Search Results (57)

Previous studies on single-polarized InSAR-based sub-canopy topography inversion have mainly relied on simplified or empirical models that only consider the volume scattering process. In a boreal forest area, the canopy layer is often discontinuous. In such a case, the radar backscattering echoes are mainly dominated by ground surface and volume scattering processes. However, interferometric scattering models like Random Volume over Ground (RVoG) have been little utilized in the case of single-polarized InSAR. In this study, we propose a novel method for retrieving sub-canopy topography by combining the RVoG model with multi-baseline InSAR data. Prior to the RVoG model inversion, a SAR-based dimidiate pixel model and a coherence-based penetration depth model are introduced to quantify the initial values of the unknown parameters, thereby minimizing the reliance on external vegetation datasets. Building on this, a nonlinear least-squares algorithm is employed. Then, we estimate the scattering phase center height and subsequently derive the sub-canopy topography. Two frames of multi-baseline TanDEM-X co-registered single-look slant-range complex (CoSSC) data (resampled to 10 m × 10 m) over the Krycklan catchment in northern Sweden are used for the inversion. Validation from airborne light detection and ranging (LiDAR) data shows that the root-mean-square error (RMSE) for the two test sites is 3.82 m and 3.47 m, respectively, demonstrating a significant improvement over the InSAR phase-measured digital elevation model (DEM). Furthermore, diverse interferometric baseline geometries and different initial values are identified as key factors influencing retrieval performance. In summary, our work effectively addresses the limitations of the traditional RVoG model and provides an advanced and practical tool for sub-canopy topography mapping in forested areas. Full article

Due to the shortage of rural labor and an increasingly aging population, promoting the mechanized plucking of bulk tea and improving plucking efficiency have become urgent problems for tea plantations. Previous bulk tea plucking machines have not fully adapted to tea plantations in hilly areas, necessitating enhancements in the performance of cutter profiling. In this paper, we present an automatic cutter profiling method based on an RGB-D camera, which utilizes the depth information of bulk tea shoots to tackle the issues mentioned above. Specifically, we use improved super-green features and the Otsu method to detect and segment the shoots from the RGB images of the tea canopy taken from different lighting conditions. Furthermore, the cutting pose based on the depth value of the tea shoots can be generated as a basis for cutter profiling. Lastly, the profiling task is completed by the upper computer controlling motors to adjust the cutter pose. Field tests were conducted in the tea plantation to verify the proposed profiling method’s effectiveness. The average bud and leaf integrity rate, leakage rate, loss rate, tea making rate, and qualified rate were 81.2%, 0.91%, 0.66%, and 90.4%, respectively. The results show that the developed algorithm can improve cutting pose calculation accuracy and that the harvested bulk tea shoots meet the requirements of machine plucking quality standards and the subsequent processing process. Full article

Environmental factors like light, photoperiod, temperature, and water are vital for crop growth, and even slight deviations from their optimal ranges can cause seedling stress and reduce yield. Therefore, this study aimed to quantify seedling stress symptoms using image features analysis under varying light, photoperiod, temperature, and water conditions. Seedlings were grown under controlled low, normal, and high environmental conditions. Light intensity at 50 µmol m⁻² s⁻¹ (low), 250 µmol m⁻² s⁻¹ (normal), and 450 µmol m⁻² s⁻¹ (high), photoperiod cycles, 8/16 h (day/night) (low), 10/14 h (day/night) (normal), and 16/8 h (day/night) (high) day/night, temperature at 20 °C (low), 25 °C (normal), and 30 °C (high), and water availability at 1 L per day (optimal), 1 L every two days (moderate stress), and 1 L every three days (severe stress) were applied for 15 days. Commercial low-cost RGB, thermal, and depth sensors were used to collect data every day. A total of 1080 RGB images, which were pre-processed with histogram equalization and filters (Median and Gaussian), were used for noise reduction to minimize illumination effects. Morphological, color, and texture features were then analyzed using ANOVA (p < 0.05) to assess treatment effects. The result shows that the maximum canopy area for tomato was 115,226 pixels, while lettuce’s maximum plant height was 9.28 cm. However, 450 µmol m⁻² s⁻¹ light intensity caused increased surface roughness, indicating stress-induced morphological alteration. The analysis of Combined Stress Index (CSI) values indicated that the highest stress levels were 50% for pepper, 55% for tomato, 62% for cucumber, 55% for watermelon, 50% for lettuce, and 50% for pak choi. The findings showed that image-based stress detection enables precise environmental control and improves early-stage crop management. Full article

To address the challenges of water scarcity and the limited accuracy of terrestrial water storage (TWS) estimation in Inner Mongolia, this study integrates GRACE satellite observations, the GLDAS-Noah hydrological model, and ground-based precipitation records, in combination with Theil–Sen median trend analysis and the Mann–Kendall test, to systematically evaluate the spatiotemporal evolution of TWS from 2003 to 2016. The results demonstrate that: (1) GRACE data reliably capture regional water storage dynamics. Over the study period, TWS exhibited a significant overall decline, with an average rate of −5.2 × 10⁻⁴ cm/year, and seasonal variations were strongly coupled with precipitation patterns. (2) Spatially, TWS anomalies (TWSa) decreased from northeast to southwest, with values ranging from approximately +1.22 cm to −2.94 cm. The most pronounced decline was detected in the southern Ordos region. (3) Soil water changes were more substantial than those in canopy or snow water, with sharp reductions occurring during 2004–2007 and 2013–2015. Soil water exhibited clear stratification across different depths, and variations in deep soil water and groundwater were primarily influenced by non-precipitation factors. These findings provide a scientific basis for the sustainable utilization of water resources in Inner Mongolia and yield important insights for regional water management and policy formulation. Full article

Detecting citrus Huanglongbing (HLB) in orchard environments is particularly challenging due to multi-scale targets and occlusions due to clustering, which manifest as complex and variable backgrounds, targets ranging from distant single leaves to nearby full canopies, and frequent instances where symptomatic leaves are hidden behind others, all significantly hindering accurate detection. To overcome these challenges, this study introduces a novel citrus object detection model, Multi-Scale Huanglongbing DETR (MSHLB-DETR), developed on the basis of an improved Real-Time DEtection TRansformer (RT-DETR). The model significantly enhances detection accuracy and efficiency for HLB under complex orchard conditions. To address the issue of small target feature loss in leaf detection, a new efficient transformer module called Smart Disease Recognition for Citrus Huanglongbing with Multi-scale (SDRM) is introduced. SDRM includes a space-to-depth (SPD) module and inverted residual mobile block (IRMB), which facilitate deep interaction between local and global features and significantly improve the computational efficiency of the transformer. Additionally, the transformer encoder incorporates a Context-Guided Block (CGBlock) for contextual feature learning. To evaluate the proposed model under complex background conditions, a dataset of 4367 images was collected from diverse orchard scenes, preprocessed, and divided into training, validation, and testing subsets. The experimental results demonstrate that the proposed MSHLB-DETR achieved the best detection performance on the test set, with an ${\mathrm{mAP}}_{50}$ of 96.0%, surpassing other state-of-the-art models of similar scale. Compared to the original RT-DETR, the proposed model increased ${\mathrm{mAP}}_{50}$ by 15.8%, reduced Params by 7.5%, and decreased GFLOPs by 5.2%. This study reveals the critical importance of developing efficient multi-scale detection techniques for the accurate identification of citrus Huanglongbing in complex real-time monitoring scenarios. The proposed algorithm is expected to provide valuable references and new insights for the precise and timely detection of citrus Huanglongbing. Full article

This study investigates the application of unmanned aerial vehicles with multispectral cameras for monitoring the condition of olive groves with high accuracy. Multispectral images of olive groves provided detailed insight into the spectral data required for the analysis of vegetation indices. Using deep learning-based object detection, individual olive trees were identified within the images, which allowed the extraction of parts corresponding to each tree. To separate the background from the canopy, segmentation based on the monocular depth estimation algorithm, Depth Anything, was applied. In this way, elements that are not part of the tree’s crown were removed for more accurate analysis and calculation of the NDVI (Normalized Difference Vegetation Index) and NDRE (Normalized Difference Red Edge Index) indices. The obtained results were compared with the results obtained for unsegmented patches, threshold-based patches, and manually segmented patches. The comparison and analysis carried out shows that the proposed segmentation approach improved the accuracy of NDVI and NDRE by focusing exclusively on the crowns of the observed trees, excluding the noise of the surrounding vegetation and soil. In addition, measurements were carried out on three observed olive groves at different parts of the vegetation cycle, and the values of the vegetation indices were compared. This integrated method combining drone-based multispectral imaging, deep learning object detection, and advanced segmentation techniques highlights a robust approach to olive tree health monitoring and provides insight into seasonal vegetation dynamics, for winter and spring, to capture differences in vegetative activity. Full article

In a hypothetical climate change scenario, zoysiagrass species could be a good choice for turfgrass areas due to their adaptation to heat conditions and the great variability in species and cultivars. Knowledge of the root system’s characteristics is paramount for predicting cultivar adaptation to different heat–drought scenarios and therefore for designing proper turfgrass management programs, especially irrigation. A field experiment was conducted in the Mediterranean environment of Valencia (Spain) to study the root weight density (RWD), root length density (RLD), and average root diameter (RDI) at three different soil depths (0–5, 5–15, and 15–30 cm) of five new zoysiagrass genotypes (Zoysia matrella (L.) Merr., Zoysia japonica Steud., and their hybrid), relating these parameters to the performance of these experimental lines during their establishment. All the tested experimental lines had a higher RWD and RLD in the upper soil layer (0–5 cm), while the RDI was higher in the lowest layer of the sampled soil profile (0.269 mm compared with 0.249 mm and 0.241 mm in the upper layers). All the tested genotypes showed the same RWD and RLD, while the Zoysia matrella experimental line A showed a higher RDI value (0.2683 mm) than those for the Z. japonica (0.2369 mm) and the hybrid (0.2394 mm) genotypes. This last finding could have influenced its more rapid establishment, although it was not linked to its NDVI values during autumn. In conclusion, different morphological root characteristics were detected among new zoysiagrass genotypes and soil depths, which could have affected their canopy performance, and they are expected to affect irrigation management in a possible future drought scenario. Full article

Precision pesticide application is a key focus in orchard management, with targeted spraying serving as a core technology to optimize pesticide delivery and reduce environmental pollution. However, its accurate implementation relies on high-precision environmental sensing technologies to enable the precise identification of target objects and dynamic regulation of spraying strategies. This paper systematically reviews the application of orchard environmental sensing technologies in targeted spraying. It first focuses on key sensors used in environmental sensing, providing an in-depth analysis of their operational mechanisms and advantages in orchard environmental perception. Subsequently, this paper discusses the role of multi-source data fusion and artificial intelligence analysis techniques in improving the accuracy and stability of orchard environmental sensing, supporting crown structure modeling, pest and disease monitoring, and weed recognition. Additionally, this paper reviews the practical paths of environmental sensing-driven targeted spraying technologies, including variable spraying strategies based on canopy structure perception, precise pesticide application methods combined with intelligent pest and disease recognition, and targeted weed control technologies relying on weed and non-target area detection. Finally, this paper summarizes the challenges faced by multi-source sensing and targeted spraying technologies in light of current research progress and industry needs, and explores potential future developments in low-cost sensors, real-time data processing, intelligent decision making, and unmanned agricultural machinery. Full article

Agricultural robots can mitigate labor shortages and advance precision farming. However, the dense vegetation canopies and uneven terrain in orchard environments reduce the reliability of traditional GPS-based localization, thereby reducing navigation accuracy and making autonomous navigation challenging. Moreover, inefficient path planning and an increased risk of collisions affect the robot’s ability to perform tasks such as fruit harvesting, spraying, and monitoring. To address these limitations, this study integrated stereo visual odometry with real-time appearance-based mapping (RTAB-Map)-based simultaneous localization and mapping (SLAM) to improve mapping and localization in both indoor and outdoor orchard settings. The proposed system leverages stereo image pairs for precise depth estimation while utilizing RTAB-Map’s graph-based SLAM framework with loop-closure detection to ensure global map consistency. In addition, an incorporated inertial measurement unit (IMU) enhances pose estimation, thereby improving localization accuracy. Substantial improvements in both mapping and localization performance over the traditional approach were demonstrated, with an average error of 0.018 m against the ground truth for outdoor mapping and a consistent average error of 0.03 m for indoor trails with a 20.7% reduction in visual odometry trajectory deviation compared to traditional methods. Localization performance remained robust across diverse conditions, with a low RMSE of 0.207 m. Our approach provides critical insights into developing more reliable autonomous navigation systems for agricultural robots. Full article

Early detection of nitrogen deficiency in cotton requires timely identification of stress symptoms like leaf chlorosis (yellowing) and canopy stunting. Chlorosis initially appears in older, lower-canopy leaves, which are often not visible in conventional nadir-looking imaging. This study investigates oblique ground-based multispectral imaging to estimate plant height and capture spectral details from the upper (UC) and lower (LC) cotton canopy layers. Images were collected from four camera pitch and height configurations: set 1 (30°, 2 m), set 2 (55°, 2 m), set 3 (68°, 3 m), and set 4 (70°, 1.5 m). A pre-trained monocular depth estimation model (MiDaS) was used to estimate plant height from aligned RGB images and an empirically derived tangential model corrected for perspective distortion. Further, the lower and upper vertical halves of the plants were categorized as LC and UC, with vegetation indices (CI_green, CI_rededge) calculated for each. The aligned images in set 1 had the best sharpness and quality. The plant height estimates from set 1 had the highest correlation (r = 0.64) and lowest root mean squared error (RMSE = 0.13 m). As the images became more oblique, alignment and monocular depth/height accuracy decreased. Also, the effects of perspective and object-scale ambiguity in monocular depth estimation were prominent in the high oblique and relatively low altitude images. The spectral vegetation indices (VIs) were affected by band misalignment and shadows. VIs from the different canopy layers demonstrated moderate correlation with leaf nitrogen concentration, and sets 2 and 3 specifically showed high and low differences in VIs from the UC and LC layers for the no and high-nitrogen treatments, respectively. However, improvements in the multispectral alignment process, extensive data collection, and ground-truthing are needed to conclude whether the LC spectra are useful for early nitrogen stress detection in field cotton. Full article

Accurately estimating soil moisture at multiple depths is essential for sustainable farming practices, as it supports efficient irrigation management, optimizes crop yields, and conserves water resources. This study integrates a drone-mounted hyperspectral sensor with machine learning techniques to enhance soil moisture estimation at 10 cm and 30 cm depths in a cornfield. The primary aim was to understand the relationship between root zone water content and canopy reflectance, pinpoint the depths where this relationship is most significant, identify the most informative wavelengths, and train a machine learning model using those wavelengths to estimate soil moisture. Our results demonstrate that PCA effectively detected critical variables for soil moisture estimation, with the ANN model outperforming other machine learning algorithms, including Random Forest (RF), Support Vector Regression (SVR), and Gradient Boosting (XGBoost). Model comparisons between irrigated and non-irrigated treatments showed that soil moisture in non-irrigated plots could be estimated with greater accuracy across various dates. This finding indicates that plants experiencing high water stress exhibit more significant spectral variability in their canopy, enhancing the correlation with soil moisture in the root zone. Moreover, over the growing season, when corn exhibits high chlorophyll content and increased resilience to environmental stressors, the correlation between canopy spectrum and root zone soil moisture weakens. Error analysis revealed the lowest relative estimation errors in non-irrigated plots at a 30 cm depth, aligning with periods of elevated water stress at shallower levels, which drove deeper root growth and strengthened the canopy reflectance relationship. This correlation corresponded to lower RMSE values, highlighting improved model accuracy. Full article

Remote sensing is heavily relied upon where eelgrass maps are needed for tracking trends, project siting and permitting, water quality assessments, and restoration planning. However, there is only a moderate degree of confidence in the accuracy of maps derived from remote sensing, thus risking inadequate resource protection. In this study, semi-synchronous drone, side-scan sonar, airplane, and satellite missions were conducted at five Massachusetts eelgrass meadows to assess each method’s edge-detection capability and mapping accuracy. To ground-truth the remote sensing surveys, SCUBA divers surveyed the meadow along transects perpendicular to shore to locate the last shoot (i.e., meadow’s edge) and sampled quadrat locations along the transect for percent cover, canopy height, and meadow patchiness. In addition, drop frame underwater camera surveys were conducted to assess the accuracy of each remote sensing survey. Eelgrass meadow delineations derived from each remote sensing method were compared to ground-truthing data to address the following study objectives: (1) determine if and how much eelgrass was missed during manual photointerpretation of the imagery from each remote sensing method, (2) assess map accuracy, as well as the effects of eelgrass percent cover, canopy height, and meadow patchiness on method performance, and (3) make management recommendations regarding the use of remote sensing data for eelgrass mapping. Results showed that all remote sensing methods were associated with the underestimation of eelgrass. At the shallow edge, mean edge detection error was lowest for drone imagery (11.2 m) and increased with decreasing image resolution, up to 38.5 m for satellite imagery. At the deep edge, mean edge detection error varied by survey method but ranged from 72 to 106 m. Maximum edge detection errors across all sites and depths for each survey method were 112.4 m, 121.4 m, 121.7 m, and 106.7 m for drone, sonar, airplane, and satellite data, respectively. The overall accuracy of eelgrass delineations across the survey methods ranged from 76–89% and corresponded with image resolution, where drones performed best, followed by sonar, airplanes, and satellites; however, there was a high degree of site variability. Accuracy at the shallow edge was greater than at the deep edge across all survey types except for satellite, where accuracy was the same at both depths. Accuracy was influenced by eelgrass percent cover, canopy height, and meadow patchiness. Low eelgrass density (i.e., 1–10% cover), patchy eelgrass (i.e., shoots or patches spaced > 5 m) and shorter canopy height (i.e., <22 cm) were associated with reduced accuracy across all methods; however, drones performed best across all scenarios. Management recommendations include applying regulatory buffers to eelgrass maps derived from remote sensing in order to protect meadow edge areas from human disturbances, the prioritization of using SCUBA and high-resolution platforms like drones and sonar for eelgrass mapping, and for existing mapping programs to allocate more resources to ground-truthing along meadow edges. Full article

Automatic acquisition of phenotypic traits in tomato plants is important for tomato variety selection and scientific cultivation. Because of time-consuming and labor-intensive traditional manual measurements, the lack of complete structural information in two-dimensional (2D) images, and the complex structure of the plants, it is difficult to automatically obtain the phenotypic traits of the tomato canopy. Thus, a method for calculating the phenotypic traits of tomato canopy in greenhouse was proposed based on the extraction of the branch skeleton. First, a top-view-based acquisition platform was built to obtain the point cloud data of the tomato canopy, and the improved K-means algorithm was used to segment the three-dimensional (3D) point cloud of branches. Second, the Laplace algorithm was used to extract the canopy branch skeleton structure. Branch and leaf point cloud separation was performed using branch local skeleton vectors and internal features. In addition, the DBSCAN clustering algorithm was applied to recognize individual leaf organs. Finally, phenotypic traits including mean leaf inclination, digital biomass, and light penetration depth of tomato canopies were calculated separately based on the morphological structure of the 3D point cloud. The experimental results show that the detection accuracies of branches and leaves were above 88% and 93%, respectively, and the coefficients of determination between the calculated and measured values of mean leaf inclination, digital biomass, and light penetration depth were 0.9419, 0.9612, and 0.9093, respectively. The research results can provide an effective quantitative basis and technical support for variety selection and scientific cultivation of the tomato plant. Full article

Tree canopy cover is an important forest inventory parameter and a critical component for the in-depth mapping of forest fuels. This research examines the potential of employing single-date Sentinel-2 multispectral imagery, combined with contextual spatial information, to classify areas based on their tree cover density using Random Forest classifiers. Three spatial information extraction methods are investigated for their capacity to acutely detect canopy cover: two based on Gray-Level Co-Occurrence Matrix (GLCM) features and one based on segment statistics. The research was carried out in three different biomes in Greece, in a total study area of 23,644 km². Three tree cover classes were considered, namely, non-forest (cover < 15%), open forest (cover = 15%–70%), and closed forest (cover ≥ 70%), based on the requirements set for fuel mapping in Europe. Results indicate that the best approach identified delivers F1-scores ranging 70%–75% for all study areas, significantly improving results over the other alternatives. Overall, the synergistic use of spectral and spatial features derived from Sentinel-2 images highlights a promising approach for the generation of tree cover density information layers in Mediterranean regions, enabling the creation of additional information in support of the detailed mapping of forest fuels. Full article

Effective lettuce cultivation requires precise monitoring of growth characteristics, quality assessment, and optimal harvest timing. In a recent study, a deep learning model based on multimodal data fusion was developed to estimate lettuce phenotypic traits accurately. A dual-modal network combining RGB and depth images was designed using an open lettuce dataset. The network incorporated both a feature correction module and a feature fusion module, significantly enhancing the performance in object detection, segmentation, and trait estimation. The model demonstrated high accuracy in estimating key traits, including fresh weight (fw), dry weight (dw), plant height (h), canopy diameter (d), and leaf area (la), achieving an R² of 0.9732 for fresh weight. Robustness and accuracy were further validated through 5-fold cross-validation, offering a promising approach for future crop phenotyping. Full article