Anomaly Detection Based on Local Nearest Neighbor Distance Descriptor in Crowded Scenes
We propose a novel local nearest neighbor distance (LNND) descriptor for anomaly detection in crowded scenes. Comparing with the commonly used low-level feature descriptors in previous works, LNND descriptor has two major advantages. First, LNND descriptor efficiently incorporates spatial and tempor...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-01-01
|
| Series: | The Scientific World Journal |
| Online Access: | http://dx.doi.org/10.1155/2014/632575 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832559832961384448 |
|---|---|
| author | Xing Hu Shiqiang Hu Xiaoyu Zhang Huanlong Zhang Lingkun Luo |
| author_facet | Xing Hu Shiqiang Hu Xiaoyu Zhang Huanlong Zhang Lingkun Luo |
| author_sort | Xing Hu |
| collection | DOAJ |
| description | We propose a novel local nearest neighbor distance (LNND) descriptor for anomaly detection in crowded scenes. Comparing with the commonly used low-level feature descriptors in previous works, LNND descriptor has two major advantages. First, LNND descriptor efficiently incorporates spatial and temporal contextual information around the video event that is important for detecting anomalous interaction among multiple events, while most existing feature descriptors only contain the information of single event. Second, LNND descriptor is a compact representation and its dimensionality is typically much lower than the low-level feature descriptor. Therefore, not only the computation time and storage requirement can be accordingly saved by using LNND descriptor for the anomaly detection method with offline training fashion, but also the negative aspects caused by using high-dimensional feature descriptor can be avoided. We validate the effectiveness of LNND descriptor by conducting extensive experiments on different benchmark datasets. Experimental results show the promising performance of LNND-based method against the state-of-the-art methods. It is worthwhile to notice that the LNND-based approach requires less intermediate processing steps without any subsequent processing such as smoothing but achieves comparable event better performance. |
| format | Article |
| id | doaj-art-5c2931efc1ab4f3495043f648db4fd4a |
| institution | Kabale University |
| issn | 2356-6140 1537-744X |
| language | English |
| publishDate | 2014-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | The Scientific World Journal |
| spelling | doaj-art-5c2931efc1ab4f3495043f648db4fd4a2025-02-03T01:29:05ZengWileyThe Scientific World Journal2356-61401537-744X2014-01-01201410.1155/2014/632575632575Anomaly Detection Based on Local Nearest Neighbor Distance Descriptor in Crowded ScenesXing Hu0Shiqiang Hu1Xiaoyu Zhang2Huanlong Zhang3Lingkun Luo4School of Aeronautics and Astronautics, Shanghai Jiao Tong University, Dongchuan Road, No. 800, Shanghai, ChinaSchool of Aeronautics and Astronautics, Shanghai Jiao Tong University, Dongchuan Road, No. 800, Shanghai, ChinaSchool of Aeronautics and Astronautics, Shanghai Jiao Tong University, Dongchuan Road, No. 800, Shanghai, ChinaSchool of Aeronautics and Astronautics, Shanghai Jiao Tong University, Dongchuan Road, No. 800, Shanghai, ChinaSchool of Aeronautics and Astronautics, Shanghai Jiao Tong University, Dongchuan Road, No. 800, Shanghai, ChinaWe propose a novel local nearest neighbor distance (LNND) descriptor for anomaly detection in crowded scenes. Comparing with the commonly used low-level feature descriptors in previous works, LNND descriptor has two major advantages. First, LNND descriptor efficiently incorporates spatial and temporal contextual information around the video event that is important for detecting anomalous interaction among multiple events, while most existing feature descriptors only contain the information of single event. Second, LNND descriptor is a compact representation and its dimensionality is typically much lower than the low-level feature descriptor. Therefore, not only the computation time and storage requirement can be accordingly saved by using LNND descriptor for the anomaly detection method with offline training fashion, but also the negative aspects caused by using high-dimensional feature descriptor can be avoided. We validate the effectiveness of LNND descriptor by conducting extensive experiments on different benchmark datasets. Experimental results show the promising performance of LNND-based method against the state-of-the-art methods. It is worthwhile to notice that the LNND-based approach requires less intermediate processing steps without any subsequent processing such as smoothing but achieves comparable event better performance.http://dx.doi.org/10.1155/2014/632575 |
| spellingShingle | Xing Hu Shiqiang Hu Xiaoyu Zhang Huanlong Zhang Lingkun Luo Anomaly Detection Based on Local Nearest Neighbor Distance Descriptor in Crowded Scenes The Scientific World Journal |
| title | Anomaly Detection Based on Local Nearest Neighbor Distance Descriptor in Crowded Scenes |
| title_full | Anomaly Detection Based on Local Nearest Neighbor Distance Descriptor in Crowded Scenes |
| title_fullStr | Anomaly Detection Based on Local Nearest Neighbor Distance Descriptor in Crowded Scenes |
| title_full_unstemmed | Anomaly Detection Based on Local Nearest Neighbor Distance Descriptor in Crowded Scenes |
| title_short | Anomaly Detection Based on Local Nearest Neighbor Distance Descriptor in Crowded Scenes |
| title_sort | anomaly detection based on local nearest neighbor distance descriptor in crowded scenes |
| url | http://dx.doi.org/10.1155/2014/632575 |
| work_keys_str_mv | AT xinghu anomalydetectionbasedonlocalnearestneighbordistancedescriptorincrowdedscenes AT shiqianghu anomalydetectionbasedonlocalnearestneighbordistancedescriptorincrowdedscenes AT xiaoyuzhang anomalydetectionbasedonlocalnearestneighbordistancedescriptorincrowdedscenes AT huanlongzhang anomalydetectionbasedonlocalnearestneighbordistancedescriptorincrowdedscenes AT lingkunluo anomalydetectionbasedonlocalnearestneighbordistancedescriptorincrowdedscenes |