摘要
错误的目标检测可能导致严重事故,因此高精度的目标检测在汽车自动驾驶中至关重要。提出了一种嵌入注意力和特征交织模块的Gaussian-YOLO v3目标检测方法。该方法主要对Gaussian-YOLO v3的几个特定特征图进行了改进:首先在特征图中添加注意力模块以自主学习每个通道的权重,增强关键特征、抑制冗余特征,从而加强网络对前景目标和背景的区分能力;其次,同时将特征图的不同通道进行特征交织得到更具表征性的特征;最后,把注意力和特征交织模块分别得到的特征融合构成新的特征图。实验结果表明,所提方法在BDD100K数据集上达到了20.81%的平均精确率均值(mAP)和18.17%的F1分数,使误报率减少了3.5%,意味着误报率得到了有效降低。由此可见,所提方法的检测性能优于YOLO v3和Gaussian-YOLO v3。
Wrong object detection may lead to serious accidents,so high-precision object detection is very important in autonomous driving.An object detection method of Gaussian-YOLO v3 combining attention and feature intertwine module was proposed,in which several specific feature maps were mainly improved.First,the attention module was added to the feature map to learn the weight of each channel autonomously,enhancing the key features and suppressing the redundant features,so as to enhance the network ability to distinguish foreground object and background.Second,at the same time,different channels of the feature map were intertwined to obtain more representative features.Finally,the features obtained by the attention and feature intertwine modules were fused to form a new feature map.Experimental results show that the proposed method achieves mAP(mean Average Precision)of 20.81%and F1 score of 18.17%on BDD100K dataset,and has the false alarm rate decreased by 3.5 percentage points,reducing the false alarm rate effectively.It can be seen that the detection performance of the proposed method is better than those of YOLO v3 and Gaussian-YOLO v3.
作者
刘丹
吴亚娟
罗南超
郑伯川
LIU Dan;WU Yajuan;LUO Nanchao;ZHENG Bochuan(School of Computer Science,China West Normal University,Nanchong Sichuan 637002,China;School of Computer Science and Technology,Aba Teachers University,Aba Sichuan 623002,China;School of Mathematics and Information,China West Normal University,Nanchong Sichuan 637002,China)
出处
《计算机应用》
CSCD
北大核心
2020年第8期2225-2230,共6页
journal of Computer Applications
基金
四川省科技计划项目(2019YFG0299)
西华师范大学基本科研项目(19B045)
西华师范大学大学生创新创业项目(cxcy2018305)。
