A dual-channel SSD pedestrian detection algorithm based on feature fusion

Proceedings of the 7th International Conference on Cyber Security and Information Engineering Pub Date : 2022-09-23 DOI:10.1145/3558819.3565142

Jiangkun Lu, Hongyang Chen

{"title":"A dual-channel SSD pedestrian detection algorithm based on feature fusion","authors":"Jiangkun Lu, Hongyang Chen","doi":"10.1145/3558819.3565142","DOIUrl":null,"url":null,"abstract":"In order to solve the phenomenon of false detection and missed detection in the pedestrian counting algorithm caused by the change of occlusion and illumination in crowded scenes, this paper proposes a dual-channel SSD pedestrian detection algorithm based on feature fusion, which improves pedestrian detection under illumination and occlusion conditions. In the dual-channel SSD network structure, the Conv4_3 and FC7 layers in the color image channel are fused with the Conv4_3 and FC7 layers in the depth image channel in Concat or Eltwise ways to obtain the optimal dual-channel SSD network model. Then, the Conv4_3_Fuse layer in the network is fused with the Conv10_2_Fuse and Conv11_2_Fuse layers to fully learn the feature information of pedestrian heads. The experimental results show that the improved algorithm is tested on the TVHeads data set, and the detection accuracy obtained is 95.4%, which is 13.16% higher than that of the SSD algorithm, which improves the problem of missed detection caused by illumination changes and occlusion, and enhances the detection of pedestrians head recognition.","PeriodicalId":373484,"journal":{"name":"Proceedings of the 7th International Conference on Cyber Security and Information Engineering","volume":"116 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 7th International Conference on Cyber Security and Information Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3558819.3565142","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

In order to solve the phenomenon of false detection and missed detection in the pedestrian counting algorithm caused by the change of occlusion and illumination in crowded scenes, this paper proposes a dual-channel SSD pedestrian detection algorithm based on feature fusion, which improves pedestrian detection under illumination and occlusion conditions. In the dual-channel SSD network structure, the Conv4_3 and FC7 layers in the color image channel are fused with the Conv4_3 and FC7 layers in the depth image channel in Concat or Eltwise ways to obtain the optimal dual-channel SSD network model. Then, the Conv4_3_Fuse layer in the network is fused with the Conv10_2_Fuse and Conv11_2_Fuse layers to fully learn the feature information of pedestrian heads. The experimental results show that the improved algorithm is tested on the TVHeads data set, and the detection accuracy obtained is 95.4%, which is 13.16% higher than that of the SSD algorithm, which improves the problem of missed detection caused by illumination changes and occlusion, and enhances the detection of pedestrians head recognition.

查看原文本刊更多论文

一种基于特征融合的双通道SSD行人检测算法

为了解决拥挤场景中遮挡和照度变化导致的行人计数算法中的误检和漏检现象，本文提出了一种基于特征融合的双通道SSD行人检测算法，改进了光照和遮挡条件下的行人检测。在双通道SSD网络结构中，将彩色图像通道中的Conv4_3和FC7层与深度图像通道中的Conv4_3和FC7层以Concat或Eltwise的方式融合，得到最优的双通道SSD网络模型。然后，将网络中的Conv4_3_Fuse层与Conv10_2_Fuse和Conv11_2_Fuse层进行融合，充分学习行人头部的特征信息。实验结果表明，改进算法在TVHeads数据集上进行了测试，获得的检测准确率为95.4%，比SSD算法提高了13.16%，改善了光照变化和遮挡导致的漏检问题，增强了对行人头部识别的检测。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Proceedings of the 7th International Conference on Cyber Security and Information Engineering

自引率

0.00%

发文量