AVS-Net: Automatic Visual Surveillance Using Relation Network

Sein Jang, Young-Ho Park, Aziz Nasridinov

AAAI 2019 pp. 9947-9948

doi:10.1609/AAAI.V33I01.33019947 /aaai/2019/jang2019aaai-avs/

Abstract

Visual surveillance through closed circuit television (CCTV) can help to prevent crime. In this paper, we propose an automatic visual surveillance network (AVS-Net), which simultaneously performs image processing and object detection to determine the dangers of situations captured by CCTV. In addition, we add a relation module to infer the relationships of the objects in the images. Experimental results show that the relation module greatly improves classification accuracy, even if there is not enough information.

PDF AAAI Semantic Scholar

Cite

Text

Jang et al. "AVS-Net: Automatic Visual Surveillance Using Relation Network." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33019947

Markdown

[Jang et al. "AVS-Net: Automatic Visual Surveillance Using Relation Network." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/jang2019aaai-avs/) doi:10.1609/AAAI.V33I01.33019947

BibTeX

@inproceedings{jang2019aaai-avs,
  title     = {{AVS-Net: Automatic Visual Surveillance Using Relation Network}},
  author    = {Jang, Sein and Park, Young-Ho and Nasridinov, Aziz},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {9947-9948},
  doi       = {10.1609/AAAI.V33I01.33019947},
  url       = {https://mlanthology.org/aaai/2019/jang2019aaai-avs/}
}