Recognition of occluded objects by reducing feature interactions

The main difficulty for the recognition of occluded objects lies in the fact that the original feature set is corrupted and no longer reliable to represent the object of interest. This corruption is caused by the interactions between features from different objects, denoted as feature interactions, which is a key issue addressed in our algorithm. In this paper, a local to global strategy is represented for the occlusion recognition problem, which combines the pairwise grouping and graph matching algorithms. Local appearance similarity serves as priors to reduce feature interactions, by which the performance of graph matching algorithms is improved in order to deal with the contaminated data set. With our formulation, a global decision on object recognition can be made based on locally gathered information. Experimental results show that the proposed framework can dramatically reduce incorrect matches and objects under severe occlusions can still be recognized.

► Graph matching technique is introduced to occlusion recognition for the first time.
► Pairwise grouping is combined with graph matching.
► Appearance information is integrated into geometric consistency.
► Recognition decision is made based on a local to global strategy.
► Our method provides possible way integrating intermediate vision cue into object recognition.