Pedestrian Detection Using Multi-Objective Optimization
Pedestrian detection on urban video sequences challenges classification systems because of the presence of cluttered backgrounds which drop their performances. This article proposes a Multi-Objective Optimization (MOO) technique reducing this limitation. It trains a pool of cascades of boosted classifiers using different positive datasets. A Pareto Front is obtained from the locally non-dominated operational points of the Receptive Objective Curve (ROC) of those classifiers. Using information about the dynamic of the scene, different pairs of operational points from the Pareto Front are employed to improve the performance of the system. Results on a real sequences outperform traditional detector systems.
KeywordsMulti-objective optimization Pedestrian detection
- 1.Bradley, A.: The use of the area under the roc curve in the evaluation of machine learning algorithms. PR 30, 1145–1159 (1997)Google Scholar
- 4.Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. CVPR 1, 886–893 (2005)Google Scholar
- 8.Negri, P., Goussies, N., Lotito, P.: Detecting pedestrians on a movement feature space. PR 47(1), 56–71 (2014)Google Scholar
- 10.Rosales-Pérez, A., Gonzalez, J.A., Coello-Coello, C.A., Reyes-Garcia, C.A., Escalante, H.J.: Evolutionary multi-objective approach for prototype generation and feature selection. In: Bayro-Corrochano, E., Hancock, E. (eds.) CIARP 2014. LNCS, vol. 8827, pp. 424–431. Springer, Heidelberg (2014) Google Scholar
- 12.Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. CVPR 1, 511–518 (2001)Google Scholar