With the progress of computer vision and the development of unmanned aerial vehicles (UAVs), UAVs have been widely used in forest resource investigation and tree feature extraction. In the field of crown width measurement, the use of traditional manual measurement methods is time-consuming and costly and affects factors such as terrain and weather. Although the crown width extraction method based on the segmentation of UAV images that have recently risen in popularity extracts a large amount of information, it consumes long amounts of time for dataset establishment and segmentation. This paper proposes an improved YOLOv7 model designed to precisely extract the crown width of Metasequoia glyptostroboides. This species is distinguished by its well-developed terminal buds and distinct central trunk morphology. Taking the M. glyptostroboides forest in the Qingshan Lake National Forest Park in Lin’an District, Hangzhou City, Zhejiang Province, China, as the target sample plot, YOLOv7 was improved using the simple, parameter-free attention model (SimAM) attention and SIoU modules. The SimAM attention module was experimentally proved capable of reducing the attention to other irrelevant information in the training process and improving the model’s accuracy. The SIoU module can improve the tightness between the detection frame and the edge of the target crown during the detection process and effectively enhance the accuracy of crown width measurement. The experimental results reveal that the improved model achieves 94.34% mAP@0.5 in the task of crown detection, which is 5% higher than that achieved by the original model. In crown width measurement, the R² of the improved model reaches 0.837, which is 0.151 higher than that of the original model, thus verifying the effectiveness of the improved algorithm.

Accurately assessing forest carbon stock (FCS) is essential for analyzing its spatial distribution and gauging the capacity of forests to sequester carbon. This research introduces a novel approach for estimating FCS by integrating multiple data sources, such as Sentinel-1 (S1) radar imagery, optical images from Sentinel-2 (S2) and Landsat 8 (L8), digital elevation modeling (DEM), and inventory data used in forest management and planning (FMP). Additionally, the estimation of FCS incorporates four key ecological features, including forest composition, primary tree species, humus thickness, and slope direction, to improve the accuracy of the estimation. Subsequently, insignificant features were eliminated using Lasso and recursive feature elimination (RFE) feature selection techniques. Three machine learning (ML) models were employed to estimate FCS: XGBoost, random forest (RF), and LightGBM. The results show that the inclusion of ecological information features improves the performance of the models. Among the models, LightGBM achieved superior performance (R² = 0.78, mean squared error (MSE) = 0.85, root mean squared error (RMSE) = 0.92, mean absolute error (MAE) = 0.58, relative RMSE (rRMSE) = 41.37%, and mean absolute percentage error (MAPE) = 30.72%), outperforming RF (R² = 0.76, MSE = 0.93, RMSE = 0.97, MAE = 0.60, rRMSE = 43.42%, and MAPE = 30.85%) and XGBoost (R² = 0.77, MSE = 0.90, RMSE = 0.95, MAE = 0.61, rRMSE = 42.66%, and MAPE = 34.61%).

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.

Effective monitoring of protected wildlife is crucial for biodiversity conservation. While camera traps provide valuable data for ecological observation, existing deep learning models often suffer from low accuracy in detecting rare species and high computational costs, hindering their deployment on edge devices. To address these challenges, this study proposes YOLO11-APS, an improved lightweight model for protected wildlife detection. It enhances the YOLO11n by integrating the self-Attention and Convolution (ACmix) module, the Partial Convolution (PConv) module, and the SlimNeck paradigm. These improvements strengthen feature extraction under complex conditions while reducing computational costs. Experimental results demonstrate that YOLO11-APS achieves superior detection performance compared to the baseline model, attaining a precision of 92.7%, a recall of 87.0%, an mAP@0.5 of 92.6% and an mAP@0.5:0.95 of 62.2%. In terms of model lightweighting, YOLO11-APS reduces the number of parameters, floating-point operations, and model size by 10.1%, 11.1%, and 9.5%, respectively. YOLO11-APS achieves an optimal balance between accuracy and model complexity, outperforming existing mainstream lightweight detection models. Furthermore, tests on unseen wildlife data confirm its strong transferability and robustness. This work provides an efficient deep learning tool for automated wildlife monitoring in protected areas, facilitating the development of intelligent ecological sensing systems.

Sudden changes in the morphological characteristics of trees are closely related to plant health, and automated phenotypic measurements can help improve the efficiency of plant health monitoring, and thus aid in the conservation of old and valuable tress. The irregular distribution of branches and the influence of the natural environment make it very difficult to monitor the status of branches in the field. In order to solve the problem of branch phenotype monitoring of tall and valuable plants in the field environment, this paper proposes an improved UNet model to achieve accurate extraction of trunk and branches. This paper also proposes an algorithm that can measure the branch length and inclination angle by using the main trunk and branches separated in the previous stage, finding the skeleton line of a single branch via digital image morphological processing and the Zhang–Suen thinning algorithm, obtaining the number of pixel points as the branch length, and then using Euclidean distance to fit a straight line to calculate the inclination angle of each branch. These were carried out in order to monitor the change in branch length and inclination angle and to determine whether plant branch breakage or external stress events had occurred. We evaluated the method on video images of Abies beshanzuensis, and the experimental results showed that the present algorithm has more excellent performance at 94.30% MIoU as compared with other target segmentation algorithms. The coefficient of determination (R²) is higher than 0.89 for the calculation of the branch length and inclination angle. In summary, the algorithm proposed in this paper can effectively segment the branches of tall plants and measure their length and inclination angle in a field environment, thus providing an effective method to monitor the health of valuable plants.

It is challenging to achieve accurate tea bud detection in optical images with complex backgrounds since distinguishing between the foregrounds and backgrounds of these images remains difficult. Although several studies have been proposed to implicitly distinguish foregrounds and backgrounds via various attention mechanisms, explicit distinction between foregrounds and backgrounds has been seldom explored. Inspired by recent successful applications of the Segment Anything Model (SAM) in computer vision, this study proposes a SAM-assisted dual-branch YOLOv8 model named SD-YOLOv8 for tea bud detection to address the challenges of explicit distinction between foregrounds and backgrounds. The SD-YOLOv8 model mainly consists of two key components: (1) the SAM-based foreground segmenter (SFS) to generate foreground masks of tea bud images without any training, and (2) the heterogeneous feature extractor to parallelly capture both color features in optical images and edge features in foreground masks. The experimental results show that the proposed SD-YOLOv8 significantly improves the performance of tea bud detection based on the explicit distinction between foregrounds and backgrounds. The mean Average Precision of the SD-YOLOv8 model reaches 86.0%, surpassing the YOLOv8 (mAP 81.6%) by 5 percentage points and outperforming recent object detection models, including Faster R-CNN (mAP 60.7%), DETR (mAP 64.6%), YOLOv5 (mAP 72.4%), and YOLOv7 (mAP 80.6%). This demonstrates its superior capability in efficiently detecting tea buds against complex backgrounds. Additionally, this study proposes a self-built tea bud dataset with three seasons to address the data shortages in tea bud detection.