Detecting pedestrians on a Movement Feature Space

作者：

Highlights：

• A Movement Feature Space generates oriented histogram family descriptors.

• Detection system involves motion detection, hypothesis generation and validation.

• A cascade of classifiers combine generative and discriminants functions.

• Best result gives 25.5% of miss rate with 0.1 false positives per image.

• Running time is between 2 and 6 fps in 640×480 frames size.

摘要

Highlights•A Movement Feature Space generates oriented histogram family descriptors.•Detection system involves motion detection, hypothesis generation and validation.•A cascade of classifiers combine generative and discriminants functions.•Best result gives 25.5% of miss rate with 0.1 false positives per image.•Running time is between 2 and 6 fps in 640×480 frames size.

论文关键词：Pedestrian detection,Movement Feature Space,Histograms of oriented level lines,Adaboost cascade,Linear SVM

论文评审过程：Available online 6 June 2013.

论文官网地址：https://doi.org/10.1016/j.patcog.2013.05.020