基于红外图像的行人识别是现代安防系统的重要组成部分.在计算资源受限场景,由于红外行人检测算法中模型尺寸的影响,检测精度与部署难度往往难以平衡.针对此问题,本文提出了一种基于YOLOv5s的轻量化目标检测算法:首先引入MobileNetv3轻量化特征提取网络,并使用深度可分离卷积减小模型尺寸,使其更易部署至CPU设备;其次,将最近邻插值上采样方式替换为CARAFE(Content-Aware ReAssembly of FEatures),明显提升了图像重建效果;最后使用EIOU Loss作为边界框损失函数改善模型回归性能.本文在采样后的LLVIP红外行人图像数据集上进行了测试:对于红外图像下的行人目标,本文在保持高检测精度(AP=95.4％)的同时,模型大小减少80.6％,参数量减少82.8％;在使用CPU平台进行推理时,推理速度提升43.3％,且检测多尺度目标的性能有所提升.以上两方面结果验证了算法的有效性.
Research on pedestrian target detection in lightweight infrared images based on YOLOv5s
Pedestrian recognition based on infrared images is an important component of modern security systems.In scenarios with limited computing resources,it is often difficult to balance the detection accuracy and deployment diffi-culty due to the influence of model size in infrared pedestrian detection algorithms.In response to this issue,a light-weight object detection algorithm based on YOLOv5s is proposed in this paper.Firstly,the MobileNetv3 lightweight feature extraction network is introduced and deep separable convolution is used to reduce the model size,making it easier to deploy to CPU devices.Secondly,the nearest neighbor interpolation upsampling method is replaced with CA-RAFE(Content-Aware ReAssembly of FEatures)which significantly improves the image reconstruction effect.Finally,EIOU Loss is used as the loss function of the bounding box to improve the regression performance of the model.Additionally,tests are conducted on the sampled LLVIP infrared pedestrian image dataset and the results show that for pedestrian targets in infrared images,the model size is reduced by 80.6％and the number of parameters is reduced by 82.8％while maintaining a high detection accuracy(AP=95.4％);and the inference speed is improved by 43.3％when using a CPU platform for inference,and the performance of detecting multi-scale targets is im-proved.The above two results validate the effectiveness of the algorithm.
万方数据
维普
