A Pedestrian Detection Algorithm Based on Improved YOLOv7-tiny

Abstract

With the widespread development of embedded device applications based on deep learning, pedestrian detection using deep learning often requires the use of complex and large neural networks. However, these networks have a large memory footprint, which makes them difficult to deploy on embedded devices, and are computationally intensive, which makes it difficult to guarantee the speed of operation on embedded devices. To address these issues, a lightweight network, YOLO-Micro, is proposed in this paper. The model reduces the complexity of the model by replacing the original module in YOLOv7-tiny with the G-ELAN module proposed in this paper. Meanwhile, the attention mechanism and the activation function were introduced and replaced to enhance the feature extraction capability of the model. Finally, the model was successfully deployed to Android mobile. Experimental results on the PASCAL VOC Pedestrian dataset show that the inference speed of YOLO-Micro is 20.8% faster than the original model, and the mAP is improved from 77.95% to 79.42% of the original model.