Video object tracking with a sequential hierarchy of template deformations

Abstract

We have developed a new contour-based tracking algorithm that uses a sequence of template deformations to model and track generic video objects. We organize the deformations into a hierarchy: globally affine deformations, piecewise (locally) affine deformations, and arbitrary smooth deformations (snakes). This design enables the algorithm to track objects whose pose and shape change in time compared to the template. If the object is not a rigid body, we model the temporal evolution of its shape by updating the entire template after each video frame; otherwise, we only update the pose of the object. Experimental results demonstrate that our method is able to track a variety of video objects, including those undergoing rapid changes. We quantitatively compare our algorithm with its constituent pieces (e.g., the snake algorithm) and show that the complete algorithm can track objects with moving parts for a longer duration than partial versions of the hierarchy. It could be benefited from a higher level algorithm to dynamically adjust the parameters and template deformations to improve the segmentation accuracy further. The hierarchical nature of this algorithm provides a framework that offers a modular approach for the design and enhancement of future object-tracking algorithms.

Region tracking for non-rigid video objects in a non-parametric MAP framework

“…(19) indicate a force that prevents severe boundary change from the previously tracked region R nÀ1 . Once a pixel x evolves outwardly across the region boundary of R nÀ1 , we will have pðR n ðxÞ ¼ 1jR nÀ1 ÞopðR n ðxÞ ¼ 0jR nÀ1 Þ.…”

“…Several techniques [20,19] assume that a video object follows a uniform motion or has a parametric shape and thus need only a limited number of parameters to track the object. However, for video object composed of multiple regions with different moving behaviors, their inconsistent motions and the resulting self-occlusion become a tough issue in region tracking.…”

“…Contour-based methods [4][5][6][7][8]14,15,17,19] use a contour (or boundary) to encompass a tracking region and keep fitting the contour to certain visual features detected from each video frame. The method proposed in [14,15] updates the contour by partially matching the edge points of a tracking region across contiguous frames.…”

Recent Advances in Region-of-interest Video Coding

“…According to these methods, the objects (such as faces) are detected by using predetermined templates (Schoepflin et al, 2001). As mentioned above, phe pixel-domain approach is, generally, more accurate than the compressed-domain approach, but has relatively high computational complexity and requires further additional computational resources for decoding compressed video streams.…”

Evaluation of tracking reliability metrics based on information theory and normalized correlation

“…Most of the tracking techniques use subjective evaluation methods, while some of them use quantitative evaluations based on ground truth data [1]. The implementation of reliability measures not resorting to ground truth data is particularly important.…”