HOG-Based Descriptors on Rotation Invariant Human Detection

In the past decade, there have been many proposed techniques on human detection. Dalal and Triggs suggested Histogram of Oriented Gradient (HOG) features combined with a linear SVM to handle the task. Since then, there have been many variations of HOG-based detection introduced. They are, nevertheless, based on an assumption that the human must be in upright pose due to the limitation in geometrical variation. HOG-based human detections obviously fails in monitoring human activities in the daily life such as sleeping, lying down, falling, and squatting. This paper focuses on exploring various features based on HOG for rotation invariant human detection. The results show that square-shaped window can cover more poses but will cause a drop in performance. Moreover, some rotation-invariant techniques used in image retrieval outperform other techniques in human classification on upright pose and perform very well on various poses. This could help in neglecting the assumption of upright pose generally used.

[1]  Mohammad Mehdi Ebadzadeh,et al.  Fuzzy generalized hough transform invariant to rotation and scale in noisy environment , 2009, 2009 IEEE International Conference on Fuzzy Systems.

[2]  Muhammad Saleem,et al.  Comparative analysis of invariant schemes for logo classification , 2009, 2009 International Conference on Emerging Technologies.

[3]  Christian Wöhler,et al.  An adaptable time-delay neural-network algorithm for image sequence analysis , 1999, IEEE Trans. Neural Networks.

[4]  Md. Monirul Islam,et al.  Rotation invariant curvelet features for texture image retrieval , 2009, 2009 IEEE International Conference on Multimedia and Expo.

[5]  Ijaz Mansoor Qureshi,et al.  Rotation and gray-scale-invariant texture analysis using radon and differential radon transforms based hidden Markov models , 2010 .

[6]  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).

[7]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[8]  James J. Little,et al.  Simultaneous Tracking and Action Recognition using the PCA-HOG Descriptor , 2006, The 3rd Canadian Conference on Computer and Robot Vision (CRV'06).

[9]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[10]  Andrew Zisserman,et al.  Progressive search space reduction for human pose estimation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  François Brémond,et al.  Tracking HoG Descriptors for Gesture Recognition , 2009, 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance.

[12]  Touradj Ebrahimi,et al.  Orientation histogram-based matching for region tracking , 2007, Eighth International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS '07).

[13]  Dariu Gavrila,et al.  Monocular Pedestrian Detection: Survey and Experiments , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Tieniu Tan,et al.  Rapid and robust human detection and tracking based on omega-shape features , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[15]  Dariu Gavrila,et al.  Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle , 2007, International Journal of Computer Vision.

[16]  Wei-Yun Yau,et al.  Novel region-based modeling for human detection within highly dynamic aquatic environment , 2004, CVPR 2004.

[17]  Jinye Peng,et al.  Images similarity detection based on directional gradient angular histogram , 2002, Object recognition supported by user interaction for service robots.

[18]  Parham Aarabi,et al.  Fourier-based Rotation Invariant image features , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[19]  António M. G. Pinheiro,et al.  Image Descriptors Based on the Edge Orientation , 2009, 2009 Fourth International Workshop on Semantic Media Adaptation and Personalization.