Pedestrian and Head-Shoulders Cascade Detection Algorithm Based on Attention Enhancement

doi:10.3778/j.issn.1002-8331.2205-0530

Abstract

Abstract: In the surveillance video, pedestrians may have different perspectives and different degrees of occlusion, resulting in a high rate of missed detection and error detection of the current pedestrian detector. Therefore, a pedestrian detector is proposed for cascading detection of the whole pedestrian and the head and shoulder area of the pedestrian with enhanced attention. Firstly, a new channel attention mechanism called fully convolutional channel attention mechanism is proposed. Secondly, channel attention mechanism and spatial attention mechanism are added respectively for classification and regression tasks to enhance effective detection features and suppress background features. Finally, a cascade pedestrian detector is designed for the pedestrian as a whole and the pedestrian head and shoulder area, and the detection results are cascaded through the matching algorithm of the pedestrian as a whole and the pedestrian head and shoulder area. This algorithm also can greatly weaken the missed detection rate, particularly in the case of serious occlusion of the lower body. Experimental results indicate that the log-average missed rate of Reasonable（reasonable subset） pedestrian detection test dataset in Caltech is reduced to 5.37%, and the log-average missed rate of Occ=heavy（severely obscured subset） is reduced to 23.33%. At the same time, the algorithm also has good detection performance on ETH and CityPersons pedestrian detection datasets.

Key words: blocking pedestrian detection, attention mechanism, head-shoulder area detection branch, cascade detector

摘要： 在监控视频中，行人会存在不同视角、不同程度的遮挡问题，导致当前行人检测器漏检率、错检率较高，于是提出了一种注意力增强下的行人整体与行人头肩区域级联检测的行人检测器。提出一种新的通道注意力机制，称为全卷积通道注意力机制；针对分类和回归任务分别融入相适应的注意力机制，来增强有效的检测特征，抑制背景特征信息；设计行人整体与行人头肩区域级联行人检测器，通过行人整体与行人头肩区域的匹配算法，级联地处理检测结果。该算法，尤其针对下半身严重遮挡的情况，极大降低了遮挡行人的漏检率。实验结果表明，在Caltech公开行人检测测试数据集Reasonable（合理子集）的对数平均漏检率降低到5.37%，尤其在Occ=heavy（严重遮挡子集）上的对数平均漏检率降低到23.33%，同时在ETH和CityPersons行人检测数据集上，该算法亦拥有较好的检测效果。

关键词: 遮挡行人检测, 注意力机制, 头肩区域检测分支, 级联检测器

ZHUANG Shuqing, ZHANG Xiaowei, CAO Shuai, SONG Mingchen. Pedestrian and Head-Shoulders Cascade Detection Algorithm Based on Attention Enhancement[J]. Computer Engineering and Applications, 2023, 59(19): 166-176.

庄淑青, 张晓伟, 曹帅, 宋明晨. 基于注意力增强的行人与头肩级联检测算法[J]. 计算机工程与应用, 2023, 59(19): 166-176.

References

[1] 陈宁，李梦璐，袁皓，等.遮挡情形下的行人检测方法综述[J].计算机工程与应用，2020，56（16）：13-20.
CHEN N，LI M L，YUAN H，et al.Review of pedestrian detection with occlusion[J].Computer Engineering and Applications，2020，56（16）：13-20.
[2] SABZMEYDANI P，MORI G.Detecting pedestrians by learning shapelet features[C]//Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition.Los Alamitos，CA，USA：IEEE Press，2007：1-8.
[3] 郭烈，赵宗艳，聂倩，等.利用腿部区域HOG特征的行人检测方法[J].计算机工程与应用，2013，49（1）：217-221.
GUO L，ZHAO Z Y，NIE Q，et al.Pedestrian detection with HOG in region of leg[J].Computer Engineering and Applications，2013，49（1）：217-221.
[4] ZEILER M D，FERGUS R.Visualizing and understanding convolutional networks[C]//Proceedings of the 13th European Conference on Computer Vision.Cham：Springer，2014：818-833.
[5] ZHANG S，JIAN Y，SCHIELE B.Occluded pedestrian detection through guided attention in CNNs[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR）.Los Alamitos，CA，USA：IEEE Press，2018：6995-7003.
[6] ZHANG S，WEN L，BIAN X，et al.Occlusion-aware R-CNN：detecting pedestrians in a crowd[C]//Proceedings of the 15th European Conference on Computer Vision.Cham：Springer，2018：657-674.
[7] WANG X，XIAO T，JIANG Y，et al.Repulsion loss：detecting pedestrians in a crowd[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos，CA，USA：IEEE Press，2018：7774-7783.
[8] BODLA N，SINGH B，CHELLAPPA R，et al.Soft-NMS—improving object detection with one line of code[C]//Proceedings of the IEEE International Conference on Computer Vision.Los Alamitos，CA，USA：IEEE Press，2017：5562-5570.
[9] WU J，ZHOU C，YANG M，et al.Temporal-Context enhanced detection of heavily occluded pedestrians[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR）.Los Alamitos，CA，USA：IEEE Press，2020：13427-13436.
[10] HOU Y，ZHENG L，GOULD S.Multiview detection with feature perspective transformation[C]//Proceedings of the Computer Vision and Pattern Recognition（CVPR）.Los Alamitos，CA，USA：IEEE Press，2020.
[11] 赵世阳，王晓峰.基于多尺度上下文信息的遮挡行人检测[J].计算机工程与应用，2022，58（11）：141-149.
ZHAO S Y，WANG X F.Occluded pedestrian detection based on multi-scale context information[J].Computer Engineering and Applications，2022，58（11）：141-149.
[12] DAI J，LI Y，HE K，et al.R- FCN：object detection via region-based fully convolutional networks[C]//Advances in Neural Information Processing Systems，2016：379-387.
[13] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal neworks[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2016，39（6）：1137-1149.
[14] DAI J，QI H，XIONG Y，et al.Deformable convolutional networks[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision.Los Alamitos，CA，USA：IEEE Press，2017：764-773
[15] LU R，MA H.Semantic head enhanced pedestrian detection in a crowd[J].Neurocomputing，2020，400（4）：343-351.
[16] JIE H，LI S，GANG S，et al.Squeeze-and-excitation networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，42（8）：2011-2023.
[17] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（CVPR）.Los Alamitos，CA，US：IEEE Press，2016：770-778.
[18] FELZENSZWALB P F，GIRSHICK R B，MCALLESTER D，et al.Object detection with discriminatively trained part-based models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2010，32（9）：1627-1645.
[19] SONG T，SUN L，XIE D，et al.Small-scale pedestrian detection based on somatic topology localization and temporal feature aggregation[C]//Proceedings of the European Conference on Computer Vision.Berlin：Springer，2018：554-569.
[20] CAI Z，FAN Q，FERIS R，et al.A unified multi-scale deep convolutional neural network for fast object detection[C]//Proceedings of the European Conference on Computer Vision（ECCV）.Berlin：Springer，2016：354-370.
[21] DOLLAR P，WOJEK C，SCHIELE B，et al.Pedestrian detection：an evaluation of the state of the art[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2011，34（4）：743-761.
[22] ESS A，LEIBE B，SCHINDLER K，et al.Robust multiperson tracking from a mobile platform[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2009，31（10）：1831-1846.
[23] ZHANG S，BENENSON R，SCHIELE B.Filtered channel features for pedestrian detection[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）.Los Alamitos，CA，USA：IEEE Press，2015：1751-1760.
[24] BRAZIL G，LIU X.Pedestrian detection with autoregressive network phases[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway，NJ：IEEE Press，2019：7231-7240.
[25] OUYANG W，WANG X.Joint deep learning for pedestrian detection[C]//Proceedings of the IEEE International Conference on Computer Vision.Berlin：Springer，2013：2056-2063.
[26] ZHANG S，BENENSON R，SCHIELE B.Citypersons：a diverse dataset for pedestrian detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway，NJ：IEEE Press，2017：3213-3221.
[27] WANG S，CHENG J，LIU H，et al.PCN：part and context information for pedestrian detection with CNNs[J].arXiv：1804.04483，2018.
[28] LIN C，LU J，WANG G，et al.Graininess-aware deep feature learning for pedestrian detection[C]//Proceedings of the European Conference on Computer Vision.Berlin：Springer，2018：732-747.
[29] DU X，EI-KHAMY M，MORARIU V I，et al.Fused deep neural networks for efficient pedestrian detection[J].arXiv：1805.08688，2018.
[30] ZHANG L，LIN L，HE K，et al.Is faster R-CNN doing well for pedestrian detection?[J].arXiv：1607.07032，2016.
[31] LIU W，LIAO S，REN W，et al.High-level semantic feature detection：anew perspective for pedestrian detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway，NJ：IEEE Press，2019：5187-5196.
[32] LIU W，LIAO S，HU W，et al.Learning efficient single-stage pedestrian detectors by asymptotic localization fitting[C]//Proceedings of the European Conference on Computer Vision.Berlin：Springer，2018：618-634.
[33] FEI C，LIU B，CHEN Z，et al.Learning pixel-level and instance-level context-aware features for pedestrian detection in crowds[J].IEEE Access，2019，7：94944-94953.