Asymmetric Pruning for Learning Cascade Detectors

Cascade classifiers are one of the most important contributions to real-time object detection. Nonetheless, there are many challenging problems arising in training cascade detectors. One common issue is that the node classifier is trained with a symmetric classifier. Having a low misclassification error rate does not guarantee an optimal node learning goal in cascade classifiers, i.e., an extremely high detection rate with a moderate false positive rate. In this work, we present a new approach to train an effective node classifier in a cascade detector. The algorithm is based on two key observations: 1) Redundant weak classifiers can be safely discarded; 2) The final detector should satisfy the asymmetric learning objective of the cascade architecture. To achieve this, we separate the classifier training into two steps: finding a pool of discriminative weak classifiers/features and training the final classifier by pruning weak classifiers which contribute little to the asymmetric learning criterion (asymmetric classifier construction). Our model reduction approach helps accelerate the learning time while achieving the pre-determined learning objective. Experimental results on both face and car data sets verify the effectiveness of the proposed algorithm. On the FDDB face data sets, our approach achieves the state-of-the-art performance, which demonstrates the advantage of our approach.

READ FULL TEXT

page 7

page 11

page 12

research
01/10/2013

Training Effective Node Classifiers for Cascade Classification

Cascade classifiers are widely used in real-time object detection. Diffe...
research
08/23/2010

Optimally Training a Cascade Classifier

Cascade classifiers are widely used in real-time object detection. Diffe...
research
07/30/2016

Learning Tree-Structured Detection Cascades for Heterogeneous Networks of Embedded Devices

In this paper, we present a new approach to learning cascaded classifier...
research
10/03/2013

Efficient pedestrian detection by directly optimize the partial area under the ROC curve

Many typical applications of object detection operate within a prescribe...
research
05/22/2010

LACBoost and FisherBoost: Optimally Building Cascade Classifiers

Object detection is one of the key tasks in computer vision. The cascade...
research
05/25/2017

Real-Time Background Subtraction Using Adaptive Sampling and Cascade of Gaussians

Background-Foreground classification is a fundamental well-studied probl...
research
09/16/2010

Asymmetric Totally-corrective Boosting for Real-time Object Detection

Real-time object detection is one of the core problems in computer visio...

Please sign up or login with your details

Forgot password? Click here to reset