Abstract
Superpixel segmentation is a widely used preprocessing method in computer vision, but its performance is unsatisfactory for color images in cluttered indoor environments. In this work, a superpixel method named weighted coplanar feature clustering (WCFC) is proposed, which produces full coverage of superpixels in RGB-depth (RGBD) images of indoor scenes. Basically, a linear iterative clustering is adopted based on a cluster criterion that measures the color similarity, space proximity and geometric resemblance between pixels. However, to avoid the adverse impact of RGBD image flaws and to make full use of the depth information, WCFC first preprocesses the raw depth maps with an inpainting algorithm called a Cross-Bilateral Filter. Second, a coplanar feature is extracted from the refined RGBD image to represent the geometric similarities between pixels. Third, combined with the colors and positions of the pixels, the coplanar feature constructs the feature vector of the clustering method; thus, the distance measure, as the cluster criterion, is computed by normalizing the feature vectors. Finally, in order to extract the features of the RGBD image dynamically, a content-adaptive weight is introduced as a coefficient of the coplanar feature, which strikes a balance between the coplanar feature and other features. Experiments performed on the New York University (NYU) Depth V2 dataset demonstrate that WCFC outperforms the available state-of-the-art methods in terms of accuracy of superpixel segmentation, while maintaining a high speed.
Highlights
Superpixel segmentation is an unsupervised technique that can effectively capture image features [1] and benefit many computer vision applications
The mean filter size applied in normal estimation was set to 15 by 15, because several experiments have shown that the 15 × 15 mean filter is suitable for the point cloud in the estimation of normal maps and can ensure that there is no fragmentation in the normal maps produced
Examples of the superpixel segmentations produced by each method appear in Figure 4, and more detailed results compared with other superpixel algorithms are provided in Appendix A, Figures A1–A4
Summary
Superpixel segmentation is an unsupervised technique that can effectively capture image features [1] and benefit many computer vision applications. RGBD images provide more information than traditional color images, such as the depth at each pixel in the image region. An RGBD image can be projected from the 2D space onto the 3D coordinate system to form a color point cloud. Especially RGBD images, can run on point clouds and produce supervoxels, the neighborhood data of each point is insufficient. Weighted coplanar feature clustering makes a trade-off between the color and depth information by a content-adaptive weight and allows superpixels to completely cover the entire image by using the raw RGBD image.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have