An Improved Multibranch Convolutional Neural Network with a Compensator for Crowd Counting
Image-based crowd counting has extremely important applications in public safety issues. Most of the previous studies focused on extremely dense crowds. However, as the number of webcams increases, a crowd with extremely high density can obtain less error by summing the images of multiple close-rang...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2022/8213855 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832550156674793472 |
|---|---|
| author | Zhiyun Zheng Zhenhao Sun Guanglei Zhu Zhenfei Wang Junfeng Wang |
| author_facet | Zhiyun Zheng Zhenhao Sun Guanglei Zhu Zhenfei Wang Junfeng Wang |
| author_sort | Zhiyun Zheng |
| collection | DOAJ |
| description | Image-based crowd counting has extremely important applications in public safety issues. Most of the previous studies focused on extremely dense crowds. However, as the number of webcams increases, a crowd with extremely high density can obtain less error by summing the images of multiple close-range webcams, but there are still some problems such as heavy occlusions and large-scale variation. To solve the above problems, this paper proposes a new type of multibranch neural network with a compensator, in which features are extracted through multibranch subnetworks of different scales. The weights between the branches are adjusted by the compensator, and the captured features are distinguished among different branches. To avoid learning nearly the same features in each branch and reducing the training deviation, the dataset is labeled with head scale, and the adaptive grading loss function is used to calculate the estimated loss of the subregions. The experimental results show that the accuracy of the network proposed in this paper is about 10% higher than that of the comparison network. |
| format | Article |
| id | doaj-art-9d811a562a114f548a215e75b9faea6d |
| institution | Kabale University |
| issn | 1099-0526 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-9d811a562a114f548a215e75b9faea6d2025-02-03T06:07:34ZengWileyComplexity1099-05262022-01-01202210.1155/2022/8213855An Improved Multibranch Convolutional Neural Network with a Compensator for Crowd CountingZhiyun Zheng0Zhenhao Sun1Guanglei Zhu2Zhenfei Wang3Junfeng Wang4School of Information EngineeringSchool of Information EngineeringSchool of Information EngineeringSchool of Information EngineeringSchool of Information EngineeringImage-based crowd counting has extremely important applications in public safety issues. Most of the previous studies focused on extremely dense crowds. However, as the number of webcams increases, a crowd with extremely high density can obtain less error by summing the images of multiple close-range webcams, but there are still some problems such as heavy occlusions and large-scale variation. To solve the above problems, this paper proposes a new type of multibranch neural network with a compensator, in which features are extracted through multibranch subnetworks of different scales. The weights between the branches are adjusted by the compensator, and the captured features are distinguished among different branches. To avoid learning nearly the same features in each branch and reducing the training deviation, the dataset is labeled with head scale, and the adaptive grading loss function is used to calculate the estimated loss of the subregions. The experimental results show that the accuracy of the network proposed in this paper is about 10% higher than that of the comparison network.http://dx.doi.org/10.1155/2022/8213855 |
| spellingShingle | Zhiyun Zheng Zhenhao Sun Guanglei Zhu Zhenfei Wang Junfeng Wang An Improved Multibranch Convolutional Neural Network with a Compensator for Crowd Counting Complexity |
| title | An Improved Multibranch Convolutional Neural Network with a Compensator for Crowd Counting |
| title_full | An Improved Multibranch Convolutional Neural Network with a Compensator for Crowd Counting |
| title_fullStr | An Improved Multibranch Convolutional Neural Network with a Compensator for Crowd Counting |
| title_full_unstemmed | An Improved Multibranch Convolutional Neural Network with a Compensator for Crowd Counting |
| title_short | An Improved Multibranch Convolutional Neural Network with a Compensator for Crowd Counting |
| title_sort | improved multibranch convolutional neural network with a compensator for crowd counting |
| url | http://dx.doi.org/10.1155/2022/8213855 |
| work_keys_str_mv | AT zhiyunzheng animprovedmultibranchconvolutionalneuralnetworkwithacompensatorforcrowdcounting AT zhenhaosun animprovedmultibranchconvolutionalneuralnetworkwithacompensatorforcrowdcounting AT guangleizhu animprovedmultibranchconvolutionalneuralnetworkwithacompensatorforcrowdcounting AT zhenfeiwang animprovedmultibranchconvolutionalneuralnetworkwithacompensatorforcrowdcounting AT junfengwang animprovedmultibranchconvolutionalneuralnetworkwithacompensatorforcrowdcounting AT zhiyunzheng improvedmultibranchconvolutionalneuralnetworkwithacompensatorforcrowdcounting AT zhenhaosun improvedmultibranchconvolutionalneuralnetworkwithacompensatorforcrowdcounting AT guangleizhu improvedmultibranchconvolutionalneuralnetworkwithacompensatorforcrowdcounting AT zhenfeiwang improvedmultibranchconvolutionalneuralnetworkwithacompensatorforcrowdcounting AT junfengwang improvedmultibranchconvolutionalneuralnetworkwithacompensatorforcrowdcounting |