In this paper an algorithm is presented to extract the valid depth data and correct the values of flying pixels by using depth information and confidence image. An adaptive segmentation for the measured depth image is executed based on kernel density estimation and one-pass connected component labeling. Then a modified structure tensor is used to detect the invalid pixels and the flying pixels contained in the depth image. Finally these pixels are corrected with the bi-cubic interpolation method or selectively removed by voting operation. And also, the erroneous pixels are excluded with augmented confidence. Experimental results have demonstrated the effectiveness of our algorithm.
The great advantage of Microsoft Kinect makes the depth acquisition real-time and inexpensive. But the depth maps directly obtained with the Microsoft Kinect device have absent regions and holes caused by optical factors. The noisy depth maps affect lots of complex tasks in computer vision. In order to improve the quality of the depth maps, this paper presents an efficient image inpainting strategy which is based on watershed segmentation and region merging framework of the corresponding color images. The primitive regions produced by watershed transform are merged into lager regions according to color similarity and edge among regions. Finally, mean filter operator to the adjacent pixels is used to fill up missing depth values and deblocking filter is applied for smoothing depth maps.
As the demand for 3DTV keep increasing these years, the conversion from exist 2D videos to 3D ones becomes a new area of research. Depth map generation plays a key point in the process. Two most important clues of depth are geometry of the scene and motion vector. This paper presents an algorithm of depth map generation, which intends to get the depth map combines two aspects of information. Compared to the previous work, our method is improved in finding vanishing point, detect motion vectors, and depth map generation.