基于关键点和多帧图像特征融合的限高深度检测网络
Height Limit Deep Detection Network Based on Key Points and Multi-Frame Image Feature Fusion
刘路生 1徐婕 1崔峰 2谢启伟 3龙潜4
作者信息
- 1. 湖北大学计算机与信息工程学院,武汉 430062
- 2. 北京中科慧眼科技有限公司,北京 100023
- 3. 北京工业大学现代制造业发展研究基地,北京 100124
- 4. 天津科技大学人工智能学院,天津 300457
- 折叠
摘要
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.
Abstract
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.
关键词
深度学习/关键点/多帧图像/限高检测/智能驾驶/注意力机制Key words
Deep learning/key points/multi-frame image/height limit detection/intelligent driving/attention mechanism引用本文复制引用
基金项目
国家重点研发计划(2020YFA0714201)
国家重大研发计划(2018AAA0103103)
出版年
2024
NETL
NSTL
万方数据