Introduction: To enhance the detection of litchi fruits in natural scenes, address challenges such as dense occlusion and small target identification, this paper proposes a novel multimodal target detection method, denoted as YOLOv5-Litchi.Methods: Initially, the Neck layer network of YOLOv5s is simplified by changing its FPN+PAN structure to an FPN structure and increasing the number of detection heads from 3 to 5. Additionally, the detection heads with resolutions of 80 × 80 pixels and 160 × 160 pixels are replaced by TSCD detection heads to enhance the model's ability to detect small targets. Subsequently, the positioning loss function is replaced with the EIoU loss function, and the confidence loss is substituted by VFLoss to further improve the accuracy of the detection bounding box and reduce the missed detection rate in occluded targets. A sliding slice method is then employed to predict image targets, thereby reducing the miss rate of small targets.Results: Experimental results demonstrate that the proposed model improves accuracy, recall, and mean average precision (mAP) by 9.5, 0.9, and 12.3 percentage points, respectively, compared to the original YOLOv5s model. When benchmarked against other models such as YOLOx, YOLOv6, and YOLOv8, the proposed model's AP value increases by 4.0, 6.3, and 3.7 percentage points, respectively.Discussion: The improved network exhibits distinct improvements, primarily focusing on enhancing the recall rate and AP value, thereby reducing the missed detection rate which exhibiting a reduced number of missed targets and a more accurate prediction frame, indicating its suitability for litchi fruit detection. Therefore, this method significantly enhances the detection accuracy of mature litchi fruits and effectively addresses the challenges of dense occlusion and small target detection, providing crucial technical support for subsequent litchi yield estimation.

This paper introduces an advanced and efficient method for distributed drone-based fruit recognition and localization, tailored to satisfy the precision and security requirements of autonomous agricultural operations. Our method incorporates depth information to ensure precise localization and utilizes a streamlined detection network centered on the RepVGG module. This module replaces the traditional C2f module, enhancing detection performance while maintaining speed. To bolster the detection of small, distant fruits in complex settings, we integrate Selective Kernel Attention (SKAttention) and a specialized small-target detection layer. This adaptation allows the system to manage difficult conditions, such as variable lighting and obstructive foliage. To reinforce security, the tasks of recognition and localization are distributed among multiple drones, enhancing resilience against tampering and data manipulation. This distribution also optimizes resource allocation through collaborative processing. The model remains lightweight and is optimized for rapid and accurate detection, which is essential for real-time applications. Our proposed system, validated with a D435 depth camera, achieves a mean Average Precision (mAP) of 0.943 and a frame rate of 169 FPS, which represents a significant improvement over the baseline by 0.039 percentage points and 25 FPS, respectively. Additionally, the average localization error is reduced to 0.82 cm, highlighting the model’s high precision. These enhancements render our system highly effective for secure, autonomous fruit-picking operations, effectively addressing significant performance and cybersecurity challenges in agriculture. This approach establishes a foundation for reliable, efficient, and secure distributed fruit-picking applications, facilitating the advancement of autonomous systems in contemporary agricultural practices.

In large-scale cattle farming, accurate behavior recognition is central to achieving intensive health monitoring and animal welfare assessment. To address challenges such as background interference from fences, feed troughs, and stains in real-world barns, and overlapping of cattle coupled with the inability of single-RGB modalities to capture physical spatial structure, which leads to issues like blurred detection boundaries and significant noise interference—we propose a cattle behavior detection method based on RGB-Depth dual-modal information fusion. This approach jointly models the texture information from RGB images and the spatial structural information from depth images. Within this framework, this paper constructs three collaborative optimization modules: first, the CDSAM module is developed, which evaluates neuron importance through a parameter-free attention mechanism and combines dynamic convolutions to adapt to the cattle’s variable postures, effectively suppressing complex background noise. Second, we propose the C2BRA module based on a two-layer routed attention mechanism. By adopting a two-stage modeling approach of “region-level routing—intra-region fine-grained attention,” it adapts to changes in target scale and enhances the model’s ability to represent spatial context for multi-scale semantic information. Finally, in the prediction stage, a lightweight shared convolutional detection head (LSCD) is introduced. By sharing convolutional parameters across scales and decoupling the classification and regression architectures, it reduces computational overhead while maintaining accuracy. Experimental results show that the improved model achieves a mAP@0.5 of 90.3% on our self-built cattle behavior dataset, representing a 4.3 percentage point increase compared to the baseline model, while reducing GFLOPs from 11.0 G to 9.6 G, a decrease of 12.7%; Visualization results indicate that the improved model can focus more accurately on cattle body contours and key behavioral regions, thereby reducing false negatives and enhancing detection accuracy. Concurrently, the model achieves an optimal balance between detection performance and computational complexity, providing robust technical support for automated cattle behavior monitoring on smart farms.