Research on subway pedestrian detection algorithms based on SSD model
Accurate target recognition and location is one of the key technologies in the field of smart city application. In order to solve the problem of large pedestriain flow impact in crowded metro stations, a method of in‐depth learning detection based on SSD (single shot multibox detector) is proposed....
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-11-01
|
| Series: | IET Intelligent Transport Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-its.2019.0806 |
| _version_ | 1817996213073477632 |
|---|---|
| author | Jie Yang Wen Yu He Tian Lu Zhang Chun Lei Zhang Lu Zeng Bing Fei Nan |
| author_facet | Jie Yang Wen Yu He Tian Lu Zhang Chun Lei Zhang Lu Zeng Bing Fei Nan |
| author_sort | Jie Yang |
| collection | DOAJ |
| description | Accurate target recognition and location is one of the key technologies in the field of smart city application. In order to solve the problem of large pedestriain flow impact in crowded metro stations, a method of in‐depth learning detection based on SSD (single shot multibox detector) is proposed. The algorithm extracts the feature information of the input image, then returns the boundary box of the location on the feature map and classifies the object categories. Using the method of local feature extraction, the features of different positions, different aspect ratios and sizes are obtained, and VGG16 is used as the base network to optimise and improve the network structure. The results of simulation experiments on VOC2007 and data_sub show that the maximum value of mAP is 77% and the highest accuracy is 96.31%. Compared with other mainstream deep learning target detection methods, SSD has higher accuracy, better real‐time and robustness. It can solve the problem of different pedestrian target sizes and better realise pedestrians in subway station environment. Detection provides decision‐making basis for flow statistics. |
| first_indexed | 2024-04-14T02:18:50Z |
| format | Article |
| id | doaj.art-a5a67b4946bf42fc9f3d35e449715a43 |
| institution | Directory Open Access Journal |
| issn | 1751-956X 1751-9578 |
| language | English |
| last_indexed | 2024-04-14T02:18:50Z |
| publishDate | 2020-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Intelligent Transport Systems |
| spelling | doaj.art-a5a67b4946bf42fc9f3d35e449715a432022-12-22T02:18:06ZengWileyIET Intelligent Transport Systems1751-956X1751-95782020-11-0114111491149610.1049/iet-its.2019.0806Research on subway pedestrian detection algorithms based on SSD modelJie Yang0Wen Yu He1Tian Lu Zhang2Chun Lei Zhang3Lu Zeng4Bing Fei Nan5Department of Electrical Engineering and AutomationJiangxi University of Science and TechnologyJiangxi341000People's Republic of ChinaDepartment of Electrical Engineering and AutomationJiangxi University of Science and TechnologyJiangxi341000People's Republic of ChinaDepartment of Electrical Engineering and AutomationJiangxi University of Science and TechnologyJiangxi341000People's Republic of ChinaDepartment of Electrical Engineering and AutomationJiangxi University of Science and TechnologyJiangxi341000People's Republic of ChinaDepartment of Electrical Engineering and AutomationJiangxi University of Science and TechnologyJiangxi341000People's Republic of ChinaDepartment of Electrical Engineering and AutomationJiangxi University of Science and TechnologyJiangxi341000People's Republic of ChinaAccurate target recognition and location is one of the key technologies in the field of smart city application. In order to solve the problem of large pedestriain flow impact in crowded metro stations, a method of in‐depth learning detection based on SSD (single shot multibox detector) is proposed. The algorithm extracts the feature information of the input image, then returns the boundary box of the location on the feature map and classifies the object categories. Using the method of local feature extraction, the features of different positions, different aspect ratios and sizes are obtained, and VGG16 is used as the base network to optimise and improve the network structure. The results of simulation experiments on VOC2007 and data_sub show that the maximum value of mAP is 77% and the highest accuracy is 96.31%. Compared with other mainstream deep learning target detection methods, SSD has higher accuracy, better real‐time and robustness. It can solve the problem of different pedestrian target sizes and better realise pedestrians in subway station environment. Detection provides decision‐making basis for flow statistics.https://doi.org/10.1049/iet-its.2019.0806subway pedestrian detection algorithmsSSD modeltarget recognitionsmart city applicationpedestriain flow impactcrowded metro stations |
| spellingShingle | Jie Yang Wen Yu He Tian Lu Zhang Chun Lei Zhang Lu Zeng Bing Fei Nan Research on subway pedestrian detection algorithms based on SSD model IET Intelligent Transport Systems subway pedestrian detection algorithms SSD model target recognition smart city application pedestriain flow impact crowded metro stations |
| title | Research on subway pedestrian detection algorithms based on SSD model |
| title_full | Research on subway pedestrian detection algorithms based on SSD model |
| title_fullStr | Research on subway pedestrian detection algorithms based on SSD model |
| title_full_unstemmed | Research on subway pedestrian detection algorithms based on SSD model |
| title_short | Research on subway pedestrian detection algorithms based on SSD model |
| title_sort | research on subway pedestrian detection algorithms based on ssd model |
| topic | subway pedestrian detection algorithms SSD model target recognition smart city application pedestriain flow impact crowded metro stations |
| url | https://doi.org/10.1049/iet-its.2019.0806 |
| work_keys_str_mv | AT jieyang researchonsubwaypedestriandetectionalgorithmsbasedonssdmodel AT wenyuhe researchonsubwaypedestriandetectionalgorithmsbasedonssdmodel AT tianluzhang researchonsubwaypedestriandetectionalgorithmsbasedonssdmodel AT chunleizhang researchonsubwaypedestriandetectionalgorithmsbasedonssdmodel AT luzeng researchonsubwaypedestriandetectionalgorithmsbasedonssdmodel AT bingfeinan researchonsubwaypedestriandetectionalgorithmsbasedonssdmodel |