Abstract | ||
---|---|---|
This paper presents a fast and effective method based on features to obtain real-time video stabilization for vehicle video recorder system. The corresponding feature points are first obtained from two consecutive frames and then optical flows are calculated based on these points. Next, the obtained optical flows are mapped to polar coordinates to obtain clusters and remove incorrect optical flows. These obtained clusters are used to evaluate the global motion and rotation angle. Finally, the obtained global motion and rotation angle are smoothed and then compensated to obtain the stabilized video. Experimental results show that the proposed method has good performance for video stabilization. |
Year | DOI | Venue |
---|---|---|
2018 | https://doi.org/10.1007/s11042-017-4369-7 | Multimedia Tools Appl. |
Keywords | Field | DocType |
Video stabilization,Moving camera,Optical flow,Feature point | Computer vision,Block-matching algorithm,Computer graphics (images),Effective method,Computer science,Image stabilization,Videocassette recorder,Motion compensation,Polar coordinate system,Artificial intelligence,Feature based,Optical flow | Journal |
Volume | Issue | ISSN |
77 | 5 | 1380-7501 |
Citations | PageRank | References |
0 | 0.34 | 24 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wu-Chih Hu | 1 | 244 | 27.01 |
Chen Chao-Ho | 2 | 34 | 10.14 |
Yi-Jen Su | 3 | 1 | 0.70 |
Tzu-Hsing Chang | 4 | 0 | 0.34 |