Abstract
Scene recognition is still a very important topic in many fields, and that is definitely the case in robotics. Nevertheless, this task is view-dependent, which implies the existence of preferable directions when recognizing a particular scene. Both in human and computer vision-based classification, this actually often turns out to be biased. In our case, instead of trying to improve the generalization capability for different view directions, we have opted for the development of a system capable of filtering out noisy or meaningless images while, on the contrary, retaining those views from which is likely feasible that the correct identification of the scene can be made. Our proposal works with a heuristic metric based on the detection of key points in 3D meshes (Harris 3D). This metric is later used to build a model that combines a Minimum Spanning Tree and a Support Vector Machine (SVM). We have performed an extensive number of experiments through which we have addressed (a) the search for efficient visual descriptors, (b) the analysis of the extent to which our heuristic metric resembles the human criteria for relevance and, finally, (c) the experimental validation of our complete proposal. In the experiments, we have used both a public image database and images collected at our research center.
Highlights
There is an increasing market for service robots which is still dependent on progress to overcome technological limitations
Taking advantage of the great deal of research and progress made in the field of visual scene recognition [3,4], the basic idea of current image-based place recognition and location approaches in robotics is to search a database of indoor images and return the best match [5,6]
The first global descriptor we have considered is the combination of Local Difference Sign Binary Patterns (LSBP) and Local Difference Magnitude
Summary
There is an increasing market for service robots which is still dependent on progress to overcome technological limitations. In this environment, the extent to which domestic and personal service robots can recognize scenes will have a direct impact on what these robots can do to assist humans in their daily activities. Since collecting geo-tagged datasets is time-consuming and labor-intensive, and indoor places do not necessarily have GPS (Global Positioning System) information, image-based place recognition and localization has been attempted for indoor environments in recent years [1,2]. Taking advantage of the great deal of research and progress made in the field of visual scene recognition [3,4], the basic idea of current image-based place recognition and location approaches in robotics is to search a database of indoor images and return the best match [5,6]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.