Detail publikace

Pedestrian Detection from Low Resolution Public Cameras in the Wild

Originální název

Pedestrian Detection from Low Resolution Public Cameras in the Wild

Anglický název

Pedestrian Detection from Low Resolution Public Cameras in the Wild

Jazyk

en

Originální abstrakt

Since security situation in the world is changing, monitoring of protected areas using surveillance systems has been of increased significance in the recent years. Although the today object detection methods significantly improved accuracy, for real situations, where the video is stream basically of a low resolution and objects are often small and blurry, the methods are still struggling with precise detection. The key parts of any security system are 1) person detection and then also 2) person recognition, which must perform in real-time processing. This paper deals with pedestrian detection in so called wild - i.e. from sources with bad quality, blurry images or small objects for detection. We used Single Shot MultiBox Detector (SSD) which was trained on VOC 2007 dataset and using fine-tuning it achieved percentage increase 11.98% of accuracy for life scenarios. Thus, SSD confirmed its state-of-the-art position and ability to be simply adapted to specific cases of detection while keeping its high performance.

Anglický abstrakt

Since security situation in the world is changing, monitoring of protected areas using surveillance systems has been of increased significance in the recent years. Although the today object detection methods significantly improved accuracy, for real situations, where the video is stream basically of a low resolution and objects are often small and blurry, the methods are still struggling with precise detection. The key parts of any security system are 1) person detection and then also 2) person recognition, which must perform in real-time processing. This paper deals with pedestrian detection in so called wild - i.e. from sources with bad quality, blurry images or small objects for detection. We used Single Shot MultiBox Detector (SSD) which was trained on VOC 2007 dataset and using fine-tuning it achieved percentage increase 11.98% of accuracy for life scenarios. Thus, SSD confirmed its state-of-the-art position and ability to be simply adapted to specific cases of detection while keeping its high performance.

BibTex


@inproceedings{BUT146172,
  author="Martin {Rajnoha} and Lukáš {Povoda} and Jan {Mašek} and Radim {Burget} and Malay Kishore {Dutta}",
  title="Pedestrian Detection from Low Resolution Public Cameras in the Wild",
  annote="Since security situation in the world is changing, monitoring of protected areas using surveillance systems has been of increased significance in the recent years. Although the today object detection methods significantly improved accuracy, for real situations, where the video is stream basically of a low resolution and objects are often small and blurry, the methods are still struggling with precise detection. The key parts of any security system are 1) person detection and then also 2) person recognition, which must perform in real-time processing. This paper deals with pedestrian detection in so called wild - i.e. from sources with bad quality, blurry images or small objects for detection. We used Single Shot MultiBox Detector (SSD) which was trained on VOC 2007 dataset and using fine-tuning it achieved percentage increase 11.98% of accuracy for life scenarios. Thus, SSD confirmed its state-of-the-art position and ability to be simply adapted to specific cases of detection while keeping its high performance.",
  booktitle="2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)",
  chapter="146172",
  doi="10.1109/SPIN.2018.8474255",
  howpublished="electronic, physical medium",
  year="2018",
  month="february",
  pages="291--295",
  type="conference paper"
}