Search Results (22)

Pedestrian detection systems are widely used in safety-critical domains such as autonomous driving, where deep neural networks accurately perceive individuals and distinguish them from other objects. However, their vulnerability to backdoor attacks remains understudied. Existing backdoor attacks, relying on unnatural digital perturbations or explicit patches, are difficult to deploy stealthily in the physical world. In this paper, we propose a novel backdoor attack method that leverages real-world occlusions (e.g., backpacks) as natural triggers for the first time. We design a dynamically optimized heuristic-based strategy to adaptively adjust the trigger’s position and size for diverse occlusion scenarios, and develop three model-independent trigger embedding mechanisms for attack implementation. We conduct extensive experiments on two different pedestrian detection models using publicly available datasets. The results demonstrate that while maintaining baseline performance, the backdoored models achieve average attack success rates of 75.1% on KITTI and 97.1% on CityPersons datasets, respectively. Physical tests verify that pedestrians wearing backpack triggers could successfully evade detection under varying shooting distances of iPhone cameras, though the attack failed when pedestrians rotated by 90°, confirming the practical feasibility of our method. Through ablation studies, we further investigate the impact of key parameters such as trigger patterns and poisoning rates on attack effectiveness. Finally, we evaluate the defense resistance capability of our proposed method. This study reveals that common occlusion phenomena can serve as backdoor carriers, providing critical insights for designing physically robust pedestrian detection systems. Full article

To address the low estimation accuracy of deep learning-based crop yield image recognition methods under untrained shooting distances, this study proposes a shooting distance adaptive crop yield estimation method by fusing RGB and depth image information through multi-modal data fusion. Taking strawberry fruit fresh weight as an example, RGB and depth image data of 348 strawberries were collected at nine heights ranging from 70 to 115 cm. First, based on RGB images and shooting height information, a single-modal crop yield estimation model was developed by training a convolutional neural network (CNN) after cropping strawberry fruit images using the relative area conversion method. Second, the height information was expanded into a data matrix matching the RGB image dimensions, and multi-modal fusion models were investigated through input-layer and output-layer fusion strategies. Finally, two additional approaches were explored: direct fusion of RGB and depth images, and extraction of average shooting height from depth images for estimation. The models were tested at two untrained heights (80 cm and 100 cm). Results showed that when using only RGB images and height information, the relative area conversion method achieved the highest accuracy, with R² values of 0.9212 and 0.9304, normalized root mean square error (NRMSE) of 0.0866 and 0.0814, and mean absolute percentage error (MAPE) of 0.0696 and 0.0660 at the two untrained heights. By further incorporating depth data, the highest accuracy was achieved through input-layer fusion of RGB images with extracted average height from depth images, improving R² to 0.9475 and 0.9384, reducing NRMSE to 0.0707 and 0.0766, and lowering MAPE to 0.0591 and 0.0610. Validation using a developed shooting distance adaptive crop yield estimation platform at two random heights yielded MAPE values of 0.0813 and 0.0593. This model enables adaptive crop yield estimation across varying shooting distances, significantly enhancing accuracy under untrained conditions. Full article

In recent years, the continuous advancement of deep learning has led to significant progress in object-detection technology for remote-sensing images. However, most current detection methods passively perform detection on the input image without considering the relationship between imaging configurations and detection-algorithm performance. Therefore, when factors such as poor lighting conditions, extreme shooting angles, or long acquisition distances degrade image quality, the passive detection framework limits the effectiveness of the current detection algorithm, preventing it from completing the detection task. To address the limitations above, this paper proposes an active object-detection (AOD) method based on deep reinforcement learning, taking adaptive brightness and collection position adjustments as examples. Specifically, we first established an end-to-end network structure to generate attribute control policies. Then, we designed a reward function suitable for remote-sensing images based on the degree of improvement in detection performance. Finally, we propose a new viewpoint-management method in this paper, which is successfully implemented by a training method of long-term Prioritized Experience Replay (LPER), which significantly reduces the accumulation of negative and repetitive samples and improves the success rate of the AOD algorithm for remote-sensing images. The experiments on two public datasets have fully demonstrated the effectiveness and advantages of the algorithm proposed in this paper. Full article

White lupin (Lupinus albus) has become a model plant for understanding plant adaptations to phosphorus (P) and iron (Fe) deficiency, two major limiting factors for plant productivity. In response to both nutrient deficiencies, white lupin forms cluster roots, bottle-brush-like root structures that aid in P and Fe acquisition from soil. While the cluster root function is well-studied, not much is known about the signaling pathways involved in sensing and responding to a P and Fe deficiency. Sucrose has been identified as a long-distance signal sent in increased concentrations from shoot to root in response to both a P and Fe deficiency. Thus, sucrose plays a dual role both as a signal and as a major source of energy for the root. To unravel the responses to sucrose as a signal, we performed an Illumina paired-end cDNA sequencing of white lupin roots treated with sucrose for 20, 40 or 80 min, compared to untreated controls (0 min). We identified 634 up-regulated and 956 down-regulated genes in response to sucrose. Twenty minutes of sucrose treatment showed the most responses, with the ethylene-activated signaling pathway as the most enriched Gene Ontology (GO) category. The number of up-regulated genes decreased at 40 min and 80 min, and protein dephosphorylation became the most enriched category. Taken together, our findings indicate active responses to sucrose as a signal at 20 min after a sucrose addition, but fewer responses and a potential resetting of signal transduction pathways by the dephosphorylation of proteins at 40 and 80 min. Full article

As crucial predecessor tasks for fault detection and transmission line inspection, insulators, anti-vibration hammers, and arc sag detection are critical jobs. Due to the complexity of the high-voltage transmission line environment and other factors, target detection work on transmission lines remains challenging. A method for high-voltage transmission line inspection based on DETR (TLI-DETR) is proposed to detect insulators, anti-vibration hammers, and arc sag. This model achieves a better balance in terms of speed and accuracy than previous methods. Due to environmental interference such as mountainous forests, rivers, and lakes, this paper uses the Improved Multi-Scale Retinex with Color Restoration (IMSRCR) algorithm to make edge extraction more robust with less noise interference. Based on the TLI-DETR’s feature extraction network, we introduce the edge and semantic information by Momentum Comparison (MoCo) to boost the model’s feature extraction ability for small targets. The different shooting angles and distances of drones result in the target images taking up small proportions and impeding each other. Consequently, the statistical profiling of the area and aspect ratio of transmission line targets captured by UAV generate target query vectors with prior information to enable the model to adapt to the detection needs of transmission line targets more accurately and effectively improve the detection accuracy of small targets. The experimental results show that this method has excellent performance in high-voltage transmission line detection, achieving up to 91.65% accuracy and a 55FPS detection speed, which provides a technical basis for the online detection of transmission line targets. Full article

Compared to images captured from ground-level perspectives, objects in UAV images are often more challenging to track due to factors such as long-distance shooting, occlusion, and motion blur. Traditional multi-object trackers are not well-suited for UAV multi-object tracking tasks. To address these challenges, we propose an online multi-object tracking network, OMCTrack. To better handle object occlusion and re-identification, we designed an occlusion perception module that re-identifies lost objects and manages occlusion without increasing computational complexity. By employing a simple yet effective hierarchical association method, this module enhances tracking accuracy and robustness under occlusion conditions. Additionally, we developed an adaptive motion compensation module that leverages prior information to dynamically detect image distortion, enabling the system to handle the UAV’s complex movements. The results from the experiments on the VisDrone2019 and UAVDT datasets demonstrate that OMCTrack significantly outperforms existing UAV video tracking methods. Full article

Plant organ biomass allocation and morphological characteristics are important functional traits. The responses of plant root, stem, and leaf traits to heterogeneous habitats in floodplain wetlands are highly important for understanding the ecological adaptation strategies of riparian plants. However, the patterns of these responses remain unclear. In a floodplain wetland in the middle reaches of the Heihe River, we studied the responses of the root, stem, and leaf morphological traits and biomass allocation of Leymus secalinus to varying habitat conditions. We measured these traits in three sample plots, delineated based on distance from the riverbank: plot I (near the riparian zone, 50–150 m from the riverbank), plot II (middle riparian zone, 200–300 m from the riverbank), and plot III (far riparian zone, 350–450 m from the riverbank). The results showed that in plot I, L. secalinus tended to have slender roots and stems and small leaves, with a biomass allocation strategy that maximized the root–shoot ratio (RSR). In plot II, L. secalinus had thick stems and moderate leaf and root patterns, and the RSR values were between those of plot I and plot III. In plot III, L. secalinus had thin and short stems and large leaves; furthermore, among the root morphological structures, plot III had the shortest Rhizome length (RL) and longest Rhizome diameter (RD), and the RSR was the lowest. Moreover, there was a significant correlation between organ biomass and leaf thickness, stem length, RD, and RL in the three habitats (p < 0.05). By balancing the biomass allocation among organs, wetland plants in floodplains balance changes in root, stem, and leaf morphological characteristics to improve their environmental adaptation. Full article

Phosphorus (P) and iron (Fe) deficiency are major limiting factors for plant productivity worldwide. White lupin (Lupinus albus L.) has become a model plant for understanding plant adaptations to P and Fe deficiency, because of its ability to form cluster roots, bottle-brush-like root structures play an important role in the uptake of P and Fe from soil. However, little is known about the signaling pathways involved in sensing and responding to P and Fe deficiency. Sucrose, sent in increased concentrations from the shoot to the root, has been identified as a long-distance signal of both P and Fe deficiency. To unravel the responses to sucrose as a signal, we performed Oxford Nanopore cDNA sequencing of white lupin roots treated with sucrose for 10, 15, or 20 min compared to untreated controls. We identified a set of 17 genes, including 2 bHLH transcription factors, that were up-regulated at all three time points of sucrose treatment. GO (gene ontology) analysis revealed enrichment of auxin and gibberellin responses as early as 10 min after sucrose addition, as well as the emerging of ethylene responses at 20 min of sucrose treatment, indicating a sequential involvement of these hormones in plant responses to sucrose. Full article

The adaption of plants to stressful environments depends on long-distance responses in plant organs, which themselves are remote from sites of perception of external stimuli. Jasmonic acid (JA) and its derivatives are known to be involved in plants’ adaptation to salinity. However, to our knowledge, the transport of JAs from roots to shoots has not been studied in relation to the responses of shoots to root salt treatment. We detected a salt-induced increase in the content of JAs in the roots, xylem sap, and leaves of pea plants related to changes in transpiration. Similarities between the localization of JA and lipid transfer proteins (LTPs) around vascular tissues were detected with immunohistochemistry, while immunoblotting revealed the presence of LTPs in the xylem sap of pea plants and its increase with salinity. Furthermore, we compared the effects of exogenous MeJA and salt treatment on the accumulation of JAs in leaves and their impact on transpiration. Our results indicate that salt-induced changes in JA concentrations in roots and xylem sap are the source of accumulation of these hormones in leaves leading to associated changes in transpiration. Furthermore, they suggest the possible involvement of LTPs in the loading/unloading of JAs into/from the xylem and its xylem transport. Full article

Unmanned aerial vehicles (UAVs) are now widely used in many fields. Due to the randomness of UAV flight height and shooting angle, UAV images usually have the following characteristics: many small objects, large changes in object scale, and complex background. Therefore, object detection in UAV aerial images is a very challenging task. To address the challenges posed by these characteristics, this paper proposes a novel UAV image object detection method based on global feature aggregation and context feature extraction named the multi-scale feature information extraction and fusion network (MFEFNet). Specifically, first of all, to extract the feature information of objects more effectively from complex backgrounds, we propose an efficient spatial information extraction (SIEM) module, which combines residual connection to build long-distance feature dependencies and effectively extracts the most useful feature information by building contextual feature relations around objects. Secondly, to improve the feature fusion efficiency and reduce the burden brought by redundant feature fusion networks, we propose a global aggregation progressive feature fusion network (GAFN). This network adopts a three-level adaptive feature fusion method, which can adaptively fuse multi-scale features according to the importance of different feature layers and reduce unnecessary intermediate redundant features by utilizing the adaptive feature fusion module (AFFM). Furthermore, we use the MPDIoU loss function as the bounding-box regression loss function, which not only enhances model robustness to noise but also simplifies the calculation process and improves the final detection efficiency. Finally, the proposed MFEFNet was tested on VisDrone and UAVDT datasets, and the mAP0.5 value increased by 2.7% and 2.2%, respectively. Full article

In order to analyze the relay action process from an imaging perspective and further investigate the bounce phenomenon of relay contacts during the contact process, this paper utilizes a high-speed shooting platform to capture images of relay action. In light of the situation where the stationary contact in the image is inclined and continuously changing, a rotation template matching algorithm based on adaptive weight is proposed. The algorithm identifies and obtains the inclination angle of the stationary contact, enabling the study of the relay contact bounce process. By extracting contact bounce distance data from the images, a bounce process curve is plotted. Combined with the analysis of the contact bounce process, the reasons for the bounce are explored. The results indicate that the proposed rotation template matching algorithm can accurately identify stationary contacts and their angles at different angles. By analyzing the contact status and bounce process of the relay contacts in conjunction with the relay structure, parameters such as the bounce time, bounce height, and time required to reach the maximum distance can be calculated. Additionally, the main reason for contact bounce in the relay studied in this paper is the limitation imposed on the continued movement of the stationary contact by the presence of the relay brackets when the kinetic energy of the contact is too high. This phenomenon occurs during the first vibration peak in the vibration process after the moving contact contacts the stationary contact. The research results provide a reference for further studying the relay contact bounce process, optimizing relay structure, and suppressing contact bounce. Full article

Adaptation to changes in the environment depends, in part, on signaling between plant organs to integrate adaptive response at the level of the whole organism. Changes in the delivery of hormones from one organ to another through the vascular system strongly suggest that hormone transport is involved in the transmission of signals over long distances. However, there is evidence that, alternatively, systemic responses may be brought about by other kinds of signals (e.g., hydraulic or electrical) capable of inducing changes in hormone metabolism in distant organs. Long-distance transport of hormones is therefore a matter of debate. This review summarizes arguments for and against the involvement of the long-distance transport of cytokinins in signaling mineral nutrient availability from roots to the shoot. It also assesses the evidence for the role of abscisic acid (ABA) and jasmonates in long-distance signaling of water deficiency and the possibility that Lipid-Binding and Transfer Proteins (LBTPs) facilitate the long-distance transport of hormones. It is assumed that proteins of this type raise the solubility of hydrophobic substances such as ABA and jasmonates in hydrophilic spaces, thereby enabling their movement in solution throughout the plant. This review collates evidence that LBTPs bind to cytokinins, ABA, and jasmonates and that cytokinins, ABA, and LBTPs are present in xylem and phloem sap and co-localize at sites of loading into vascular tissues and at sites of unloading from the phloem. The available evidence indicates a functional interaction between LBTPs and these hormones. Full article

The implementation of roof bolt support within a coal mine roadway has the capacity to bolster the stability of the encompassing rock strata and thereby mitigate the potential for accidents. To enhance the automation of support operations, this paper introduces a binocular vision positioning method for drilling holes, which relies on the adaptive adjustment of parameters. Through the establishment of a predictive model, the correlation between the radius of the target circular hole in the image and the shooting distance is ascertained. Based on the structural model of the anchor drilling robot and the related sensing data, the shooting distance range is defined. Exploiting the geometric constraints inherent to adjacent anchor holes, the precise identification of anchor holes is detected by a Hough transformer with an adaptive parameter-adjusted method. On this basis, the matching of the anchor hole contour is realized by using linear slope and geometric constraints, and the spatial coordinates of the anchor hole center in the camera coordinate system are determined based on the binocular vision positioning principle. The outcomes of the experiments reveal that the method attains a positioning accuracy of 95.2%, with an absolute error of around 1.52 mm. When compared with manual operation, this technique distinctly enhances drilling accuracy and augments support efficiency. Full article

Due to the special characteristics of the shooting distance and angle of remote sensing satellites, the pixel area of ship targets is small, and the feature expression is insufficient, which leads to unsatisfactory ship detection performance and even situations such as missed and false detection. To solve these problems, this paper proposes an improved-YOLOv5 algorithm mainly including: (1) Add the Convolutional Block Attention Module (CBAM) into the Backbone to enhance the extraction of target-adaptive optimal features; (2) Introduce a cross-layer connection channel and lightweight GSConv structures into the Neck to achieve higher-level multi-scale feature fusion and reduce the number of model parameters; (3) Use the Wise-IoU loss function to calculate the localization loss in the Output, and assign reasonable gradient gains to cope with differences in image quality. In addition, during the preprocessing stage of experimental data, a median+bilateral filter method was used to reduce interference from ripples and waves and highlight the information of ship features. The experimental results show that Improved-YOLOv5 has a significant improvement in recognition accuracy compared to various mainstream target detection algorithms; compared to the original YOLOv5s, the mean Average Precision (mAP) improved by 3.2% and the Frames Per Second (FPN) accelerated by 8.7%. Full article

Soil salinization is one of the most serious abiotic stresses restricting plant growth. Buffalograss is a C₄ perennial turfgrass and forage with an excellent resistance to harsh environments. To clarify the adaptative mechanisms of buffalograss in response to salinity, we investigated the effects of NaCl treatments on photosynthesis, water status and K⁺/Na⁺ homeostasis of this species, then analyzed the expression of key genes involved in these processes using the qRT-PCR method. The results showed that NaCl treatments up to 200 mM had no obvious effects on plant growth, photosynthesis and leaf hydrate status, and even substantially stimulated root activity. Furthermore, buffalograss could retain a large amount of Na⁺ in roots to restrict Na⁺ overaccumulation in shoots, and increase leaf K⁺ concentration to maintain a high K⁺/Na⁺ ratio under NaCl stresses. After 50 and 200 mM NaCl treatments, the expressions of several genes related to chlorophyll synthesis, photosynthetic electron transport and CO₂ assimilation, as well as aquaporin genes (BdPIPs and BdTIPs) were upregulated. Notably, under NaCl treatments, the increased expression of BdSOS1, BdHKT1 and BdNHX1 in roots might have helped Na⁺ exclusion by root tips, retrieval from xylem sap and accumulation in root cells, respectively; the upregulation of BdHAK5 and BdSKOR in roots likely enhanced K⁺ uptake and long-distance transport from roots to shoots, respectively. This work finds that buffalograss possesses a strong ability to sustain high photosynthetic capacity, water balance and leaf K⁺/Na⁺ homeostasis under salt stress, and lays a foundation for elucidating the molecular mechanism underlying the salt tolerance of buffalograss. Full article