Publication detail

Pedestrian Detection from Low Resolution Public Cameras in the Wild

RAJNOHA, M. POVODA, L. MAŠEK, J. BURGET, R. DUTTA, M.

Original Title

Pedestrian Detection from Low Resolution Public Cameras in the Wild

English Title

Pedestrian Detection from Low Resolution Public Cameras in the Wild

Type

conference paper

Language

en

Original Abstract

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.

English abstract

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.

Keywords

surveillance; detection; recognition; classification; SSD; CNN; pedestrian; people; person

Released

22.02.2018

Location

New Delhi, India

ISBN

978-1-5386-3045-7

Book

2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)

Pages from

291

Pages to

295

Pages count

5

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"
}