Redesigned Skip-Network for Crowd Counting with Dilated Convolution and Backward Connection
Crowd counting is a challenging task dealing with the variation of an object scale and a crowd density. Existing works have emphasized on skip connections by integrating shallower layers with deeper layers, where each layer extracts features in a different object scale and crowd density. However, on...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/6/5/28 |
| _version_ | 1797568878714290176 |
|---|---|
| author | Sorn Sooksatra Toshiaki Kondo Pished Bunnun Atsuo Yoshitaka |
| author_facet | Sorn Sooksatra Toshiaki Kondo Pished Bunnun Atsuo Yoshitaka |
| author_sort | Sorn Sooksatra |
| collection | DOAJ |
| description | Crowd counting is a challenging task dealing with the variation of an object scale and a crowd density. Existing works have emphasized on skip connections by integrating shallower layers with deeper layers, where each layer extracts features in a different object scale and crowd density. However, only high-level features are emphasized while ignoring low-level features. This paper proposes an estimation network by passing high-level features to shallow layers and emphasizing its low-level feature. Since an estimation network is a hierarchical network, a high-level feature is also emphasized by an improved low-level feature. Our estimation network consists of two identical networks for extracting a high-level feature and estimating the final result. To preserve semantic information, dilated convolution is employed without resizing the feature map. Our method was tested in three datasets for counting humans and vehicles in a crowd image. The counting performance is evaluated by mean absolute error and root mean squared error indicating the accuracy and robustness of an estimation network, respectively. The experimental result shows that our network outperforms other related works in a high crowd density and is effective for reducing over-counting error in the overall case. |
| first_indexed | 2024-03-10T20:03:05Z |
| format | Article |
| id | doaj.art-0a1dd49f203f444b908676474169d5fe |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-10T20:03:05Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-0a1dd49f203f444b908676474169d5fe2023-11-19T23:22:38ZengMDPI AGJournal of Imaging2313-433X2020-05-01652810.3390/jimaging6050028Redesigned Skip-Network for Crowd Counting with Dilated Convolution and Backward ConnectionSorn Sooksatra0Toshiaki Kondo1Pished Bunnun2Atsuo Yoshitaka3School of Information and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, ThailandSchool of Information and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, ThailandNational Electronic and Computer Technology Center, National Science and Technology Development Agency, Pathum Thani 12120, ThailandSchool of Information Science, Japan Advanced Institute of Science and Technology, Ishikawa 923-1211, JapanCrowd counting is a challenging task dealing with the variation of an object scale and a crowd density. Existing works have emphasized on skip connections by integrating shallower layers with deeper layers, where each layer extracts features in a different object scale and crowd density. However, only high-level features are emphasized while ignoring low-level features. This paper proposes an estimation network by passing high-level features to shallow layers and emphasizing its low-level feature. Since an estimation network is a hierarchical network, a high-level feature is also emphasized by an improved low-level feature. Our estimation network consists of two identical networks for extracting a high-level feature and estimating the final result. To preserve semantic information, dilated convolution is employed without resizing the feature map. Our method was tested in three datasets for counting humans and vehicles in a crowd image. The counting performance is evaluated by mean absolute error and root mean squared error indicating the accuracy and robustness of an estimation network, respectively. The experimental result shows that our network outperforms other related works in a high crowd density and is effective for reducing over-counting error in the overall case.https://www.mdpi.com/2313-433X/6/5/28surveillance systemcrowd countingregression-based approachskip connectiondilated convolution |
| spellingShingle | Sorn Sooksatra Toshiaki Kondo Pished Bunnun Atsuo Yoshitaka Redesigned Skip-Network for Crowd Counting with Dilated Convolution and Backward Connection Journal of Imaging surveillance system crowd counting regression-based approach skip connection dilated convolution |
| title | Redesigned Skip-Network for Crowd Counting with Dilated Convolution and Backward Connection |
| title_full | Redesigned Skip-Network for Crowd Counting with Dilated Convolution and Backward Connection |
| title_fullStr | Redesigned Skip-Network for Crowd Counting with Dilated Convolution and Backward Connection |
| title_full_unstemmed | Redesigned Skip-Network for Crowd Counting with Dilated Convolution and Backward Connection |
| title_short | Redesigned Skip-Network for Crowd Counting with Dilated Convolution and Backward Connection |
| title_sort | redesigned skip network for crowd counting with dilated convolution and backward connection |
| topic | surveillance system crowd counting regression-based approach skip connection dilated convolution |
| url | https://www.mdpi.com/2313-433X/6/5/28 |
| work_keys_str_mv | AT sornsooksatra redesignedskipnetworkforcrowdcountingwithdilatedconvolutionandbackwardconnection AT toshiakikondo redesignedskipnetworkforcrowdcountingwithdilatedconvolutionandbackwardconnection AT pishedbunnun redesignedskipnetworkforcrowdcountingwithdilatedconvolutionandbackwardconnection AT atsuoyoshitaka redesignedskipnetworkforcrowdcountingwithdilatedconvolutionandbackwardconnection |