Pedestrian Motion Path Detection Method Based on Deep Learning and Foreground Detection
For the surveillance video images captured by monocular camera, this paper proposes a method combining foreground detection and deep learning to detect moving pedestrians, making full use of the invariable background of video image. Firstly, the motion region is extracted by the method of interframe...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/5596135 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832560130228486144 |
|---|---|
| author | Meiman Li Wenfu Xie |
| author_facet | Meiman Li Wenfu Xie |
| author_sort | Meiman Li |
| collection | DOAJ |
| description | For the surveillance video images captured by monocular camera, this paper proposes a method combining foreground detection and deep learning to detect moving pedestrians, making full use of the invariable background of video image. Firstly, the motion region is extracted by the method of interframe difference and background difference. Then, the normalized motion region extracts the feature vectors based on the improved YOLOv3 tiny network. Finally, the trained linear support vector machine is used for pedestrian detection, and the performance of the fusion detection algorithm on caviar dataset is given, which proves the effectiveness of the proposed fusion detection algorithm. Experimental results show that the proposed method not only improves the practical application of pedestrian rerecognition but also reduces the detection range, computational complexity, and false detection rate compared with sliding window method. |
| format | Article |
| id | doaj-art-a4ae38d544e742efa0227ced5e2e4a30 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-a4ae38d544e742efa0227ced5e2e4a302025-02-03T01:28:23ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/55961355596135Pedestrian Motion Path Detection Method Based on Deep Learning and Foreground DetectionMeiman Li0Wenfu Xie1School of Artificial Intelligence, The Open University of Guangdong, Guangzhou 510091, Guangdong, ChinaSchool of Artificial Intelligence, The Open University of Guangdong, Guangzhou 510091, Guangdong, ChinaFor the surveillance video images captured by monocular camera, this paper proposes a method combining foreground detection and deep learning to detect moving pedestrians, making full use of the invariable background of video image. Firstly, the motion region is extracted by the method of interframe difference and background difference. Then, the normalized motion region extracts the feature vectors based on the improved YOLOv3 tiny network. Finally, the trained linear support vector machine is used for pedestrian detection, and the performance of the fusion detection algorithm on caviar dataset is given, which proves the effectiveness of the proposed fusion detection algorithm. Experimental results show that the proposed method not only improves the practical application of pedestrian rerecognition but also reduces the detection range, computational complexity, and false detection rate compared with sliding window method.http://dx.doi.org/10.1155/2021/5596135 |
| spellingShingle | Meiman Li Wenfu Xie Pedestrian Motion Path Detection Method Based on Deep Learning and Foreground Detection Complexity |
| title | Pedestrian Motion Path Detection Method Based on Deep Learning and Foreground Detection |
| title_full | Pedestrian Motion Path Detection Method Based on Deep Learning and Foreground Detection |
| title_fullStr | Pedestrian Motion Path Detection Method Based on Deep Learning and Foreground Detection |
| title_full_unstemmed | Pedestrian Motion Path Detection Method Based on Deep Learning and Foreground Detection |
| title_short | Pedestrian Motion Path Detection Method Based on Deep Learning and Foreground Detection |
| title_sort | pedestrian motion path detection method based on deep learning and foreground detection |
| url | http://dx.doi.org/10.1155/2021/5596135 |
| work_keys_str_mv | AT meimanli pedestrianmotionpathdetectionmethodbasedondeeplearningandforegrounddetection AT wenfuxie pedestrianmotionpathdetectionmethodbasedondeeplearningandforegrounddetection |