Timely and effective pest detection is essential for agricultural production, facing challenges such as complex backgrounds and a vast number of parameters. Seeking solutions has become a pressing matter. This paper, based on the YOLOv5 algorithm, developed the PestLite model. The model surpasses previous spatial pooling methods with our uniquely designed Multi-Level Spatial Pyramid Pooling (MTSPPF). Using a lightweight unit, it integrates convolution, normalization, and activation operations. It excels in capturing multi-scale features, ensuring rich extraction of key information at various scales. Notably, MTSPPF not only enhances detection accuracy but also reduces the parameter size, making it ideal for lightweight pest detection models. Additionally, we introduced the Involution and Efficient Channel Attention (ECA) attention mechanisms to enhance contextual understanding. We also replaced traditional upsampling with Content-Aware ReAssembly of FEatures (CARAFE), which enable the model to achieve higher mean average precision in detection. Testing on a pest dataset showed improved accuracy while reducing parameter size. The mAP50 increased from 87.9% to 90.7%, and the parameter count decreased from 7.03 M to 6.09 M. We further validated the PestLite model using the IP102 dataset, and on the other hand, we conducted comparisons with mainstream models. Furthermore, we visualized the detection targets. The results indicate that the PestLite model provides an effective solution for real-time target detection in agricultural pests.

Traffic sign detection significantly reduces traffic accidents, but in real-world scenarios, the considerable distance between traffic signs and in-vehicle cameras means only a small proportion of traffic signs are captured in the images. This makes far-off traffic sign detection a small object detection problem, and with fewer details in small sign objects, detection becomes increasingly challenging. In this paper, we specifically address poor localization, low accuracy, and missed detections when using You Only Look Once Version 5 (YOLOv5) for detecting small traffic sign objects. Firstly, we incorporate a decoupled head into YOLOv5’s detection algorithm, which serves to improve detection accuracy and accelerate network convergence. Then, to handle low-resolution targets better, we substitute the network’s original convolution layers with Space-to-Depth Convolution (SPD-Conv) modules. This modification enhances the model’s capacity to extract features from low-resolution traffic sign objects. Lastly, we integrate the Context Augmentation Module (CAM) into YOLOv5 by employing variable rate extended convolution. This module extracts context information from multiple receptive fields, thus providing essential supplementary information and significantly enhancing detection accuracy. Empirical results demonstrate the efficacy of our algorithm, shown by a substantial increase in object detection precision rate to 95.0%, a recall rate of 91.6%, and an average precision of 95.4%. These results represent improvements of 2.1%, 4.8% and 3.7%, respectively, when compared to the original YOLOv5 algorithm. Furthermore, when tested against other state-of-the-art methods, our proposed methodology shows superior performance.

In industrial production, precise detection of bearing defects is crucial for optimal machinery performance and maintenance, directly impacting the efficiency of industrial systems and the field of instrumentation and measurement. To tackle the diverse types and unique characteristics of bearing defects, we introduce an approach for identifying defects in bearings, named Bearing Enhanced Detection YOLO (BED-YOLO), which is based on convolutional neural networks. We propose the Intelligent Feature Concentration (IFC) module, a lightweight adaptive downsampling technique that exploits the attention mechanism to accurately control the feature compression process, prioritizing the retention of key features through the generation and normalization of spatial attention maps. Additionally, we design the Efficient Feature Fusion for Scalable Convolution (EFFSC) module to capture and fuse multi-scale features through convolution kernels of different sizes and optimize the computational efficiency using grouped convolution, which significantly improves the model expressiveness and processing speed. To ensure the robustness and reliability of our model, we conducted k-fold cross-validation on our BRG-Dataset, which allowed us to thoroughly evaluate the model’s performance and ensure its generalizability. The experimental results show that the BED-YOLO model demonstrates an excellent balance between performance and efficiency. The model achieves a mean Average Precision (mAP50) of 92.5%. Moreover, the model maintains high efficiency with a computational demand of only 7.7 GFLOPS and achieves processing speeds of 312.5 frames per second (FPS), while requiring only 2.5M parameters. These results highlight our model’s superiority in speed and accuracy, making it particularly suitable for real-time applications that require rapid and precise detection, and well-equipped to meet the rigorous demands of industrial defect detection. Further tests on the MS COCO dataset underscore the model’s remarkable adaptability and accuracy. Access to the methodology’s code is provided through GitHub at https://github.com/YOLO-dennis/BED-YOLO.

In the field of aerial remote sensing, detecting small objects in aerial images is challenging. Their subtle presence against broad backgrounds, combined with environmental complexities and low image resolution, complicates identification. While their detection is crucial for urban planning, traffic monitoring, and military reconnaissance, many deep learning approaches demand significant computational resources, hindering real-time applications. To elevate the accuracy of small object detection in aerial imagery and cater to real-time requirements, we introduce SenseLite, a lightweight and efficient model tailored for aerial image object detection. First, we innovatively structured the YOLOv5 model for a more streamlined structure. In the backbone, we replaced the original structure with cutting-edge lightweight neural operator Involution, enhancing contextual semantics and weight distribution. For the neck, we incorporated GSConv and slim-Neck, striking a balance between reduced computational complexity and performance, which is ideal for rapid predictions. Additionally, to enhance detection accuracy, we integrated a squeeze-and-excitation (SE) mechanism to amplify channel communication and improve detection accuracy. Finally, the Soft-NMS strategy was employed to manage overlapping targets, ensuring precise concurrent detections. Performance-wise, SenseLite reduces parameters by 30.5%, from 7.05 M to 4.9 M, as well as computational demands, with GFLOPs decreasing from 15.9 to 11.2. It surpasses the original YOLOv5, showing a 5.5% mAP0.5 improvement, 0.9% higher precision, and 1.4% better recall on the DOTA dataset. Compared to other leading methods, SenseLite stands out in terms of performance.