Discriminative boosted forest with convolutional neural network-based patch descriptor for object detection

Tao Xiang; Tao Li; Mao Ye; Xudong Li

doi:10.1117/1.JEI.25.1.013002

6 January 2016 Discriminative boosted forest with convolutional neural network-based patch descriptor for object detection

Tao Xiang, Tao Li, Mao Ye, Xudong Li

Author Affiliations +

Journal of Electronic Imaging, Vol. 25, Issue 1, 013002 (January 2016). https://doi.org/10.1117/1.JEI.25.1.013002

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.

Citation Download Citation

Tao Xiang, Tao Li, Mao Ye, and Xudong Li "Discriminative boosted forest with convolutional neural network-based patch descriptor for object detection," Journal of Electronic Imaging 25(1), 013002 (6 January 2016). https://doi.org/10.1117/1.JEI.25.1.013002

Published: 6 January 2016

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available