Abstract
This research features object recognition that exploits the context of object-action interaction to enhance the recognition performance. Since objects have specific usages, and human actions corresponding to these usages can be associated with these objects, human actions can provide effective information for object recognition. When objects from different categories have similar appearances, the human action associated with each object can be very effective in resolving ambiguities related to recognizing these objects. We propose an efficient method that integrates human interaction with objects into a form of object recognition. We represent human actions by concatenating poselet vectors computed from key frames and learn the probabilities of objects and actions using random forest and multi-class AdaBoost algorithms. Our experimental results show that poselet representation of human actions is quite effective in integrating human action information into object recognition.
Highlights
Object recognition is difficult due to a variety of factors, including viewpoint variation, illumination changes, occlusion, etc
We have used Bag of Visual words (BoV) model of local N-jets [20,21,22], which are built from space-time interest points (STIP) [21,22]
This work focused on the efficient use of object-action context to resolve the inherent difficulty of object recognition caused by large intra-category appearance variations and inter-category appearance similarities
Summary
Object recognition is difficult due to a variety of factors, including viewpoint variation, illumination changes, occlusion, etc. Before encountering these factors, the inherent difficulty of object recognition lies in the fact that there is a large amount of intra-category appearance variation, and objects from different categories may have similar appearances. In order to improve the performance of object recognition, researchers have exploited contextual information that includes spatial [1,2,3], semantic [4,5,6,7], and scale [8,9] contexts. Semantic context provides clues related to the co-occurrence of objects with other objects in a scene. Scale context gives the relative scale of objects in a scene
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
