Query Adaptive Similarity Measure for RGB-D Object Recognition

• Main Authors: Cheng, Yanhua, Cai, Rui, Zhang, Chi, Li, Zhiwei, Zhao, Xin, Huang, Kaiqi, Rui, Yong
• Format: Conference Proceeding
• Language: English
• Subjects: Accuracy; Cameras; Categories; Computer vision; Conferences; Constants; Feature extraction; Image color analysis; Matching; Object recognition; Shape; Similarity
• ISSN: 2380-7504
• DOI: 10.1109/ICCV.2015.25

This paper studies the problem of improving the top-1 accuracy of RGB-D object recognition. Despite of the impressive top-5 accuracies achieved by existing methods, their top-1 accuracies are not very satisfactory. The reasons are in two-fold: (1) existing similarity measures are sensitive to object pose and scale changes, as well as intra-class variations, and (2) effectively fusing RGB and depth cues is still an open problem. To address these problems, this paper first proposes a new similarity measure based on dense matching, through which objects in comparison are warped and aligned, to better tolerate variations. Towards RGB and depth fusion, we argue that a constant and golden weight doesn't exist. The two modalities have varying contributions when comparing objects from different categories. To capture such a dynamic characteristic, a group of matchers equipped with various fusion weights is constructed, to explore the responses of dense matching under different fusion configurations. All the response scores are finally merged following a learning-to-combination way, which provides quite good generalization ability in practice. The proposed approach win the best results on several public benchmarks, e.g., achieves 92.7% top-1 test accuracy on the Washington RGB-D object dataset, with a 5.1% improvement over the state-of-the-art.