Herd counting based on VDNet convolutional neural network

DU Yongxing; MIAO Xiaowei; QIN Ling; LI Baoshan

doi:10.7510/jgjs.issn.1001-3806.2021.05.023

LASER TECHNOLOGY > 2021 > 45(5): 675-680. > DOI: 10.7510/jgjs.issn.1001-3806.2021.05.023

DU Yongxing, MIAO Xiaowei, QIN Ling, LI Baoshan. Herd counting based on VDNet convolutional neural network[J]. LASER TECHNOLOGY, 2021, 45(5): 675-680. DOI: 10.7510/jgjs.issn.1001-3806.2021.05.023

Citation:

DU Yongxing, MIAO Xiaowei, QIN Ling, LI Baoshan. Herd counting based on VDNet convolutional neural network[J]. LASER TECHNOLOGY, 2021, 45(5): 675-680. DOI: 10.7510/jgjs.issn.1001-3806.2021.05.023

Citation:

DU Yongxing, MIAO Xiaowei, QIN Ling, LI Baoshan. Herd counting based on VDNet convolutional neural network[J]. LASER TECHNOLOGY, 2021, 45(5): 675-680. DOI: 10.7510/jgjs.issn.1001-3806.2021.05.023

PDF (5038 KB)

Herd counting based on VDNet convolutional neural network

School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou 014000, China

More Information

Received Date: September 08, 2020
Revised Date: October 08, 2020
Published Date: September 24, 2021

Graphical Abstract

Abstract

Abstract

In order to avoid the interference of mutual occlusion between sheep in the traditional flock counting task and improve the accuracy of flock counting, the VDNet(VGG-16+DC net) convolutional neural network flock counting method, combining visual geometry group(VGG) 16 and dialated convolution (DC) net, was adopted. VGG-16 with the fully connected layer removed was used at the front end of the network to extract 2-D features, 6 layers of DC with different dilated rates was used to extract more advanced features. DC expanded the receptive field, replaced the pooling operation, and decreased the complexity of the network while kept the resolution unchanged at the same time. The theoretical analysis and experimental verification were carried out. Finally, a convolutional layer with a convolution kernel size of 1×1 was used to output a high-quality density map, and then the number of sheep in the input image was obtained by integrating the pixels of the density map. The results show that the average absolute error of the counting method in this paper is 2.51, the mean square error is 3.74, and the average accuracy is 93%, respectively. This result is helpful for the task of counting sheep.
- image processing,
- sheep count,
- dilated convolution,
- convolutional neural network

FullText(HTML)

References (21)

References

[1]	TIAN L. Design of sheep number detection system[D]. Hohhot: Inner Mongolia University, 2019: 45-57(in Chinese).
[2]	ZHANG L, XU J, TIAN Z, et al. Research and implementation of intelligent counting sheep system in pastoral areas[J]. Telecom Power Technologies, 2017, 34(4): 165-166(in Chinese). http://en.cnki.com.cn/Article_en/CJFDTotal-TXDY201704069.htm
[3]	ENZWEILER M, GAVRILA D, GAVRILA D M. Monocular pedestrian detection: Survey and experiments[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(12): 2179-2195. DOI: 10.1109/TPAMI.2008.260
[4]	JONES M J, SNOW D. Pedestrian detection using boosted features over many frames[C]// International Conference on Pattern Recognition. New York, USA: IEEE, 2008: 8-11.
[5]	WU B, NEVATIA R. Detection and tracking of multiple, partially occluded humans by bayesian combination of edgelet based part detectors[J]. International Journal of Computer Vision, 2007, 75(2): 247-266. DOI: 10.1007/s11263-006-0027-7
[6]	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. DOI: 10.1109/TPAMI.2009.167
[7]	LIU T, TAO D. On the robustness and generalization of cauchy regression[C]// 2014 4th IEEE International Conference on Information Science and Technology (ICIST). New York, USA: IEEE, 2014: 32-37.
[8]	ZHAI J Y, TU L Zh, ZHUANG Y. Saliency detection based on boundary prior and adaptive region merging[J]. Computer Engineering and Applications, 2018, 54(6): 178-182(in Chinese). http://en.cnki.com.cn/Article_en/CJFDTotal-JSGG201806029.htm
[9]	ZENG L, XU X, CAI B, et al. Multi-scale convolutional neural networks for crowd counting[C]// 2017 IEEE International Conference on Image Processing (ICIP). New York, USA: IEEE, 2017: 89-91.
[10]	HUANG S Y, LI X, CHENG Zh Q, et al. Stacked pooling: Improving crowd counting by boosting scale invariance[J]. Computer Vision and Pattern Recognition, 2018(22): 46-52. http://arxiv.org/abs/1808.07456
[11]	ZHANG Y, ZHOU D, CHEN S, et al. Single-image crowd counting via multi-column convolutional neural network[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York, USA: IEEE, 2016: 98-103.
[12]	WU X, ZHENG Y, YE H, et al. Adaptive scenario discovery for crowd counting[J]. Computer Vision and Pattern Recognition, 2019(9): 12-16. http://ieeexplore.ieee.org/document/8683744
[13]	OORO-RUBIO D, LÓPEZ-SASTRE R J. Towards perspective-free object counting with deep learning[C]// European Conference on Computer Vision(ECCV) 2016. New York, USA: IEEE, 2016: 56-64.
[14]	LEI H L. Crowd counting algorithm based on multi model deep convolution network fusion[D]. Hohhot: Inner Mongolia University, 2020: 32-37(in Chinese).
[15]	TANG S Y, TAO Y, ZHANG L L, et al. A deep crowd counting algorithm based on multi-column feature map fusion. Journal of Zhengzhou University (Natural Science Edition), 2018, 50(2): 69-74(in Chinese).
[16]	WANG Y J, ZHANG W, LIU Y Y, et al. Two-branch fusion network with attention map for crowd counting[J]. Neurocomputing, 2020, 411: 1-8. DOI: 10.1016/j.neucom.2020.06.034
[17]	WANG S, LU Y, ZHOU T, et al. SCLNet: Spatial context learning network for congested crowd counting[J]. Neurocomputing, 2020, 404: 227-239. DOI: 10.1016/j.neucom.2020.04.139
[18]	WU X, ZHENG Y, YE H, et al. Counting crowds with varying densities via adaptive scenario discovery framework[J]. Neurocomputing. 2020, 397: 127-138. DOI: 10.1016/j.neucom.2020.02.045
[19]	LI Y, ZHANG X, CHEN D. CSRNet: Dilated convolutional neural networks for understanding the highly congested scenes[J]. Computer Vision and Pattern Recognition, 2018 (27): 31-39. http://ieeexplore.ieee.org/document/8578218
[20]	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. Computer Vision and Pattern Recognition, 2014(4): 19-25. http://arxiv.org/abs/1409.1556
[21]	ZHANG C, LI H, WANG X, et al. Cross-scene crowd counting via deep convolutional neural networks[C]// 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York, USA: IEEE, 2015: 17-29.

Cited By

Cited by

Periodical cited type(7)

1.	孙佳鑫，钱传鹏，徐作冬，张检民，叶锡生. 长波量子阱红外探测器激光辐照损伤脉宽效应数值模拟. 激光与光电子学进展. 2024(21): 290-297 .
2.	胡蔚敏，王小军，田昌勇，杨晶，刘可，彭钦军. 脉宽对中红外激光带内损伤HgCdTe材料的影响. 强激光与粒子束. 2022(01): 130-137 .
3.	王云萍，侯军燕，袁春，康文运，陈安民，张鲁薇. 飞秒激光对多光谱滤波片的损伤阈值研究. 激光技术. 2022(05): 697-701 . 本站查看
4.	李玉瑶，王菲，孙同同. 薄膜激光损伤阈值标定技术. 激光技术. 2021(06): 729-734 . 本站查看
5.	白凤凤，武桂芬. 光学薄膜激光损伤阈值的智能检测研究. 激光杂志. 2020(02): 171-175 .
6.	周冰，贺宣，刘贺雄，李秉璇，张炎. 激光辐照非制冷微测辐射热计的理论研究. 激光技术. 2020(04): 411-417 . 本站查看
7.	任晓东，雷武虎，曾凌清，王勇. 基于相对运动的脉冲激光辐照探测器热效应数值分析. 光子学报. 2019(01): 105-111 .

Other cited types(2)

Get Citation

PDF

XML

Article views (7) PDF downloads (4) Cited by(9)

Turn off MathJax

Article Contents

Abstract

References

Herd counting based on VDNet convolutional neural network

Abstract

References

Cited by

Periodical cited type(7)

Other cited types(2)

Catalog

Links：

Herd counting based on VDNet convolutional neural network

Abstract

References

Cited by

Periodical cited type(7)

Other cited types(2)

Catalog

Links：

Export File

Citation

Format

Content