Crowd Anomaly Detection via Spatial Constraints and Meaningful Perturbation
Crowd anomaly detection is a practical and challenging problem to computer vision and VideoGIS due to abnormal events’ rare and diverse nature. Consequently, traditional methods rely on low-level reconstruction in a single image space, easily affected by unimportant pixels or sudden variations. In a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/11/3/205 |
| _version_ | 1797471068007432192 |
|---|---|
| author | Jiangfan Feng Dini Wang Li Zhang |
| author_facet | Jiangfan Feng Dini Wang Li Zhang |
| author_sort | Jiangfan Feng |
| collection | DOAJ |
| description | Crowd anomaly detection is a practical and challenging problem to computer vision and VideoGIS due to abnormal events’ rare and diverse nature. Consequently, traditional methods rely on low-level reconstruction in a single image space, easily affected by unimportant pixels or sudden variations. In addition, real-time detection for crowd anomaly detection is challenging, and localization of anomalies requires other supervision. We present a new detection approach to learn spatiotemporal features with the spatial constraints of a still dynamic image. First, a lightweight spatiotemporal autoencoder has been proposed, capable of real-time image reconstruction. Second, we offer a dynamic network to obtain a compact representation of video frames in motion, reducing false-positive anomaly alerts by spatial constraints. In addition, we adopt the perturbation visual interpretation method for anomaly visualization and localization to improve the credibility of the results. In experiments, our results provide competitive performance across various scenarios. Besides, our approach can process 52.9–63.4 fps in anomaly detection, making it practical for crowd anomaly detection in video surveillance. |
| first_indexed | 2024-03-09T19:44:21Z |
| format | Article |
| id | doaj.art-5aea0c0183aa4d07ba51cda090f289f9 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-09T19:44:21Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-5aea0c0183aa4d07ba51cda090f289f92023-11-24T01:28:49ZengMDPI AGISPRS International Journal of Geo-Information2220-99642022-03-0111320510.3390/ijgi11030205Crowd Anomaly Detection via Spatial Constraints and Meaningful PerturbationJiangfan Feng0Dini Wang1Li Zhang2College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCollege of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCollege of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCrowd anomaly detection is a practical and challenging problem to computer vision and VideoGIS due to abnormal events’ rare and diverse nature. Consequently, traditional methods rely on low-level reconstruction in a single image space, easily affected by unimportant pixels or sudden variations. In addition, real-time detection for crowd anomaly detection is challenging, and localization of anomalies requires other supervision. We present a new detection approach to learn spatiotemporal features with the spatial constraints of a still dynamic image. First, a lightweight spatiotemporal autoencoder has been proposed, capable of real-time image reconstruction. Second, we offer a dynamic network to obtain a compact representation of video frames in motion, reducing false-positive anomaly alerts by spatial constraints. In addition, we adopt the perturbation visual interpretation method for anomaly visualization and localization to improve the credibility of the results. In experiments, our results provide competitive performance across various scenarios. Besides, our approach can process 52.9–63.4 fps in anomaly detection, making it practical for crowd anomaly detection in video surveillance.https://www.mdpi.com/2220-9964/11/3/205VideoGISspatiotemporalgeospatial artificial intelligencespatial constraintsdeep learning |
| spellingShingle | Jiangfan Feng Dini Wang Li Zhang Crowd Anomaly Detection via Spatial Constraints and Meaningful Perturbation ISPRS International Journal of Geo-Information VideoGIS spatiotemporal geospatial artificial intelligence spatial constraints deep learning |
| title | Crowd Anomaly Detection via Spatial Constraints and Meaningful Perturbation |
| title_full | Crowd Anomaly Detection via Spatial Constraints and Meaningful Perturbation |
| title_fullStr | Crowd Anomaly Detection via Spatial Constraints and Meaningful Perturbation |
| title_full_unstemmed | Crowd Anomaly Detection via Spatial Constraints and Meaningful Perturbation |
| title_short | Crowd Anomaly Detection via Spatial Constraints and Meaningful Perturbation |
| title_sort | crowd anomaly detection via spatial constraints and meaningful perturbation |
| topic | VideoGIS spatiotemporal geospatial artificial intelligence spatial constraints deep learning |
| url | https://www.mdpi.com/2220-9964/11/3/205 |
| work_keys_str_mv | AT jiangfanfeng crowdanomalydetectionviaspatialconstraintsandmeaningfulperturbation AT diniwang crowdanomalydetectionviaspatialconstraintsandmeaningfulperturbation AT lizhang crowdanomalydetectionviaspatialconstraintsandmeaningfulperturbation |