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.

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.