{"type":"ScholarlyArticle","title":"Online Multi-Object Tracking by Quadratic Pseudo-Boolean Optimization","authors":[{"name":"Long Lan","slug":"long-lan","given":"Long","family":"Lan","affiliation":""},{"name":"Dacheng Tao","slug":"dacheng-tao","given":"Dacheng","family":"Tao","affiliation":""},{"name":"Chen Gong","slug":"chen-gong","given":"Chen","family":"Gong","affiliation":""},{"name":"Naiyang Guan","slug":"naiyang-guan","given":"Naiyang","family":"Guan","affiliation":""},{"name":"Zhigang Luo","slug":"zhigang-luo","given":"Zhigang","family":"Luo","affiliation":""}],"abstract":"Online multi-object tracking (MOT) is challenging: frame-by-frame matching of detection hypotheses to the correct trackers can be difficult. The Hungarian algorithm is the most commonly used online MOT data association method due to its rapid assignment; however, the Hungarian algorithm simply considers associations based on an affinity model. For crowded scenarios, frequently occurring interactions between objects complicate associations, and affinity-based methods usually fail in these scenarios. Here we introduce quadratic pseudo-Boolean optimization (QPBO) to an online MOT model to analyze frequent interactions. Specifically, we formulate two useful interaction types as pairwise potentials in QPBO, a design that benefits our model by exploiting informative interactions and allowing our online tracker to handle complex scenes. The auxiliary interactions result in a non-submodular QPBO, so we accelerate our online tracker by solving the model with a graph cut combined with a simple heuristic method. This combination achieves a reasonable local optimum and, importantly, implements the tracker efficiently. Extensive experiments on publicly available datasets from both static and moving cameras demonstrate the superiority of our method.","doi":null,"url":"https://ijcai.org/proceedings/2016/480","pdf":"https://ijcai.org/proceedings/2016/0480.pdf","markdown":"https://ijcai.org/proceedings/2016/480.md","bibtex":"https://ijcai.org/proceedings/2016/bibtex/480","volume":{"slug":"2016","title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2016","url":"https://ijcai.org/proceedings/2016/","year":2016,"location":"New York, NY, USA","dates":"9–15 July 2016","editors":"Subbarao Kambhampati","isbn":"978-1-57735-770-4; 978-1-57735-771-1","publisher":"AAAI Press / International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":480,"pages":{"first":3396,"last":3401},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}