Bayesian learning of a search region for pedestrian detection

• Published in: Multimedia tools and applications Vol. 75; no. 2; pp. 863 - 885
• Main Authors: Baek, Jeonghyun, Hong, Sungjun, Kim, Jisu, Kim, Euntai
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.01.2016; Springer Nature B.V
• Subjects: Algorithms; Bayesian analysis; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Datasets; Detection alarms; Experiments; Intelligent vehicles; Learning; Machine learning; Mathematical analysis; Multimedia; Multimedia Information Systems; Pedestrians; Probability distribution; Searching; Special Purpose and Application-Based Systems; Statistical analysis; Support vector machines; Surveillance; Vehicles; Caltech pedestrian dataset; Haar-like Adaboost; Pedestrian detection; Bayesian inference; HOG-LSVM; Sliding window approach
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-014-2329-z

An efficient pedestrian detection method is proposed for intelligent vehicles in this paper. The proposed method learns the region in which pedestrians are likely to be detected and narrows down the search to the likely region. The likely region is modeled as a Gaussian distribution on the y-axis and its parameters are updated by a Bayesian approach. Thus, the proposed method starts with an exhaustive full search, but gradually narrows down the search by focusing on the likely region. The learning of the likely region is formulated as a Bayesian learning problem and the likely region is analytically derived. The proposed method is combined with two popular pedestrian detection methods, Haar-like Adaboost and HOG-LSVM, and some experiments are conducted with the Caltech pedestrian dataset. The experiments show that the proposed method not only reduces computation time, but also enhances performance by rejecting false positive results.