Supervoxel Segmentation with Voxel-Related Gaussian Mixture Model

• Published in: Sensors (Basel, Switzerland) Vol. 18; no. 1; p. 128
• Main Authors: Ban, Zhihua, Chen, Zhong, Liu, Jianguo
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 05.01.2018; MDPI
• Subjects: Accuracy; Algorithms; expectation– maximization; Experiments; Gaussian mixture model; Methods; Sensors; superpixel; supervoxel; video segmentation; supervoxel; superpixel; expectation– maximization; video segmentation; Gaussian mixture model
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s18010128

Extended from superpixel segmentation by adding an additional constraint on temporal consistency, supervoxel segmentation is to partition video frames into atomic segments. In this work, we propose a novel scheme for supervoxel segmentation to address the problem of new and moving objects, where the segmentation is performed on every two consecutive frames and thus each internal frame has two valid superpixel segmentations. This scheme provides coarse-grained parallel ability, and subsequent algorithms can validate their result using two segmentations that will further improve robustness. To implement this scheme, a voxel-related Gaussian mixture model (GMM) is proposed, in which each supervoxel is assumed to be distributed in a local region and represented by two Gaussian distributions that share the same color parameters to capture temporal consistency. Our algorithm has a lower complexity with respect to frame size than the traditional GMM. According to our experiments, it also outperforms the state-of-the-art in accuracy.