2016/06/03 by Alexander Hagg, Hagg, Alexander, Frederik Hegger +4
Computer Science · Engineering · Physics and Astronomy · #Advanced Image and Video Retrieval Techniques #Artificial intelligence #Cognitive neuroscience of visual object recognition #Color Science and Applications #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #FOS: Computer and information sciences #Fusion #Industrial Vision Systems and Defect Detection #Infrared Target Detection Methodologies #Modalities #Object (grammar) #Optics #Pattern recognition (psychology) #Physics #Reflectivity #Robotics and Sensor-Based Localization #Robustness (evolution) #Sensor fusion #Specular reflection #Visual Attention and Saliency Detection #cs.CV
paper · pdf · doi:10.48550/arxiv.1606.01001
published in arXiv (Cornell University) (Cornell University) · 12 pages
arxiv created 2016/06/03 · openalex publication_date 2016/06/03 · arxiv updated 2016/06/06 · openalex created_date 2022/10/05 · openalex updated_date 2026/08/04
Current object recognition methods fail on object sets that include both\ndiffuse, reflective and transparent materials, although they are very common in\ndomestic scenarios. We show that a combination of cues from multiple sensor\nmodalities, including specular reflectance and unavailable depth information,\nallows us to capture a larger subset of household objects by extending a state\nof the art object recognition method. This leads to a significant increase in\nrobustness of recognition over a larger set of commonly used objects.\n