Object detection using edge histogram of oriented gradient

In this paper, we address the object detection problem by a proposed gradient feature, the Edge Histogram of Oriented Gradient (Edge-HOG). Edge-HOG consists of several blocks arranged along a line or an arc, which is designed to describe the edge pattern. In addition, we propose a new feature extraction method, which extracts the structural information based on the gravity centers as complementary to traditional gradient histograms. As a result, the proposed Edge-HOG not only reflects the local shape information of objects, but also captures more significant appearance information. Experimental results show that the proposed approach significantly improves both the detection accuracy and the convergence speed compared to the traditional HOG feature. It also achieves performance competitive with some commonly-used methods on pedestrian detection and car detection tasks.

[1]  Weiyao Lin,et al.  A new Local-Main-Gradient-Orientation HOG and contour differences based algorithm for object classification , 2013, 2013 IEEE International Symposium on Circuits and Systems (ISCAS2013).

[2]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[3]  Yoram Singer,et al.  Improved Boosting Algorithms Using Confidence-rated Predictions , 1998, COLT' 98.

[4]  Nuno Vasconcelos,et al.  Learning Optimal Embedded Cascades , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Shimon Ullman,et al.  The chains model for detecting parts by their context , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Yingdong Ma,et al.  Human Detection with EOH-OLBP-Based Multi-Level Features , 2014 .

[7]  Wei Gao,et al.  Adaptive Contour Features in oriented granular space for human detection and segmentation , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Shuicheng Yan,et al.  An HOG-LBP human detector with partial occlusion handling , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[9]  Fatih Murat Porikli,et al.  Pedestrian Detection via Classification on Riemannian Manifolds , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Christoph H. Lampert,et al.  Beyond sliding windows: Object localization by efficient subwindow search , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Changyin Sun,et al.  Fast Human Detection Based on Enhanced Variable Size HOG Features , 2011, ISNN.

[12]  Subhransu Maji,et al.  Classification using intersection kernel support vector machines is efficient , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  Charles Dubout,et al.  Object Classification and Detection in High Dimensional Feature Space , 2013 .

[15]  Qiang Wu,et al.  Object Detection Based on Co-occurrence GMuLBP Features , 2012, 2012 IEEE International Conference on Multimedia and Expo.

[16]  Mei-Chen Yeh,et al.  Fast Human Detection Using a Cascade of Histograms of Oriented Gradients , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[17]  Ramakant Nevatia,et al.  Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[18]  Bernt Schiele,et al.  A Performance Evaluation of Single and Multi-feature People Detection , 2008, DAGM-Symposium.

[19]  Dan Roth,et al.  Learning to detect objects in images via a sparse, part-based representation , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.