Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

12-2015

Abstract

In this paper, we propose a new approach to generate oriented object proposals (OOPs) to reduce the detection error caused by various orientations of the object. To this end, we propose to efficiently locate object regions according to pixelwise object probability, rather than measuring the objectness from a set of sampled windows. We formulate the proposal generation problem as a generative probabilistic model such that object proposals of different shapes (i.e., sizes and orientations) can be produced by locating the local maximum likelihoods. The new approach has three main advantages. First, it helps the object detector handle objects of different orientations. Second, as the shapes of the proposals may vary to fit the objects, the resulting proposals are tighter than the sampling windows with fixed sizes. Third, it avoids massive window sampling, and thereby reducing the number of proposals while maintaining a high recall. Experiments on the PASCAL VOC 2007 dataset show that the proposed OOP outperforms the state-of-the-art fast methods. Further experiments show that the rotation invariant property helps a class-specific object detector achieve better performance than the state-of-the-art proposal generation methods in either object rotation scenarios or general scenarios. Generating OOPs is very fast and takes only 0.5s per image.

Keywords

Computer vision, Generation method, Object detectors, Probabilistic modeling, Rotation invariant

Discipline

Applied Statistics | Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Research Areas

Software and Cyber-Physical Systems

Publication

2015 IEEE International Conference on Computer Vision (ICCV): Santiago, Chile, December 7-13: Proceedings

First Page

280

Last Page

288

Identifier

10.1109/ICCV.2015.40

Publisher

IEEE Computer Society

City or Country

Los Alamitos, CA

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/ICCV.2015.40

Download

Share

COinS