Assessment of Small Object Detection Algorithm Based on Improved YOLOv5s

The YOLOv5 algorithm is widely used in object detection due to its efficient inference speed and high accuracy. However, it still faces challenges in small object detection. This paper proposes a series of improvements, including the addition of small object detection layers, the integration of the CBAM attention mechanism, and the optimization of the loss function by introducing EIoU, to enhance the model's feature extraction capability and detection accuracy. First, the paper enhances the network's perception of small objects by adding pyramid low-level semantic layers and constructing new small object detection heads. Second, the CBAM module is integrated into the C3 module, improving the model's feature representation ability and effectively preventing information loss. Finally, by introducing the EIoU loss function, the quality contribution of anchor boxes is enhanced, improving the model's detection accuracy and regression speed. Experimental results show that the improved YOLOv5 algorithm performs excellently on the BDD100K dataset, especially in small object detection. Compared with the original algorithm, it shows improvements in detection accuracy, recall rate, and mean average precision (mAP), despite the slight increase in parameters and computation, it still meets real-time requirements. This research provides strong support for further enhancing small object detection in autonomous driving scenarios.