基于分割注意力与线性变换的轻量化目标检测

Lightweight object detection based on split attention and linear transformation

为了满足目标检测的实时性和模型轻量化需求,提高目标检测精度,对YOLOv5中的特征融合模块进行优化,提出基于金字塔分割注意力与线性变换的轻量化目标检测算法PG-YOLOv5.利用金字塔分割注意力模块,捕获不同尺度特征图的空间信息以丰富特征空间,提升网络的多尺度特征表示能力,提高目标检测的精度.利用基于线性变换的GhostBottleNeck模块,以少量原始特征图与线性变换得到的特征图相结合的方式,有效减少模型参数量.算法的平均精度均值从YOLOv5L的81.2%提高到PG-YOLOv5的85.7%,PG-YOLOv5的参数量比YOLOv5L的下降了36%.将PG-YOLOv5部署到Jetson TX2,并编写目标检测软件.实验结果表明,基于Jetson TX2的目标检测系统的图像处理速度为262.1 ms/帧,PG-YOLOv5的平均精度均值为85.2%;与YOLOv5原始模型相比,PG-YOLOv5更适合边缘端部署.

To meet the real-time and model lightweight requirements of target detection and improve the accuracy of object detection,a lightweight target detection algorithm PG-YOLOv5 based on pyramid split attention and linear transformation was proposed.The feature fusion module in YOLOv5 was optimized by PG-YOLOv5.First,the pyramid split attention module was used to capture the spatial information of feature maps at different scales to enrich the feature space,thus the multi-scale feature representation ability of the network and the accuracy of object detection were improved.Then,the GhostBottleNeck module based on linear transformation was used to combine a small amount of original feature maps with those obtained from linear transformation,which reduced the number of model parameters effectively.The mean average precision of the algorithm increased from 81.2%of YOLOv5L to 85.7%of PG-YOLOv5,and the number of parameters of PG-YOLOv5 was 36%lower than that of YOLOv5L.The PG-YOLOv5 was deployed on Jetson TX2 and an object detection software was designed.Experimental results showed that the image processing speed of the target detection system based on Jetson TX2 was 262.1 ms/frame,and the mean average precision of PG-YOLOv5 was 85.2%.Compared with the YOLOv5L original model,PG-YOLOv5 is more suitable for edge deployment.