Format

Send to

Choose Destination
Sensors (Basel). 2017 Feb 10;17(2). pii: E337. doi: 10.3390/s17020337.

Robust Video Stabilization Using Particle Keypoint Update and l₁-Optimized Camera Path.

Author information

1
Department of Image, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 06974, Korea. semi2530@gmail.com.
2
Department of Image, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 06974, Korea. inhyey@gmail.com.
3
ADAS Camera Team, LG Electronics, 322 Gyeongmyeong-daero, Seo-gu, Incheon 22744, Korea. inhyey@gmail.com.
4
Department of Image, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 06974, Korea. jinbeum23@gmail.com.
5
Future Technology R&D, SK Telecom, Sunae-dong, Bundang-gu, Seongnam 13595, Korea. yangs@sk.com.
6
Future Technology R&D, SK Telecom, Sunae-dong, Bundang-gu, Seongnam 13595, Korea. joyful.kim@sk.com.
7
Department of Image, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 06974, Korea. paikj@cau.ac.kr.

Abstract

Acquisition of stabilized video is an important issue for various type of digital cameras. This paper presents an adaptive camera path estimation method using robust feature detection to remove shaky artifacts in a video. The proposed algorithm consists of three steps: (i) robust feature detection using particle keypoints between adjacent frames; (ii) camera path estimation and smoothing; and (iii) rendering to reconstruct a stabilized video. As a result, the proposed algorithm can estimate the optimal homography by redefining important feature points in the flat region using particle keypoints. In addition, stabilized frames with less holes can be generated from the optimal, adaptive camera path that minimizes a temporal total variation (TV). The proposed video stabilization method is suitable for enhancing the visual quality for various portable cameras and can be applied to robot vision, driving assistant systems, and visual surveillance systems.

KEYWORDS:

camera motion estimation; feature extraction; video enhancement; video stabilization

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center