Single-frame image super-resolution through contourlet learning
EURASIP Journal on Applied Signal Processing
Object tracking in image sequences using point features
Pattern Recognition
Fast occluded object tracking by a robust appearance filter
IEEE Transactions on Pattern Analysis and Machine Intelligence
The contourlet transform: an efficient directional multiresolution image representation
IEEE Transactions on Image Processing
Hi-index | 0.00 |
In view of the detection difficulty of the Weak Aerial Target (WAT) due to no obvious characteristic. A new method for WAT based on Contourlet analysis and Mean Shift method is proposed to improve the tracking ability. Contourlet transform is used to detect the WAT, using the energy characteristic in the WAT of sub-band image to realize detection, and then extracts its centroid as the initial position of Mean Shift to track by iterative matching. Also proposed a search strategy incase the instantaneous missing of WAT. The calculations by experiment indicated that the method not only can detect the WAT precisely but also track automatically. In addition, the method has a better robustness to the target migration.