Readings in computer vision: issues, problems, principles, and paradigms
The robust estimation of multiple motions: parametric and piecewise-smooth flow fields
Computer Vision and Image Understanding
Robust Parameter Estimation in Computer Vision
SIAM Review
Hierarchical Model-Based Motion Estimation
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Lucas-Kanade 20 Years On: A Unifying Framework
International Journal of Computer Vision
Hi-index | 0.00 |
The prevailing image mosaicking algorithms are based on a collection of full images that are captured by camera sensors. However, these approaches cannot be directly applied to the emerging wireless image sensor networks (WISNs). Wireless channel insert noticeable delay before an entire image can be transmitted to the sink node in a WISN. In this paper, we propose a Progressive Image Mosaicking Algorithm (PIMA) based on the multi-scans feature of Progressive JPEG. PIMA's most distinguishing feature is that it accomplishes image mosaicking by using portions of images of a proper quality level to deliver an approximate view of the scene in a short time during the reception of the image data stream. Thereafter, it amends the image registration on the other two finer levels to gradually enhance the display quality. A variation of Sum of Absolute Difference (SAD) is used to improve the accuracy of image registration. Experimental results show that PIMA successfully decreases the delay for displaying the first scene, and preserves an equivalent performance to the existing patch-based image mosaicking algorithms.