Abnormal Event Detection via Feature Expectation Subgraph Calibrating Classification in Video Surveillance Scenes
At present, the existing abnormal event detection models based on deep learning mainly focus on data represented by a vectorial form, which pay little attention to the impact of the internal structure characteristics of feature vector. In addition, a single classifier is difficult to ensure the accu...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9099570/ |
| _version_ | 1818921137498750976 |
|---|---|
| author | Ou Ye Jun Deng Zhenhua Yu Tao Liu Lihong Dong |
| author_facet | Ou Ye Jun Deng Zhenhua Yu Tao Liu Lihong Dong |
| author_sort | Ou Ye |
| collection | DOAJ |
| description | At present, the existing abnormal event detection models based on deep learning mainly focus on data represented by a vectorial form, which pay little attention to the impact of the internal structure characteristics of feature vector. In addition, a single classifier is difficult to ensure the accuracy of classification. In order to address the above issues, we propose an abnormal event detection hybrid modulation method via feature expectation subgraph calibrating classification in video surveillance scenes in this paper. Our main contribution is to calibrate the classification of a single classifier by constructing feature expectation subgraphs. First, we employ convolutional neural network and long short-term memory models to extract the spatiotemporal features of video frame, and then construct the feature expectation subgraph for each key frame of every video, which could be used to capture the internal sequential and topological relational characteristics of structured feature vector. Second, we project expectation subgraphs on the sparse vector to combine with a support vector classifier to calibrate the results of a linear support vector classifier. Finally, the experiments on a common dataset named UCSDped1 and a coal mining video dataset in comparison with some existing works demonstrate that the performance of the proposed method is better than several the state-of-the-art approaches. |
| first_indexed | 2024-12-20T01:32:52Z |
| format | Article |
| id | doaj.art-7d93fd12bb774075a54c318d836d7aa5 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T01:32:52Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7d93fd12bb774075a54c318d836d7aa52022-12-21T19:58:04ZengIEEEIEEE Access2169-35362020-01-018975649757510.1109/ACCESS.2020.29973579099570Abnormal Event Detection via Feature Expectation Subgraph Calibrating Classification in Video Surveillance ScenesOu Ye0https://orcid.org/0000-0002-4134-9191Jun Deng1Zhenhua Yu2https://orcid.org/0000-0002-7204-3654Tao Liu3https://orcid.org/0000-0003-3897-9085Lihong Dong4College of Computer Science & Technology, Xi’an University of Science and Technology, Xi’an, ChinaCollege of Safety Science and Engineering, Xi’an University of Science and Technology, Xi’an, ChinaCollege of Computer Science & Technology, Xi’an University of Science and Technology, Xi’an, ChinaCollege of Computer Science & Technology, Xi’an University of Science and Technology, Xi’an, ChinaCollege of Computer Science & Technology, Xi’an University of Science and Technology, Xi’an, ChinaAt present, the existing abnormal event detection models based on deep learning mainly focus on data represented by a vectorial form, which pay little attention to the impact of the internal structure characteristics of feature vector. In addition, a single classifier is difficult to ensure the accuracy of classification. In order to address the above issues, we propose an abnormal event detection hybrid modulation method via feature expectation subgraph calibrating classification in video surveillance scenes in this paper. Our main contribution is to calibrate the classification of a single classifier by constructing feature expectation subgraphs. First, we employ convolutional neural network and long short-term memory models to extract the spatiotemporal features of video frame, and then construct the feature expectation subgraph for each key frame of every video, which could be used to capture the internal sequential and topological relational characteristics of structured feature vector. Second, we project expectation subgraphs on the sparse vector to combine with a support vector classifier to calibrate the results of a linear support vector classifier. Finally, the experiments on a common dataset named UCSDped1 and a coal mining video dataset in comparison with some existing works demonstrate that the performance of the proposed method is better than several the state-of-the-art approaches.https://ieeexplore.ieee.org/document/9099570/Abnormal event detectionfeature expectation subgraphcalibrating classificationsequential and topological relational characteristics |
| spellingShingle | Ou Ye Jun Deng Zhenhua Yu Tao Liu Lihong Dong Abnormal Event Detection via Feature Expectation Subgraph Calibrating Classification in Video Surveillance Scenes IEEE Access Abnormal event detection feature expectation subgraph calibrating classification sequential and topological relational characteristics |
| title | Abnormal Event Detection via Feature Expectation Subgraph Calibrating Classification in Video Surveillance Scenes |
| title_full | Abnormal Event Detection via Feature Expectation Subgraph Calibrating Classification in Video Surveillance Scenes |
| title_fullStr | Abnormal Event Detection via Feature Expectation Subgraph Calibrating Classification in Video Surveillance Scenes |
| title_full_unstemmed | Abnormal Event Detection via Feature Expectation Subgraph Calibrating Classification in Video Surveillance Scenes |
| title_short | Abnormal Event Detection via Feature Expectation Subgraph Calibrating Classification in Video Surveillance Scenes |
| title_sort | abnormal event detection via feature expectation subgraph calibrating classification in video surveillance scenes |
| topic | Abnormal event detection feature expectation subgraph calibrating classification sequential and topological relational characteristics |
| url | https://ieeexplore.ieee.org/document/9099570/ |
| work_keys_str_mv | AT ouye abnormaleventdetectionviafeatureexpectationsubgraphcalibratingclassificationinvideosurveillancescenes AT jundeng abnormaleventdetectionviafeatureexpectationsubgraphcalibratingclassificationinvideosurveillancescenes AT zhenhuayu abnormaleventdetectionviafeatureexpectationsubgraphcalibratingclassificationinvideosurveillancescenes AT taoliu abnormaleventdetectionviafeatureexpectationsubgraphcalibratingclassificationinvideosurveillancescenes AT lihongdong abnormaleventdetectionviafeatureexpectationsubgraphcalibratingclassificationinvideosurveillancescenes |