Efficient Hierarchical Graph-Based Segmentation of RGBD Videos
This work addresses the need for scalable and efficient segmentation in RGBD video analysis, though it appears incremental as it builds on existing graph-based methods with a multistage approach.
The paper tackles the problem of segmenting 3D RGBD point clouds in videos by developing an efficient, hierarchical graph-based algorithm that combines depth, color, and temporal information, resulting in robust segmentation that can process videos of any length in a streaming pipeline.
We present an efficient and scalable algorithm for segmenting 3D RGBD point clouds by combining depth, color, and temporal information using a multistage, hierarchical graph-based approach. Our algorithm processes a moving window over several point clouds to group similar regions over a graph, resulting in an initial over-segmentation. These regions are then merged to yield a dendrogram using agglomerative clustering via a minimum spanning tree algorithm. Bipartite graph matching at a given level of the hierarchical tree yields the final segmentation of the point clouds by maintaining region identities over arbitrarily long periods of time. We show that a multistage segmentation with depth then color yields better results than a linear combination of depth and color. Due to its incremental processing, our algorithm can process videos of any length and in a streaming pipeline. The algorithm's ability to produce robust, efficient segmentation is demonstrated with numerous experimental results on challenging sequences from our own as well as public RGBD data sets.