한국방송∙미디어공학회:학술대회논문집 (Proceedings of the Korean Society of Broadcast Engineers Conference)
- 한국방송∙미디어공학회 2019년도 추계학술대회
- /
- Pages.169-171
- /
- 2019
A person detection in HEVC bitstream domain based on bits density feature and YOLOv3 framework
초록
This paper proposes an algorithm to detect persons in bitstream domain by skipping a reconstruction picture process in HEVC decoding. A new 3-channel feature extraction map is introduced in this paper by modelling the relationship between bits per CU density, average PU shape in CU, and total transform coefficients in CU from syntax elements. A state-of-the-art of YOLOv3 detection algorithm is used to detect and localize person on extracted feature maps. Based on the experimental results, the proposed person detection framework can achieve mAP of 0.68 and be able to find persons on feature maps. In addition, the proposed person detection can save decoding time about 60% by removing reconstruction picture process.
키워드