Skip to Main content Skip to Navigation
New interface
Conference papers

Generic Object Discrimination for Mobile Assistive Robots using Projective Light Diffusion

Panagiotis Papadakis 1, 2 David Filliat 3, 4 
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
Abstract : A number of assistive robot services depend on the classification of objects while dealing with an increased volume of sensory data, scene variability and limited computational resources. We propose using more concise representations via a seamless combination of photometric and geometric features fused by exploiting local photometric/geometric correlation and employing domain transform filtering in order to recover scene structure. This is obtained through a projective light diffusion imaging process (PLDI) which allows capturing surface orientation, image edges and global depth gradients into a single image. Object candidates are finally encoded into a discriminative, wavelet-based de-scriptor allowing very fast object queries. Experiments with an indoor robot demonstrate improved classification performance compared to alternative methods and an overall superior discriminative power compared to state-of-the-art unsupervised descriptors within ModelNet10 benchmark.
Complete list of metadata

Cited literature [26 references]  Display  Hide  Download
Contributor : Panagiotis Papadakis Connect in order to contact the contributor
Submitted on : Friday, February 2, 2018 - 5:29:45 PM
Last modification on : Friday, August 5, 2022 - 2:54:52 PM
Long-term archiving on: : Thursday, May 3, 2018 - 10:28:20 AM


Files produced by the author(s)



Panagiotis Papadakis, David Filliat. Generic Object Discrimination for Mobile Assistive Robots using Projective Light Diffusion. WACVW 2018 : IEEE Winter Conference on Applications of Computer Vision, Workshop CV-AAL - Computer Vision for Active and Assisted Living, Mar 2018, Reno, United States. pp.1-9, ⟨10.1109/WACVW.2018.00013⟩. ⟨hal-01699842⟩



Record views


Files downloads