首页|基于关键点和多帧图像特征融合的限高深度检测网络

基于关键点和多帧图像特征融合的限高深度检测网络

扫码查看
路况检测是智能驾驶中的一项核心任务,其中包含限高检测任务.鉴于学术界中与限高检测相关的研究还不够成熟,文章对限高检测方法进行了研究,提出基于关键点和多帧图像特征融合的限高检测网络.将关键点思想引入限高检测任务,减少不必要的预测,提升检测效率;引入卷积门控循环单元(ConvGRU)对多帧图像进行建模,学习多帧图像之间的上下文关系,提升召回率,降低漏检率;提出空间细节特征(spatial particulars feature,SPF)模块,加强解码层的多尺度特征融合;引入坐标注意力机制,进一步关注目标检测区域,提升模型的查准率.实验结果表明:该网络不仅能够很好地完成限高检测任务,并且相比于BiSeNet、PINet、PSPNet等其他先进网络,能够更好地平衡查准率与召回率,拥有更高的F1值和较少的参数量;同时对于车道线检测任务,在精度与漏检率方面也表现优异,进一步证明了该网络的有效性.
Height Limit Deep Detection Network Based on Key Points and Multi-Frame Image Feature Fusion
Road condition detection is a core task in intelligent driving,including height limit detection tasks.Considering that the research related to height limit de-tection in the academic community is not yet mature,we have conducted research on height limit detection methods and proposed a height limit detection network based on key points and multi-frame image feature fusion.By adopting key points in the height limit detection task,unnecessary predictions are reduced and detection effi-ciency is improved.By introducing a convolutional gated recurrent unit(ConvGRU)to model multiple images and learn the contextual relationship between multiple im-ages,improve recall rate,and reduce missed detection rate.The spatial particulars feature(SPF)module is proposed,which strengthens the multi-scale feature fusion in the decoding layer.In order to improve the accuracy of the model,the coordi-nate attention mechanism is introduced,and the target detection area is further paid attention to.According to the experimental results,this network can not only com-plete the height limit detection task well,but also balance the precision and recall rate better,with higher F1 values and fewer parameters compared with other advanced networks such as BiSeNet,PINet,PSPNet,etc;At the same time,in the task of lane line detection,it also performs excellently in terms of accuracy and missed detection rate,further proving the effectiveness of the network.

Deep learningkey pointsmulti-frame imageheight limit detectionintelligent drivingattention mechanism

刘路生、徐婕、崔峰、谢启伟、龙潜

展开 >

湖北大学计算机与信息工程学院,武汉 430062

北京中科慧眼科技有限公司,北京 100023

北京工业大学现代制造业发展研究基地,北京 100124

天津科技大学人工智能学院,天津 300457

展开 >

深度学习 关键点 多帧图像 限高检测 智能驾驶 注意力机制

国家重点研发计划国家重大研发计划

2020YFA07142012018AAA0103103

2024

系统科学与数学
中国科学院数学与系统科学研究院

系统科学与数学

CSTPCD北大核心
影响因子:0.425
ISSN:1000-0577
年,卷(期):2024.44(7)
  • 6