | 1.0000 | r = 0.037 |
YOLOv10-n vs YOLOv11-l | 0.0318 | [−0.0591, 0.1227] | 1.0000 | r = 0.071 |
YOLOv10-n vs YOLOv10-x | 0.0227 | [−0.0682, 0.1136] | 1.0000 | r = 0.133 |
Comparison | (mean) | 95% CI | Effect | |
---|---|---|---|---|
YOLOv10-n vs YOLOv10-s | −0.0500 | [−0.1409, 0.0409] | 1.0000 | r = −0.231 |
YOLOv10-m vs YOLOv12-x | −0.0591 | [−0.1501, 0.0364] | 1.0000 | r = −0.161 |
YOLOv10-m vs YOLOv12-s | −0.0045 | [−0.0955, 0.0909] | 1.0000 | r = 0.000 |
YOLOv10-m vs YOLOv12-n | −0.0409 | [−0.1409, 0.0591] | 1.0000 | r = −0.143 |
YOLOv10-m vs YOLOv12-m | −0.0227 | [−0.1182, 0.0727] | 1.0000 | r = −0.103 |
YOLOv10-m vs YOLOv12-l | −0.0455 | [−0.1227, 0.0318] | 1.0000 | r = −0.238 |
YOLOv10-m vs YOLOv11-x | 0.0091 | [−0.0773, 0.1000] | 1.0000 | r = 0.037 |
YOLOv10-m vs YOLOv11-s | −0.0227 | [−0.1227, 0.0727] | 1.0000 | r = −0.059 |
YOLOv10-m vs YOLOv11-n | −0.0273 | [−0.1136, 0.0591] | 1.0000 | r = −0.120 |
YOLOv10-m vs YOLOv11-m | −0.0591 | [−0.1500, 0.0318] | 1.0000 | r = −0.200 |
YOLOv10-m vs YOLOv11-l | −0.0364 | [−0.1318, 0.0591] | 1.0000 | r = −0.161 |
YOLOv10-m vs YOLOv10-x | −0.0455 | [−0.1364, 0.0455] | 1.0000 | r = −0.097 |
YOLOv10-m vs YOLOv10-s | −0.1182 | [−0.2000, −0.0364] | 1.0000 | r = −0.583 |
YOLOv10-m vs YOLOv10-n | −0.0682 | [−0.1455, 0.0136] | 1.0000 | r = −0.304 |
YOLOv10-l vs YOLOv12-x | 0.0182 | [−0.0864, 0.1227] | 1.0000 | r = 0.081 |
YOLOv10-l vs YOLOv12-s | 0.0727 | [−0.0364, 0.1774] | 1.0000 | r = 0.200 |
YOLOv10-l vs YOLOv12-n | 0.0364 | [−0.0636, 0.1364] | 1.0000 | r = 0.086 |
YOLOv10-l vs YOLOv12-m | 0.0545 | [−0.0409, 0.1455] | 1.0000 | r = 0.172 |
YOLOv10-l vs YOLOv12-l | 0.0318 | [−0.0591, 0.1227] | 1.0000 | r = 0.103 |
YOLOv10-s vs YOLOv11-m | 0.0591 | [−0.0273, 0.1455] | 1.0000 | r = 0.259 |
YOLOv10-s vs YOLOv11-n | 0.0909 | [−0.0045, 0.1864] | 1.0000 | r = 0.355 |
YOLOv10-s vs YOLOv11-s | 0.0955 | [0.0045, 0.1864] | 1.0000 | r = 0.379 |
YOLOv10-s vs YOLOv11-x | 0.1273 | [0.0227, 0.2273] | 1.0000 | r = 0.405 |
YOLOv10-s vs YOLOv12-l | 0.0727 | [−0.0091, 0.1545] | 1.0000 | r = 0.391 |
YOLOv10-s vs YOLOv12-m | 0.0955 | [−0.0045, 0.1955] | 1.0000 | r = 0.314 |
YOLOv10-s vs YOLOv12-n | 0.0773 | [−0.0273, 0.1818] | 1.0000 | r = 0.222 |
YOLOv10-s vs YOLOv12-s | 0.1136 | [0.0273, 0.2000] | 1.0000 | r = 0.481 |
YOLOv10-s vs YOLOv12-x | 0.0591 | [−0.0273, 0.1455] | 1.0000 | r = 0.259 |
YOLOv10-x vs YOLOv11-l | 0.0091 | [−0.0864, 0.1045] | 1.0000 | r = −0.059 |
YOLOv10-x vs YOLOv11-m | −0.0136 | [−0.1045, 0.0773] | 1.0000 | r = −0.103 |
YOLOv10-x vs YOLOv11-n | 0.0182 | [−0.0773, 0.1136] | 1.0000 | r = 0.000 |
YOLOv10-x vs YOLOv11-s | 0.0227 | [−0.0727, 0.1182] | 1.0000 | r = 0.032 |
YOLOv10-x vs YOLOv11-x | 0.0545 | [−0.0455, 0.1545] | 1.0000 | r = 0.143 |
YOLOv10-x vs YOLOv12-l | 0.0000 | [−0.0955, 0.0955] | 1.0000 | r = −0.062 |
YOLOv10-x vs YOLOv12-m | 0.0227 | [−0.0727, 0.1182] | 1.0000 | r = 0.000 |
YOLOv11-m vs YOLOv12-l | 0.0136 | [−0.0591, 0.0864] | 1.0000 | r = 0.053 |
YOLOv11-m vs YOLOv11-x | 0.0682 | [−0.0227, 0.1591] | 1.0000 | r = 0.241 |
YOLOv11-m vs YOLOv11-s | 0.0364 | [−0.0455, 0.1182] | 1.0000 | r = 0.182 |
YOLOv11-m vs YOLOv11-n | 0.0318 | [−0.0500, 0.1182] | 1.0000 | r = 0.120 |
YOLOv11-l vs YOLOv12-x | −0.0227 | [−0.1136, 0.0682] | 1.0000 | r = −0.071 |
YOLOv11-l vs YOLOv12-s | 0.0318 | [−0.0591, 0.1227] | 1.0000 | r = 0.172 |
YOLOv11-l vs YOLOv12-n | −0.0045 | [−0.0864, 0.0773] | 1.0000 | r = 0.000 |
YOLOv11-l vs YOLOv12-m | 0.0136 | [−0.0682, 0.0955] | 1.0000 | r = 0.091 |
YOLOv11-l vs YOLOv12-l | −0.0091 | [−0.0818, 0.0636] | 1.0000 | r = 0.000 |
YOLOv11-l vs YOLOv11-x | 0.0455 | [−0.0455, 0.1364] | 1.0000 | r = 0.200 |
YOLOv11-l vs YOLOv11-s | 0.0136 | [−0.0773, 0.1045] | 1.0000 | r = 0.103 |
YOLOv11-l vs YOLOv11-n | 0.0091 | [−0.0864, 0.1045] | 1.0000 | r = 0.067 |
YOLOv11-l vs YOLOv11-m | −0.0227 | [−0.1091, 0.0636] | 1.0000 | r = −0.040 |
YOLOv10-x vs YOLOv12-x | −0.0136 | [−0.1091, 0.0818] | 1.0000 | r = −0.062 |
YOLOv10-x vs YOLOv12-s | 0.0409 | [−0.0591, 0.1409] | 1.0000 | r = 0.086 |
YOLOv10-x vs YOLOv12-n | 0.0045 | [−0.0955, 0.1045] | 1.0000 | r = −0.029 |
YOLOv11-m vs YOLOv12-m | 0.0364 | [−0.0636, 0.1409] | 1.0000 | r = 0.081 |
YOLOv11-m vs YOLOv12-n | 0.0182 | [−0.0682, 0.1045] | 1.0000 | r = 0.040 |
YOLOv11-m vs YOLOv12-s | 0.0545 | [−0.0364, 0.1455] | 1.0000 | r = 0.214 |
YOLOv11-m vs YOLOv12-x | 0.0000 | [−0.0864, 0.0864] | 1.0000 | r = −0.040 |
YOLOv11-n vs YOLOv11-s | 0.0045 | [−0.0864, 0.0955] | 1.0000 | r = 0.037 |
YOLOv11-n vs YOLOv11-x | 0.0364 | [−0.0545, 0.1273] | 1.0000 | r = 0.143 |
YOLOv11-n vs YOLOv12-l | −0.0182 | [−0.1091, 0.0727] | 1.0000 | r = −0.083 |
YOLOv11-n vs YOLOv12-m | 0.0045 | [−0.0864, 0.0955] | 1.0000 | r = 0.000 |
Comparison | (mean) | 95% CI | Effect | |
---|---|---|---|---|
YOLOv11-n vs YOLOv12-n | −0.0136 | [−0.1000, 0.0727] | 1.0000 | r = −0.077 |
YOLOv11-n vs YOLOv12-s | 0.0227 | [−0.0773, 0.1182] | 1.0000 | r = 0.091 |
YOLOv11-n vs YOLOv12-x | −0.0318 | [−0.1182, 0.0545] | 1.0000 | r = −0.111 |
YOLOv11-s vs YOLOv11-x | 0.0318 | [−0.0545, 0.1227] | 1.0000 | r = 0.111 |
YOLOv11-s vs YOLOv12-l | −0.0227 | [−0.0955, 0.0500] | 1.0000 | r = −0.158 |
YOLOv11-s vs YOLOv12-m | 0.0000 | [−0.0909, 0.0909] | 1.0000 | r = −0.034 |
YOLOv11-s vs YOLOv12-n | −0.0182 | [−0.1136, 0.0773] | 1.0000 | r = −0.103 |
YOLOv11-s vs YOLOv12-s | 0.0182 | [−0.0636, 0.1000] | 1.0000 | r = 0.091 |
References
- Darras, K.F.; Balle, M.; Xu, W.; Yan, Y.; Zakka, V.G.; Toledo-Hernández, M.; Sheng, D.; Lin, W.; Zhang, B.; Lan, Z.; et al. Eyes on nature: Embedded vision cameras for terrestrial biodiversity monitoring. Methods Ecol. Evol. 2024, 15, 2262–2275. [Google Scholar] [CrossRef]
- Ghanem, S.J.; Voigt, C.C. Chapter 7-Increasing Awareness of Ecosystem Services Provided by Bats. In Advances in the Study of Behavior; Brockmann, H.J., Roper, T.J., Naguib, M., Mitani, J.C., Simmons, L.W., Eds.; Academic Press: Cambridge, MA, USA, 2012; Volume 44, pp. 279–302. [Google Scholar] [CrossRef]
- Corrêa Scheffer, K.; Fernandes De Barros, R.; Iamamoto, K.; Mori, E.; Miyuki Asano, K.; M Achkar, S.; Estevez Garcia, A.I.; de Oliveira Lima, J.Y.; de Oliveira Fahl, W. Diphylla ecaudata y Diaemus youngi, biología y comportamiento. Diphylla ecaudata and Diaemus youngi, Biology and behavior. ACTA ZOOLÓGICA MEXICANA (N.S.) 2015, 31, 436–445. [Google Scholar] [CrossRef]
- David, O.R.; Consuelo, L.; Eduardo, N.; Livia, L.P. Selección de refugios por tres especies de murciélagos frugívoros (Chiroptera: Phyllostomidae) en la Selva Lacandona, Chiapas, México. Rev. Mex. De Biodivers. 2006, 77, 261–270. [Google Scholar]
- Brigham, R.; Fenton, B. The influence of roost closure on the roosting and foraging behaviour of Eptesicus fuscus (Chiroptera: Vespertilionidae). Can. J. Zool. 2011, 64, 1128–1133. [Google Scholar] [CrossRef]
- Labadie, M.; Morand, S.; Bourgarel, M.; Niama, F.R.; Nguilili, G.F.; Tobi, N.; Caron, A.; De Nys, H. Habitat sharing and interspecies interactions in caves used by bats in the Republic of Congo. PeerJ 2025, 13, e18145. [Google Scholar] [CrossRef]
- Bullen, R.D. A Review of Ghost Bat Ecology, Threats and Survey Requirements; Technical report; Australian Government Department of Agriculture, Water and Environment: Hillarys, Australia, 2002. [Google Scholar]
- Russo, D.; Salinas-Ramos, V.B.; Cistrone, L.; Smeraldo, S.; Bosso, L.; Ancillotto, L. Do We Need to Use Bats as Bioindicators? Biology 2021, 10, 693. [Google Scholar] [CrossRef]
- Frick, W.F.; Kingston, T.; Flanders, J. A review of the major threats and challenges to global bat conservation. Ann. N. Y. Acad. Sci. 2020, 1469, 5–25. [Google Scholar] [CrossRef]
- Platto, S.; Zhou, J.; Wang, Y.; Wang, H.; Carafoli, E. Biodiversity loss and COVID-19 pandemic: The role of bats in the origin and the spreading of the disease. Biochem. Biophys. Res. Commun. 2021, 538, 2–13. [Google Scholar] [CrossRef]
- Kunz, T.H.; Betke, M.; Hristov, N.I.; Vonhof, M.J. Methods for assessing colony size, population size, and relative abundance of bats. In Ecological and Behavioral Methods for the Study of Bats; Johns Hopkins University Press: Baltimore, MD, USA, 2009; pp. 133–157. [Google Scholar]
- Orugas, A.; Pally, I.; Ramos, A.; Gutiérrez, M. Murciélagos: Análisis de su problemática y alternativas de mitigación. Rev. Estud. AGRO-VET 2022, 6, 56–70. [Google Scholar]
- O’Shea, T.J.; Bogan, M.A. Monitoring Trends in Bat Populations of the United States and Territories: Problems and Prospects; U.S. Geological Survey, Biological Resources Discipline, Information and Technology: Reston, VA, USA, 2003. [Google Scholar]
- Whiting, J.C.; Doering, B.; Aho, K.; Bybee, B.F. Disturbance of hibernating bats due to researchers entering caves to conduct hibernacula surveys. Sci. Rep. 2024, 14, 13496. [Google Scholar] [CrossRef]
- Sabol, B.M.; Hudson, M.K. Technique using thermal infrared-imaging for estimating populations of gray bats. J. Mammal. 1995, 76, 1242–1248. [Google Scholar] [CrossRef]
- Hristov, N.I.; Betke, M.; Kunz, T.H. Applications of thermal infrared imaging for research in aeroecology. Integr. Comp. Biol. 2008, 48, 50–59. [Google Scholar] [CrossRef]
- Frank, J.; Kunz, T.; Horn, J.; Cleveland, C.; Petronio, S. Advanced infrared detection and image processing for automated bat censusing. Proc. SPIE—Int. Soc. Opt. Eng. 2003, 5074, 261–271. [Google Scholar] [CrossRef]
- Botto Nuñez, G.; Lemus, G.; Muñoz Wolf, M.; Rodales, A.; González, E.; Crisci, C. The first artificial intelligence algorithm for identification of bat species in Uruguay. Ecol. Inform. 2018, 46, 97–102. [Google Scholar] [CrossRef]
- Mac Aodha, O.; Gibb, R.; Barlow, K.E.; Browning, E.; Firman, M.; Freeman, R.; Harder, B.; Kinsey, L.; Mead, G.R.; Newson, S.E.; et al. Bat detective—Deep learning tools for bat acoustic signal detection. PLoS Comput. Biol. 2018, 14, e1005995. [Google Scholar] [CrossRef] [PubMed]
- Krivek, G.; Gillert, A.; Harder, M.; Fritze, M.; Frankowski, K.; Timm, L.; Meyer-Olbersleben, L.; von Lukas, U.F.; Kerth, G.; van Schaik, J. BatNet: A deep learning-based tool for automated bat species identification from camera trap images. Remote Sens. Ecol. Conserv. 2023, 9, 759–774. [Google Scholar] [CrossRef]
- Fujioka, E.; Fukushiro, M.; Ushio, K.; Kohyama, K.; Habe, H.; Hiryu, S. Three-Dimensional Trajectory Construction and Observation of Group Behavior of Wild Bats During Cave Emergence. J. Robot. Mechatronics 2021, 33, 556–563. [Google Scholar] [CrossRef]
- Darras, K.F.A.; Yusti, E.; Huang, J.C.C.; Zemp, D.C.; Kartono, A.P.; Wanger, T.C. Bat point counts: A novel sampling method shines light on flying bat communities. Ecol. Evol. 2021, 11, 17179–17190. [Google Scholar] [CrossRef]
- Darras, K.; Yusti, E.; Knorr, A.; Huang, J.C.C.; Kartono, A.P. Sampling flying bats with thermal and near-infrared imaging and ultrasound recording: Hardware and workflow for bat point counts. F1000Research 2022, 10, 189. [Google Scholar] [CrossRef]
- Bentley, I.; Gebran, M.; Vorderer, S.; Ralston, J.; Kloepper, L. Utilizing Neural Networks to Resolve Individual Bats and Improve Automated Counts. In Proceedings of the 2023 IEEE World AI IoT Congress (AIIoT), Seattle, WA, USA, 7–10 June 2023; pp. 0112–0119. [Google Scholar] [CrossRef]
- Koger, B.; Hurme, E.; Costelloe, B.R.; O’Mara, M.T.; Wikelski, M.; Kays, R.; Dechmann, D.K. An automated approach for counting groups of flying animals applied to one of the world’s largest bat colonies. Ecosphere 2023, 14, e4590. [Google Scholar] [CrossRef]
- Wang, Y.; Ma, C.; Zhao, C.; Xia, H.; Chen, C.; Zhang, Y. WB-YOLO: An efficient wild bat detection method for ecological monitoring in complex environments. Eng. Appl. Artif. Intell. 2025, 157, 111232. [Google Scholar] [CrossRef]
- Lee, B.; Sambado, S.; Farrant, D.N.; Boser, A.; Ring, K.; Hyon, D.; Larsen, A.E.; MacDonald, A.J. Novel Bat-Monitoring Dataset Reveals Targeted Foraging With Agricultural and Pest Control Implications. Ecol. Evol. 2025, 15, e70819. [Google Scholar] [CrossRef] [PubMed]
- Rangel, I.C.; Arroyo-Romero, J.A.; Bárcenas-Reyes, I.; González-Barbosa, J.J.; Hurtado-Ramos, J.B.; Ornelas-Rodríguez, F.J.; Ramírez-Pedraza, A. Explorando las Profundidades: Reconstrucción de Cuevas y Detección de Murciélagos mediante Imágenes Infrarrojas. Mem. Investig. En Ing. 2025, 1, 110–125. [Google Scholar] [CrossRef]
- Amézquita-Gómez, N.; González-Bautista, S.R.; Teran, M.; Salazar, C.; Corredor, J.; Corzo, G.D. Preliminary Approach for UAV-Based Multi-Sensor Platforms for Reconnaissance and Surveillance applications. Ingeniería 2023, 28, e21035. [Google Scholar] [CrossRef]
- Gutchess, D.; Trajkovics, M.; Cohen-Solal, E.; Lyons, D.; Jain, A. A background model initialization algorithm for video surveillance. In Proceedings of the Eighth IEEE International Conference on Computer Vision. ICCV 2001, Vancouver, BC, Canada, 7–14 July 2001; Volume 1, pp. 733–740. [Google Scholar] [CrossRef]
- Tai, J.C.; Song, K.T. Background segmentation and its application to traffic monitoring using modified histogram. In Proceedings of the IEEE International Conference on Networking, Sensing and Control, New Delhi, India, 21–23 March 2004; Volume 1, pp. 13–18. [Google Scholar] [CrossRef]
- Stauffer, C.; Grimson, W. Adaptive background mixture models for real-time tracking. In Proceedings of the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), Fort Collins, CO, USA, 23–25 June 1999; Volume 2, pp. 246–252. [Google Scholar] [CrossRef]
- Ramírez-Pedraza, A.; Salazar-Colores, S.; Terven, J.; Romero-González, J.A.; González-Barbosa, J.J.; Córdova-Esparza, D.M. Nutritional Monitoring of Rhodena Lettuce via Neural Networks and Point Cloud Analysis. AgriEngineering 2024, 6, 3474–3493. [Google Scholar] [CrossRef]
- Ramírez-Pedraza, A.; Salazar-Colores, S.; Cardenas-Valle, C.; Terven, J.; González-Barbosa, J.J.; Ornelas-Rodriguez, F.J.; Hurtado-Ramos, J.B.; Ramirez-Pedraza, R.; Córdova-Esparza, D.M.; Romero-González, J.A. Deep Learning in Oral Hygiene: Automated Dental Plaque Detection via YOLO Frameworks and Quantification Using the O’Leary Index. Diagnostics 2025, 15, 231. [Google Scholar] [CrossRef] [PubMed]
- Wang, A.; Chen, H.; Liu, L.; Chen, K.; Lin, Z.; Han, J.; Ding, G. YOLOv10: Real-Time End-to-End Object Detection. Adv. Neural Inf. Process. Syst. 2024, 37, 107984–108011. [Google Scholar]
- Khanam, R.; Hussain, M. YOLOv11: An Overview of the Key Architectural Enhancements. arXiv 2024, arXiv:2410.17725. [Google Scholar] [CrossRef]
- Tian, Y.; Ye, Q.; Doermann, D. YOLOv12: Attention-Centric Real-Time Object Detectors. arXiv 2025, arXiv:2502.12524. [Google Scholar]
- Chen, X.; Zhao, J.; hua Chen, Y.; Zhou, W.; Hughes, A.C. Automatic standardized processing and identification of tropical bat calls using deep learning approaches. Biol. Conserv. 2020, 241, 108269. [Google Scholar] [CrossRef]
- Hernández, B.O.; Sánchez-García, Á.J.; Alfonso, C.A.D.; Ocharán-Hernández, J.O.; Ortiz, E.M.; Ríos-Figueroa, H.V. Desarrollo de una aplicación para el conteo automático de murciélagos en cuevas basado en visión por computadora. Res. Comput. Sci. 2018, 147, 11–22. [Google Scholar] [CrossRef]
- Aza Taimal, J.J.; Bacca Cortes, B.; Restrepo Girón, A.D. Software Tool for the Extrinsic Calibration of Infrared and RGBD Cameras Applied to Thermographic Inspection. Ingeniería 2022, 28, e18145. [Google Scholar] [CrossRef]
- Rodríguez-Lira, D.C.; Córdova-Esparza, D.M.; Terven, J.; Romero-González, J.A.; Alvarez-Alvarado, J.M.; González-Barbosa, J.J.; Ramírez-Pedraza, A. Recent Developments in Image-Based 3D Reconstruction Using Deep Learning: Methodologies and Applications. Electronics 2025, 14, 3032. [Google Scholar] [CrossRef]
Parameters | Value |
---|---|
Optimizer | auto (AdamW) |
Initial learning rate () | 0.01 |
Final learning rate () | 0.01 (cosine decay) |
Momentum | 0.937 |
Weight decay | 0.0005 |
Warmup epochs | 3.0 |
Warmup momentum | 0.8 |
Warmup bias LR | 0.1 |
Patience (early stopping) | 50 |
Image size () | 640 |
Model-specific parameters | Value |
YOLOv10b | epochs = 200, batch = 32 |
YOLOv11n | epochs = 200, batch = 32 |
YOLOv12s | epochs = 200, batch = 4 |
Detector | Model | Precision | Recall | mAP@50 | mAP@0.75 | mAP@[0.5:0.95] |
---|---|---|---|---|---|---|
YOLOv10 | b | 0.917 | 0.914 | 0.959 | 0.390 | 0.474 |
l | 0.910 | 0.853 | 0.954 | 0.424 | 0.453 | |
m | 0.889 | 0.966 | 0.970 | 0.355 | 0.459 | |
n | 0.911 | 0.879 | 0.946 | 0.349 | 0.447 | |
s | 0.879 | 0.941 | 0.939 | 0.408 | 0.463 | |
x | 0.895 | 0.914 | 0.951 | 0.348 | 0.446 | |
YOLOv11 | n | 0.927 | 0.945 | 0.958 | 0.392 | 0.479 |
l | 0.941 | 0.964 | 0.979 | 0.359 | 0.462 | |
m | 0.937 | 0.951 | 0.970 | 0.389 | 0.471 | |
s | 0.935 | 0.964 | 0.947 | 0.390 | 0.476 | |
x | 0.901 | 0.912 | 0.953 | 0.337 | 0.471 | |
YOLOv12 | n | 0.940 | 0.940 | 0.957 | 0.388 | 0.486 |
l | 0.940 | 0.983 | 0.965 | 0.358 | 0.475 | |
m | 0.956 | 0.983 | 0.981 | 0.378 | 0.471 | |
s | 0.929 | 0.974 | 0.971 | 0.375 | 0.452 | |
x | 0.940 | 0.957 | 0.935 | 0.410 | 0.469 |
Comparison | (mean) | 95% CI | Effect | |
---|---|---|---|---|
YOLOv10-x vs YOLOv11-m | −0.228 | [−0.310, −0.145] | 0.000 | r = −0.514 |
YOLOv10-n vs YOLOv11-m | −0.194 | [−0.269, −0.121] | 0.001 | r = −0.493 |
Images | Images with Errors | FP | FN | Errors (FP+FN) | FP (%) | FN (%) | |
---|---|---|---|---|---|---|---|
YOLOv10 | 110 | 101 | 435 | 2 | 437 | 100 | 0 |
YOLOv11 | 110 | 41 | 108 | 3 | 111 | 97 | 3 |
YOLOv12 | 110 | 57 | 137 | 1 | 138 | 99 | 1 |
Reference | Sensor | Position | Objective | Technique | Accuracy |
---|---|---|---|---|---|
[38] | Acoustic | N/A | Identification tested with 15 species | BatNet and re-checking strategy | 0.91 |
[20] | RGB image triggered by infrared light barriers | Entrance of the hibernacula (caves or mines) | Counting the number of bats and identify 13 European bat species | BatNet | 0.993 |
[21] | Stereo cameras | Front of the cave entrance | Counting | Three-dimensional flight trajectories | 0.94 |
[22] | Thermal, ultrasound, NIR camera | Outdoors relative to the roost site | Counting the number of bats and identifying species | Multimodal detection and analysis approach | N/A |
[39] | RGB images | Inside | Counting | Background subtraction and Otsu segmentation | N/A |
[24] | Infrared, RGB and Thermal videos | Outdoors relative to the roost site | Counting the number of bats | Convolutional neural networks (CNNs) | 0.95–0.99 |
[25] | RGB images | Outdoors around the bat colony | Counting the number of bats | UNet model | 0.88 |
[23] | Thermal, ultrasound, NIR camera | Relative to the river, oil palm, or road | Counting and identification | Morphological-acoustic bat identification | N/A |
[27] | Doppler weather radar | Outdoor and Indoor to the site | Estimating bat foraging distributions and relative bat activity | Bat-Aggregated Time Series (BATS) | N/A |
[26] | RGB images: aerial images and macro photography | Outdoors relative to the roost site | Primarily identifying bat species rather than counting the number of bats | YOLOv7 | 0.94 |
Our work | NIR camera | Inside of the roost site | Counting in each frame | YOLOv10, YOLOv11, YOLOv12 | 0.98 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
González-Barbosa, J.-J.; Rangel, I.C.; Ramírez-Pedraza, A.; Ramírez-Pedraza, R.; Bárcenas-Reyes, I.; González-Barbosa, E.-A.; Razo-Razo, M. Deep Learning for Wildlife Monitoring: Near-Infrared Bat Detection Using YOLO Frameworks. Signals 2025, 6, 46. https://doi.org/10.3390/signals6030046
González-Barbosa J-J, Rangel IC, Ramírez-Pedraza A, Ramírez-Pedraza R, Bárcenas-Reyes I, González-Barbosa E-A, Razo-Razo M. Deep Learning for Wildlife Monitoring: Near-Infrared Bat Detection Using YOLO Frameworks. Signals. 2025; 6(3):46. https://doi.org/10.3390/signals6030046
Chicago/Turabian StyleGonzález-Barbosa, José-Joel, Israel Cruz Rangel, Alfonso Ramírez-Pedraza, Raymundo Ramírez-Pedraza, Isabel Bárcenas-Reyes, Erick-Alejandro González-Barbosa, and Miguel Razo-Razo. 2025. "Deep Learning for Wildlife Monitoring: Near-Infrared Bat Detection Using YOLO Frameworks" Signals 6, no. 3: 46. https://doi.org/10.3390/signals6030046
APA StyleGonzález-Barbosa, J.-J., Rangel, I. C., Ramírez-Pedraza, A., Ramírez-Pedraza, R., Bárcenas-Reyes, I., González-Barbosa, E.-A., & Razo-Razo, M. (2025). Deep Learning for Wildlife Monitoring: Near-Infrared Bat Detection Using YOLO Frameworks. Signals, 6(3), 46. https://doi.org/10.3390/signals6030046