Improvement in robustness of the statistically independent region snake-based segmentation method of target-shape tracking

Abstract

We propose a technique to increase the robustness of a snake-based segmentation method originally introduced to track the shape of a target with random white Gaussian intensity upon a random white Gaussian background. Because these statistical conditions are not always fulfilled with optronic images, we describe two improvements that increase the field of application of this approach. We first show that regularized whitening preprocessing allows one to apply the original method successfully for a target with a correlated texture upon a correlated background. We then introduce a simple multiscale approach that increases the robustness of the segmentation against the initialization of the snake (i.e., the initial shape used for the segmentation). These results provide a robust and practical method for determination of the reference image for correlation techniques.

Two approaches, coherent and incoherent, for the optical implementation of active contours

“…This PDF characterizes images that can be segmented according to the variances of the regions. To apply it on any image, a whitening preprocessing has been defined by Chesnaud et al 15 The corresponding criterion, J, operates on the variance and surface of both the target and background regions. The criterion to minimize is then:…”

Snake-based target segmentation implementable on optical correlators

“…We then introduce a simple but efficient regularized whitening preprocessing which forces the statistics of the target and of the background to become white and Gaussian. We have shown in [4] that this approach enlarges the field of application of the SIRS technique. It is interesting to note that the same whitening preprocessing can be used for the location task [9] .…”

“…This preprocessing which is described in [4] consists of whitening the input image. In that case a preprocessed image has to be correlated with the binary mask w in order to segment the target in the image.…”

Tracking of multiple objects in unknown background using Bayesian estimation in 3D space

“…There have been numerous approaches to address detection, recognition, and tracking problems using 3D integral imaging [1][2][3][4][5][6][7] or multiperspective imaging [8], or other approaches. One possible solution is contour-based object tracking [9][10][11][12][13]. Detection of the object is required for these methods, and then tracking is conducted by moving the previous contour toward the current boundaries.…”

“…In light of the fact that the active contour method [13] evaluates the changes of local intensities along the boundary; it is limited to small displacements. On the other hand, region-based methods [10,11] exploit the information of both the object and the background for more robust and flexible performance.…”