Robust object detection via soft cascade

被引：186

作者：

Bourdev, L ^{[1
]}

Brandt, J ^{[1
]}

机构：

[1] Adobe Syst Inc, Off Technol, San Jose, CA 95110 USA

来源：

2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 2, PROCEEDINGS | 2005年

关键词：

D O I：

10.1109/cvpr.2005.310

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We describe a method for training object detectors using a generalization of the cascade architecture, which results in a detection rate and speed comparable to that of the best published detectors while allowing for easier training and a detector with fewer features. In addition, the method allows for quickly calibrating the detector for a target detection rate, false positive rate or speed. One important advantage of our method is that it enables systematic exploration of the ROC Surface, which characterizes the trade-off between accuracy and speed for a given classifier.

引用

页码：236 / 243

页数：8