Semantic enhanced guide feature reconstruction for occluded pedestrian detection

被引：0

作者：

Sun X. ^{[1
]}

Wu Q. ^{[1
]}

Zhao C. ^{[1
]}

Zhang M. ^{[1
]}

机构：

[1] School of Artificial Intelligence, Hebei University of Technology, Tianjin

来源：

Hongwai yu Jiguang Gongcheng/Infrared and Laser Engineering | 2022年 / 51卷 / 09期

关键词：

feature reconstruction; pedestrian detection; semantic feature enhancement; semantic segmentation;

D O I：

10.3788/IRLA20210924

中图分类号：

学科分类号：

摘要：

In pedestrian detection, the inability to extract effective features due to pedestrians being severely occluded is one of the main reasons for missing pedestrian detection. To solve this problem, a semantic enhanced guided feature reconstruction algorithm for occlusion pedestrian detection is proposed. Firstly, the semantic feature enhancement module is designed based on the dependency between space and channel, and the global context information is established to enhance the feature of occlusion of pedestrians. Secondly, in order to focus on the visible area of pedestrians, the adaptive feature reconstruction module is used to generate the semantic segmentation map, and adaptively adjust the effective weight of the channel, enhance the distinguishability of pedestrians and background. Finally, the multi-level feature map is obtained by multi-level cascade two modules of semantic feature enhancement and adaptive feature reconstruction, and the multiple features are fusion for the final pedestrian analysis detection. On the challenging pedestrian detection benchmark CityPersons and Caltech, experimental results show that the proposed method achieves the missed rate of 47.28% and 44.04%, respectively, which effectively robust compared with other methods in the detection of occluded pedestrian. © 2022 Chinese Society of Astronautics. All rights reserved.

引用

共 29 条

[1]

Xu Xinkai, Ma Yan, Qian Xu, Et al., Scale-aware EfficientDet: Real-time pedestrian detection algorithm for automated driving, Journal of Image and Graphics, 26, 1, pp. 93-100, (2021)

[2]

Sun J B, Ji J., Memory-augmented deep autoencoder model for pedestrian abnormal behavior detection in video surveillance, Infrared and Laser Engineering, 51, 6, (2022)

[3]

Zhang Ruiyan, Jiang Xiujie, An Junshe, Et al., Design of global-contextual detection model for optical remote sensing targets, Chinese Optics, 13, 6, pp. 1302-1313, (2020)

[4]

Wang Jianlin, Fu Xuesong, Huang Zhanchao, Et al., Multitype cooperative targets detection using improved YOLOv2 convolutional neural network, Optics and Precision Engineering, 28, 1, pp. 251-260, (2020)

[5]

Wang Chunzhe, An Junshe, Jiang Xiujie, Et al., Region proposal optimization algorithm based on convolutional neural networks, Chinese Optics, 12, 6, pp. 1348-1361, (2019)

[6]

Xue Shan, Zhang Zhen, Lv Qiongying, Et al., Image recognition method of anti UAV system based on convolutional neural network, Infrared and Laser Engineering, 49, 7, (2020)

[7]

Noh J, Lee S, Kim B, Et al., Improving occlusion and hard negative handling for single-stage pedestrian detectors, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 966-974, (2018)

[8]

Yang P, Zhang G, Wang L, Et al., A part-aware multi-scale fully convolutional network for pedestrian detection, IEEE Transactions on Intelligent Transportation Systems, 22, 2, pp. 1125-1137, (2020)

[9]

Wang X, Xiao T, Jiang Y, Et al., Repulsion loss: Detecting pedestrians in a crowd, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7774-7783, (2018)

[10]

Zhang S, Wen L, Bian X, Et al., Occlusion-aware R-CNN: Detecting pedestrians in a crowd, Proceedings of the European Conference on Computer Vision (ECCV), pp. 637-653, (2018)

← 1 2 3 →