采用长距离依赖和多尺度表达的轻量化车辆检测

Lightweight vehicle detection using long-distance dependence and multi-scale representation

基于深度学习的车辆检测在众多领域发挥着至关重要的作用,是近年来计算机视觉的一个重要发展方向。车辆轻量化检测包含了对网络结构和计算效率的探索,并在智慧交通等诸多领域都得以广泛应用。然而在诸多场景下存在相机中车辆目标尺度变化大、车辆相互遮挡等问题,这些情况会影响到网络检测车辆的精度。针对上述问题,提出改进Yolov5s的车辆检测方法。首先通过视觉注意力网络捕获长距离依赖,对原有特征图施加新的权重,增强自适应性,提升网络的抗遮挡能力;接着在残差模块内部再次构造水平方向残差,在一个模块内部构建相同数量、不同大小感受野的特征图,丰富网络的多尺度表达能力。实验结果表明:改进后的网络在Pascal VOC车辆数据集上提供2.1%mAP性能提升,在MS COCO车辆数据集上提供1.7%mAP性能提升。改进后网络的多尺度表达能力更加出色,且抗遮挡能力更强,与原始网络相比检测结果更具有竞争力。

Vehicle detection based on deep learning plays a vital role in many fields.In recent years,it has presented a major development direction for computer vision.Lightweight vehicle detection includes the exploration of network structure and computing efficiency,and it is widely used in many fields such as in⁃telligent transportation.However,challenges exist in different scenarios,such as large changes in vehicle scale in detection cameras and vehicles overlapping each other,which reduce the precision of the network in detecting vehicles.To solve these problems,this study proposes an improved YOLOv5s method for de⁃tecting vehicles.First,the study proposes to capture long-distance dependencies between objects through a visual attention network and apply new weights to the network’s original feature map to increase the adaptability of the network.These operations improve the anti-occlusion ability of the network.Second,the horizontal residual is constructedagain in the residual module.The output feature maps contain the same number and different sizes of receptive fields per module.Feature extraction occurs at a more fine-grained level,thereby enriching the multi-scale representation ability of the network.The experimental re⁃sults show that the improved network provides 2.1%mAP performance on the Pascal visual object classes(VOC)vehicle telemetry dataset and a 1.7%mAP performance on the MS COCO vehicle telemetry data⁃set.The performance of the improved network is more powerful and its anti-occlusion ability is enhanced.Compared with the original network,the detection results are more competitive.