Depth edge detection using edge-preserving filter and morphological operations

Canny edge detection principle and morphological operations have been used for depth edge detection. Several image smoothing filters were proposed for the enhancement of the detection task. However, an image smoothing filter can blur the edges of an image. In this paper, we propose an enhancement of depth edge detection using an edge-preserving filter, bilateral filter. The filter smooths an image and reduces the edge blurring effects across the edge such as halos and phantom. We maintain a canny edge detection principle and incorporate it with morphological properties. The results show that, this method can detect edges of a depth image better than the method without the edge-preserving filter such as gaussian and median blur.