Title :
A pattern classification approach to dynamical object detection
Author :
Papageorgiou, Constantine ; Poggio, Tomaso
Author_Institution :
Artificial Intelligence Lab., MIT, Cambridge, MA, USA
Abstract :
Current systems for object detection in video sequences rely on explicit dynamical models like Kalman filters or hidden Markov models. There is significant overhead needed in the development of such systems as well as the a priori assumption that the object dynamics can be described with such a dynamical model. This paper describes a new pattern classification technique for object detection in video sequences that uses a rich, overcomplete dictionary of wavelet features to describe an object class. Unlike previous work where a small subset of features was selected from the dictionary, this system does no feature selection and learns the model in the full 1,326 dimensional feature space. Comparisons using different sized sets of several types of features are given. We extend this representation into the time domain without assuming any explicit model of dynamics. This data driven approach produces a model of the physical structure and short-time dynamical characteristics of people from a training set of examples; no assumptions are made about the motion of people, just that short sequences characterize their dynamics sufficiently for the purposes of detection. One of the main benefits of this approach is that transient false positives are reduced. This technique compares favorably with the static detection approach and could be applied to other object classes. We also present a real-time version of one of our static people detection systems
Keywords :
Kalman filters; hidden Markov models; object detection; pattern classification; wavelet transforms; Kalman filters; a priori assumption; dynamical object detection; explicit dynamical models; hidden Markov models; pattern classification approach; short-time dynamical characteristics; static detection approach; static people detection systems; time domain; transient false positives; video sequences; wavelet features; Biology computing; Electrical capacitance tomography; Face detection; Face recognition; Layout; Motion detection; Object detection; Pattern classification; Read only memory; Video sequences;
Conference_Titel :
Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on
Conference_Location :
Kerkyra
Print_ISBN :
0-7695-0164-8
DOI :
10.1109/ICCV.1999.790420