SEMANTIC SEGMENTATION IN DEPTH DATA : A COMPARATIVE EVALUATION OFIMAGE AND POINT CLOUD BASED METHODS

SEMANTIC SEGMENTATION IN DEPTH DATA : A COMPARATIVE EVALUATION OFIMAGE AND POINT CLOUD BASED METHODS
Jigyasa Singh Katrolia, Lars Kraemer, Jason Raphael Rambach, Bruno Mirbach, Didier Stricker
Proceedings of ICIP. IEEE International Conference on Image Processing (ICIP-2021) 28th IEEE International Conference on Image Processing (IEEE - ICIP) September 19-22 Anchorage, Alaska Alaska United States IEEE 2021 .

Abstract:

The problem of semantic segmentation from depth images can be addressed by segmenting directly in the image domain or at 3D point cloud level. In this paper, we attempt for the first time to provide a study and experimental comparison of the two approaches. Through experiments on three datasets,namely SUN RGB-D, NYUdV2 and TICaM, we extensively compare various semantic segmentation algorithms, the input to which includes images and point clouds derived from them.Based on this, we offer analysis of the performance and computational cost of these algorithms that can provide guidelines on when each method should be preferred.