A forest wildlife detection algorithm based on an improved YOLOv5s network model is proposed to advance forest wildlife monitoring and improve detection accuracy in complex forest environments. This research utilizes a data set from the Hunan Hupingshan National Nature Reserve in China, to which data augmentation and expansion methods are applied to extensively train the proposed model. To enhance the feature extraction ability of the proposed model, a weighted channel stitching method based on channel attention is introduced. The Swin Transformer module is combined with a CNN network to add a Self-Attention mechanism, thus improving the perceptual field for feature extraction. Furthermore, a new loss function (DIOU_Loss) and an adaptive class suppression loss (L_BCE) are adopted to accelerate the model’s convergence speed, reduce false detections in confusing categories, and increase its accuracy. When comparing our improved algorithm with the original YOLOv5s network model under the same experimental conditions and data set, significant improvements are observed, in particular, the mean average precision (mAP) is increased from 72.6% to 89.4%, comprising an accuracy improvement of 16.8%. Our improved algorithm also outperforms popular target detection algorithms, including YOLOv5s, YOLOv3, RetinaNet, and Faster-RCNN. Our proposed improvement measures can well address the challenges posed by the low contrast between background and targets, as well as occlusion and overlap, in forest wildlife images captured by trap cameras. These measures provide practical solutions for enhanced forest wildlife protection and facilitate efficient data acquisition.

Considering the high requirements of current kiwifruit picking recognition systems for mobile devices, including the small number of available features for image targets and small-scale aggregation, an enhanced YOLOX-S target detection algorithm for kiwifruit picking robots is proposed in this study. This involved designing a new multi-scale feature integration structure in which, with the aim of providing a small and lightweight model, the feature maps used for detecting large targets in the YOLOX model are eliminated, the feature map of small targets is sampled through the nearest neighbor values, the superficial features are spliced with the final features, the gradient of the SiLU activation function is perturbed, and the loss function at the output is optimized. The experimental results show that, compared with the original YOLOX-S, the enhanced model improved the detection average precision (AP) of kiwifruit images by 6.52%, reduced the number of model parameters by 44.8%, and improved the model detection speed by 63.9%. Hence, with its outstanding effectiveness and relatively light weight, the proposed model is capable of effectively providing data support for the 3D positioning and automated picking of kiwifruit. It may also successfully provide solutions in similar fields related to small target detection.

Background: Pesticide efficacy directly affects crop yield and quality, making targeted spraying a more environmentally friendly and effective method of pesticide application. Common targeted cabbage spraying methods often involve object detection networks. However, complex natural and lighting conditions pose challenges in the accurate detection and positioning of cabbage. Results: In this study, a cabbage detection algorithm based on the YOLOv8n neural network (YOLOv8-cabbage) combined with a positioning system constructed using a Realsense depth camera is proposed. Initially, four of the currently available high-performance object detection models were compared, and YOLOv8n was selected as the transfer learning model for field cabbage detection. Data augmentation and expansion methods were applied to extensively train the model, a large kernel convolution method was proposed to improve the bottleneck section, the Swin transformer module was combined with the convolutional neural network (CNN) to expand the perceptual field of feature extraction and improve edge detection effectiveness, and a nonlocal attention mechanism was added to enhance feature extraction. Ablation experiments were conducted on the same dataset under the same experimental conditions, and the improved model increased the mean average precision (mAP) from 88.8% to 93.9%. Subsequently, depth maps and colour maps were aligned pixelwise to obtain the three-dimensional coordinates of the cabbages via coordinate system conversion. The positioning error of the three-dimensional coordinate cabbage identification and positioning system was (11.2 mm, 10.225 mm, 25.3 mm), which meets the usage requirements. Conclusions: We have achieved accurate cabbage positioning. The object detection system proposed here can detect cabbage in real time in complex field environments, providing technical support for targeted spraying applications and positioning.

To solve the problems of poor adaptability and large sizes of pepper harvesting machinery in facility agriculture to enhance the efficiency and quality of pepper harvesting and ultimately boost farmers’ income, several flexible end-effectors were designed. These end-effectors were tailored to the unique morphologies of horn peppers, drawing inspiration from biomimicry. Subsequently, we conducted experimental verification to validate their performance. Four biological features, namely, the outer contours of a Vicia faba L. fruit, an Abelmoschus esculentus fruit, the upper jaw of a Lucanidae, and a Procambarus clarkii claw, were selected and designed using 3D software. In order to ascertain the structural viability and establish the initial design framework for the test end-effector, a simulation analysis to evaluate the strength and deformation of the flexible end-effector under various pepper-picking conditions was conducted. PLA material and 3D printing technology were used to create the end-effector, and, together with the mobile robotic arm platform ROSMASTER X3 PLUS, they were used to build a test prototype; a pepper tensile test was performed to pre-determine the reasonableness of the picking program, and then a prototype was created for the actual picking of the peppers to compare the picking effectiveness of several types of flexible end-effectors. In six experiments, each flexible end was harvested for 120 horn peppers. The Vicia faba L. flexible end-effector had the lowest average breakage rate. The average breakage rate was 1.7%. At the same time, it had the lowest average drop rate. The average drop rate was 3.3%. The test results indicated that the flexible end-effector that emulated the outer contour characteristics of the Vicia faba L. fruit demonstrated the most favorable outcomes. This design exhibited high working efficiency and the lowest rates of fruit breakage and fruit drops, surpassing both the artificial and traditional machine picking methods and effectively fulfilling the requirements for pepper-picking operations in facility agriculture.

We developed an adaptive algorithm to reduce rice loss in harvesting, promote threshing and improve the quality and efficiency of small- and medium-sized rice harvesters operating in southern China’s hilly and mountainous areas. Using a fuzzy PID control algorithm, the harvester adapts to the rice harvesting conditions in southern China, and monitors rice feed volume changes and instantly adjust the traveling speed to optimize feed volume levels and threshing quality. We compared and analyzed the algorithm and the traditional PID control regulation effect in the simulation experiment. The algorithm had a quicker response speed and stable accuracy. In the field trial, the average error rate was 3.4%, and the maximum error rate was 5.1%, with most data points centered around the ideal feeding rate of 3.2 kg/s. Our results showed that the algorithm’s stability, accuracy, and real-time performance met the threshing loss reduction requirements of southern China’s rice harvesting operations.

To address the challenges of unstable target localization and poor multi-module coordination in automated green pepper harvesting—caused by occlusions from branches and leaves, as well as varying lighting conditions—this paper presents the design and implementation of a modular robotic picking system. At the perception level, the system integrates a YOLOv8 detector with a RealSense D435i camera to identify and locate the calyx–ectocarp junctions of green peppers. A multi-target tracking with filtering algorithm is proposed, combining IoU-based association, Mahalanobis-distance-based matching, the Hungarian algorithm, Kalman filtering, and single exponential smoothing. This algorithm suppresses depth noise and trajectory jitter, thereby enhancing the stability and accuracy of 3D localization. At the control and execution level, a depth-first picking sequence strategy with ID freeze-state management is implemented within a multithreaded software–hardware co-design architecture. This approach avoids task conflicts and duplicate operations while supporting continuous multi-fruit harvesting. Field experiments under natural outdoor lighting and varying occlusion levels demon-strate that the proposed system achieves recognition rates of 91.57% and 80.29%, and harvesting success rates of 82.85% and 77.68% for non-occluded and lightly occluded fruits, respectively. The average picking cycle per pepper fruit is 9.8 s. This system provides an effective technical solution for addressing stability control challenges in the automated harvesting process of green peppers.