Covariate factors, such as persons carrying a bag and wearing a jacket, continue to cause significant misclassification in gait recognition. A novel and efficient approach learns a “typical” Gait Energy Image representation free from covariate factors which aids their mitigation in test and training data. Combating the influence of covariate factors yields a significant improvement of 11% over existing state of the art performance for sequences capturing persons wearing a jacket.
|Title of host publication||Advances in Visual Computing|
|Subtitle of host publication||9th International Symposium, ISVC 2013, Rethymnon, Crete, Greece, July 29-31, 2013. Proceedings, Part II|
|Editors||George Bebis , Richard Boyle , Bahram Parvin, Darko Koracin, Baoxin Li, Fatih Porikli, Victor Zordan, James Klosowski , Sabine Coquillart , Xun Luo, Min Chen, David Gotz|
|Number of pages||9|
|Publication status||Published - 2013|
|Name||Lecture Notes in Computer Science|
Whytock, T., Belyaev, A., & Robertson, N. (2013). Towards robust gait recognition. In G. Bebis , R. Boyle , B. Parvin, D. Koracin, B. Li, F. Porikli, V. Zordan, J. Klosowski , S. Coquillart , X. Luo, M. Chen, & D. Gotz (Eds.), Advances in Visual Computing: 9th International Symposium, ISVC 2013, Rethymnon, Crete, Greece, July 29-31, 2013. Proceedings, Part II (pp. 523-531). (Lecture Notes in Computer Science; Vol. 8034). https://doi.org/10.1007/978-3-642-41939-3_51