基于通道注意力和时序改进多摄像头的鸟瞰视角目标检测  

Optimizing Bird's-Eye-View Object Detection from Multi-Camera Images via Channel Attention and Temporal Transformers

作　　者：李伟杰 祁军[2] 潘斌 LI Weijie;QI Jun;PAN Bin(School of Artificial Intelligence and Software Engineering,Liaoning Petrochemical University,Fushun Liaoning 113001,China;School of Information and Control Engineering,Liaoning Petrochemical University,Fushun Liaoning 113001,China;Graduate School,Liaoning Petrochemical University,Fushun Liaoning 113001,China)

机构地区：[1]辽宁石油化工大学人工智能与软件学院,辽宁抚顺113001 [2]辽宁石油化工大学信息与控制工程学院,辽宁抚顺113001 [3]辽宁石油化工大学研究生院,辽宁抚顺113001

出　　处：《辽宁石油化工大学学报》2024年第6期89-96,共8页Journal of Liaoning Petrochemical University

基　　金：国家自然科学基金项目(61602228,61572290);辽宁省教育厅一般项目(L2020018)。

摘　　要：基于摄像头构建的感知和检测系统,以较低的成本和较高的分辨率实现目标检测。通过六个单目相机生成的鸟瞰图(BEV)特征可进行目标检测。其中,BEV特征包含物体的位置和尺度,适用于各种自动驾驶任务。BEV检测器通常与深度预训练的图像骨干相结合,但是两者直接连接并不能突出2D特征与3D特征的对应关系。为了解决以上问题,使用通道注意力对输出特征图加权调整提议特征通道,并与深度估计模块相结合,突出了2D与3D特征的关系;通过时序叠加融合方式解决了继承式融合方式中过去信息逐渐丢失的问题,保证了模型能够充分利用历史信息。在NuScenes数据集上进行了广泛的实验,结果表明归一化累计得分(NDS)达到了0.604,比BEVFormer模型提升了0.035,验证了模型的有效性。A perception and detection system based on cameras achieves target detection with lower cost and higher resolution.Target detection is performed using bird's-eye view(BEV)features generated by six monocular cameras.These BEV features include the position and scale of objects,making them suitable for various autonomous driving tasks.BEV detectors are typically combined with the deep pre-trained image backbones,but directly connecting the two does not effectively highlight the correspondence between 2D and 3D features.To address this issue,Channel Attention is applied to weight and adjust the proposed feature channels in the output feature map,and combined with a depth estimation module to emphasize the relationship between 2D and 3D features.Furthermore,a temporal aggregation fusion method is employed to solve the problem of gradual information loss in traditional fusion methods,ensuring that the model can fully leverage historical information.Extensive experiments on the NuScenes dataset show that the model achieves a Normalized Discounted Cumulative Score(NDS)of 0.604,a 0.035 improvement over the BEVFormer model,validating the effectiveness of the proposed approach.

关 键 词：自动驾驶 鸟瞰图检测 通道注意力 目标检测 注意力机制 时空编码器 

分 类 号：TP389.1[自动化与计算机技术—计算机系统结构]