Adaboost classifier on-line learning method and Adaboost classifier on-line learning system

Abstract

The invention relates to an Adaboost classifier on-line learning method and an Adaboost classifier on-line learning system. The Adaboost classifier on-line learning method comprises steps that: object detection is carried out by a strong classifier acquired through employing off-line training, and an object detection result is acquired; object detection is acquired by employing a background model to acquire a motion object; the object detection result acquired by the strong classifier is compared with the motion object acquired through detection by employing the background model to acquire an error classifier object; the error classifier object is taken as an on-line training sample to carry out on-line training to acquire a strong classifier after updating. According to the Adaboost classifier on-line learning method and the Adaboost classifier on-line learning system, the object detection result acquired by the off-line classifier is compared with the motion object acquired through detection by employing the background model to acquire the error classifier object, the error classifier object is taken as the on-line training sample to acquire the strong classifier after updating. Generalization performance of the object detection classifier is effectively improved, so the object detection classifier can adapt to a monitoring scene during operation, a detection ratio is improved, and a rate of false alarm is reduced.

Description

technical field [0001] The invention relates to the field of classifiers, in particular to an Adaboost classifier online learning method and system. Background technique [0002] Target detection technologies such as face detection, pedestrian detection, and vehicle detection are one of the core technologies of intelligent video surveillance. At present, there are two mainstream methods of object detection: motion detection and classifier-based detection. Based on motion detection, the moving target (foreground) in the scene is segmented through background modeling and other technologies. Separate each target, in addition, it is impossible to accurately distinguish the type of each target. Classifier-based detection is a machine learning method that trains a target-specific classifier (such as a face classifier) ​​in advance, scans the entire video frame at runtime, and detects all the targets in it. [0003] Among target detection classifiers, the Adaboost classifier is ...

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary to provide an online learning method for Adaboost classifiers for the traditional Adaboost classifier, which is generated by offline training, and the detection target task has a low detection rate and a high false positive rate. Can improve the detection rate and the false positive rate is low

Images