Share Email Print

Journal of Electronic Imaging

Discriminative boosted forest with convolutional neural network-based patch descriptor for object detection
Author(s): Tao Xiang; Tao Li; Mao Ye; Xudong Li
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Object detection with intraclass variations is challenging. The existing methods have not achieved the optimal combinations of classifiers and features, especially features learned by convolutional neural networks (CNNs). To solve this problem, we propose an object-detection method based on improved random forest and local image patches represented by CNN features. First, we compute CNN-based patch descriptors for each sample by modified CNNs. Then, the random forest is built whose split functions are defined by patch selector and linear projection learned by linear support vector machine. To improve the classification accuracy, the split functions in each depth of the forest make up a local classifier, and all local classifiers are assembled in a layer-wise manner by a boosting algorithm. The main contributions of our approach are summarized as follows: (1) We propose a new local patch descriptor based on CNN features. (2) We define a patch-based split function which is optimized with maximum class-label purity and minimum classification error over the samples of the node. (3) Each local classifier is assembled by minimizing the global classification error. We evaluate the method on three well-known challenging datasets: TUD pedestrians, INRIA pedestrians, and UIUC cars. The experiments demonstrate that our method achieves state-of-the-art or competitive performance.

Paper Details

Date Published: 6 January 2016
PDF: 11 pages
J. Electron. Imaging. 25(1) 013002 doi: 10.1117/1.JEI.25.1.013002
Published in: Journal of Electronic Imaging Volume 25, Issue 1
Show Author Affiliations
Tao Xiang, Univ. of Electronic Science and Technology of China (China)
Tao Li, Univ. of Electronic Science and Technology of China (China)
Mao Ye, Univ. of Electronic Science and Technology of China (China)
Xudong Li, Univ. of Electronic Science and Technology of China (China)

© SPIE. Terms of Use
Back to Top