Output details
11 - Computer Science and Informatics
University of Leeds
Detecting Carried Objects from Sequences of Walking Pedestrians
<23>The detection of carried bags is an important problem in some applications of computer vision. Our new method, presented in this journal article, defined the state of the art over the previous gold-standard (University of Maryland, IEEE-TPAMI, 2000). The method is being used within the DARPA Minds Eye program as baseline for developments and evaluation (consortium led by SRI, involving Leeds and Maryland, $570k to Leeds): results published in 2013 at CVPR workshop (Maryland, DOI:10.1109/CVPRW.2013.114) and ICVS (Leeds, DOI:10.1007/978-3-642-39402-7_23). An earlier version of this work appeared in the leading European conference in Computer Vision (ECCV 2008, DOI:10.1007/978-3-540-88690-7_12).