Scene Understanding through Autonomous Interactive Perception
2011 (English)In: Computer Vision Systems: Lecture Notes in Computer Science / [ed] Crowley James L., Draper Bruce, Thonnat Monique, Springer Verlag , 2011, 153-162 p.Conference paper (Refereed)
We propose a framework for detecting, extracting and mod-eling objects in natural scenes from multi-modal data. Our frameworkis iterative, exploiting different hypotheses in a complementary manner.We employ the framework in realistic scenarios, based on visual appear-ance and depth information. Using a robotic manipulator that interactswith the scene, object hypotheses generated using appearance informa-tion are confirmed through pushing. The framework is iterative, eachgenerated hypothesis is feeding into the subsequent one, continuously re-fining the predictions about the scene. We show results that demonstratethe synergic effect of applying multiple hypotheses for real-world sceneunderstanding. The method is efficient and performs in real-time.
Place, publisher, year, edition, pages
Springer Verlag , 2011. 153-162 p.
IdentifiersURN: urn:nbn:se:kth:diva-43453DOI: 10.1007/978-3-642-23968-7_16ScopusID: 2-s2.0-80053457663ISBN: 978-3642239670ISBN: 3642239676OAI: oai:DiVA.org:kth-43453DiVA: diva2:448473
8th International Conference on Computer Vision Systems; 20 - 22 September 2011, Sophia Antipolis (France)