DSCA-Net: Indoor Head Detection Network Using Dual-Stream Information and Channel Attention

QIN Pinle; SHEN Wenxiang; ZENG Jianchao

doi:10.1049/cje.2020.09.011

Volume 29 Issue 6

Dec. 2020

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2020 > 29(6): 1102-1109

QIN Pinle, SHEN Wenxiang, ZENG Jianchao, “DSCA-Net: Indoor Head Detection Network Using Dual-Stream Information and Channel Attention,” Chinese Journal of Electronics, vol. 29, no. 6, pp. 1102-1109, 2020, doi: 10.1049/cje.2020.09.011

Citation:

QIN Pinle, SHEN Wenxiang, ZENG Jianchao, “DSCA-Net: Indoor Head Detection Network Using Dual-Stream Information and Channel Attention,” Chinese Journal of Electronics, vol. 29, no. 6, pp. 1102-1109, 2020, doi: 10.1049/cje.2020.09.011

Citation:

PDF( 5530 KB)

DSCA-Net: Indoor Head Detection Network Using Dual-Stream Information and Channel Attention

doi: 10.1049/cje.2020.09.011

School of Big Data, North University of China, Taiyuan 030051, China

Funds: This work is supported by the Key R&D Projects in Shanxi Province (No.201803D31212-1).

More Information

Corresponding author: ZENG Jianchao (corresponding author) was born in 1963. He received the Ph.D degree in system engineering from Xi'an Jiaotong University. He is a professor, doctoral supervisor. His current research include system engineering, image processing, machine learning and deep learning. (Email:zjc@nuc.edu.cn)
Received Date: 2019-10-30
Publish Date: 2020-12-25

Abstract

Abstract

We propose a novel indoor head detection network using dual-stream information and multi-attention that can be used for indoor crowd counting. To solve the problem of object scale diversity in indoor human head detection, especially the problem of smallscale human head, we propose a dual-stream information flow structure to enrich the positioning and category semantic information of small-scale objects. We propose a kind of structure of the channel-attention mechanism which is used to enhance the ability of the network to identify small-scale objects. Our method has achieved a recall rate of 0.91 and an F1 score of 0.92 on SCUT-HEAD, which achieves the state-of-art performance in the field of indoor crowd detection.
- Pedestrian detection,
- Object detection,
- Attention mechanism,
- Deep learning

FullText(HTML)

References(21)

References

X. Wei, J. Du, M. Liang et al., "Crowd density field estimation based on crowd dynamics theory and social force model", Chinese Journal of Electronics, Vol. 28, No.3, pp.521-528, 2019.

J. Li, Y. Wang, C. Wang, et al., "DSFD:Dual shot face Detector", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp.5055-5064, 2019.

M. Najibi, P. Samangouei, R. Chellappa, et al., "SSH:Single stage headless face detector", IEEE International Conference on Computer Vision (ICCV), Venice, pp.4885-4894, 2017.

S. Zhang, J. Yang and B. Schiele, "Occluded pedestrian detection through guided attention in cnns", IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp.6995-7003, 2018.

J. Mao, T. Xiao, Y. Jiang, et al., "What can help pedestrian detection?", 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp.6034-6043, 2017.

K. Zhang, Z. Zhang, Z. Li, et al., "Joint face detection and alignment using multitask cascaded convolutional networks", IEEE Signal Processing Letters, Vol.23, No.10, pp.1499-1503, 2016.

A. Neubeck and L. Van Gool, "Efficient non-maximum suppression", 18th International Conference on Pattern Recognition (ICPR' 06), Hong Kong, China, pp.850-855, 2006.

B. Singh and L. S. Davis, "An analysis of scale invariance in object detection", 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018.

W. Liu, D. Anguelov, D. Erhan, et al., "SSD:Single shot multibox detector", 14th European Conference, Amsterdam, The Netherlands, pp.21-37, 2016.

T. Lin, P. Dollar, R. Girshick, et al., "Feature pyramid networks for object detection", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, pp.936-944, 2017.

J. Hu, L. Shen and G. Sun, "Squeeze-and-excitation networks", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.42, No.8, pp.2011-2023, 2017.

X. Wang, R. Girshick, A. Gupta, et al., "Non-local neural networks", 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018.

A. Neubeck and L. Van Gool, "Efficient non-maximum suppression", 18th International Conference on Pattern Recognition (ICPR' 06), Hong Kong, China, pp.850-855, 2006.

S. Zhang, L. Wen, X. Bian, et al., "Single-shot renement neural network for object detection", 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp.4203-4212, 2018.

O. Vinyals, A. Toshev, S. Bengio, et al., "Show and tell:Lessons learned from the 2015 MSCOCO image captioning challenge", IEEE Transactions on Pattern Analysis & Machine Intelligence, Vol.39, No.4, pp.652-663, 2016.

T. Vu, A. Osokin and I. Laptev, "Context-aware CNNS for person head detection", International Conference on Computer Vision, ICCV 2015, Santiago, Chile, pp.2893-2901, 2015.

D. Peng, Z. Sun, Z. Chen, et al., "Detecting heads using feature refine net and cascaded multi-scale architecture", International Conference on Pattern Recognition(ICPR), Beijing, China, pp. 2528-2533, 2018.

Y. Zhang, D. Zhou, S. Chen, et al., "Single-image crowd counting via multi-column convolutional neural network", Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, pp.589-597, 2016.

D. B. Sam, S. Surya and R. V. Babu, "Switching convolutional neural network for crowd counting", Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, pp.4031-4039, 2017.

H. Fan and H. Ling, "Sanet:Structure-aware network for visual tracking", 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA, pp.2217-2224, 2016.

F. Jiang, F. Guo and R. Ji, "Dsnet:Accelerate indoor scene semantic segmentation", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom, pp.3317-3321, 2019.

Relative Articles

Supplements(0)

Cited By

Proportional views