{"type":"ScholarlyArticle","title":"Peripheral-Foveal Vision for Real-time Object Recognition and Tracking in Video","authors":[{"name":"Stephen Gould","slug":"stephen-gould","given":"Stephen","family":"Gould","affiliation":""},{"name":"Joakim Arfvidsson","slug":"joakim-arfvidsson","given":"Joakim","family":"Arfvidsson","affiliation":""},{"name":"Adrian Kaehler","slug":"adrian-kaehler","given":"Adrian","family":"Kaehler","affiliation":""},{"name":"Benjamin Sapp","slug":"benjamin-sapp","given":"Benjamin","family":"Sapp","affiliation":""},{"name":"Marius Messner","slug":"marius-messner","given":"Marius","family":"Messner","affiliation":""},{"name":"Gary R. Bradski","slug":"gary-r-bradski","given":"Gary R.","family":"Bradski","affiliation":""},{"name":"Paul Baumstarck","slug":"paul-baumstarck","given":"Paul","family":"Baumstarck","affiliation":""},{"name":"Sukwon Chung","slug":"sukwon-chung","given":"Sukwon","family":"Chung","affiliation":""},{"name":"Andrew Y. Ng","slug":"andrew-y-ng","given":"Andrew Y.","family":"Ng","affiliation":""}],"abstract":"Human object recognition in a physical 3-d environment is still far superior to that of any robotic vision system. We believe that one reason (out of many) for this — one that has not heretofore been significantly exploited in the artificial vision literature — is that humans use a fovea to fixate on, or near an object, thus obtaining a very high resolution image of the bject and rendering it easy to recognize. In this paper, we present a novel method for identifying and tracking objects in multi-resolution digital video of partially cluttered environments. Our method is motivated by biological vision systems and uses a learned attentive interest map on a low resolution data stream to direct a high resolution fovea. Objects that are recognized in the fovea can then be tracked using peripheral vision. Because object recognition is run only on a small foveal image, our system achieves performance in real-time object recognition and tracking that is well beyond simpler systems.","doi":null,"url":"https://ijcai.org/proceedings/2007/341","pdf":"https://ijcai.org/proceedings/2007/0341.pdf","markdown":"https://ijcai.org/proceedings/2007/341.md","bibtex":"https://ijcai.org/proceedings/2007/bibtex/341","volume":{"slug":"2007","title":"Proceedings of the Twentieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2007","url":"https://ijcai.org/proceedings/2007/","year":2007,"location":"Hyderabad, India","dates":"","editors":"Ramon López de Mántaras","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":341,"pages":{"first":2115,"last":2120},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}