An effective local feature descriptor for object detection in real scenes

In this study, we advocate the importance of robust local features that allow object form to be distinguished from other objects for detection purpose. We start from the grid of Histogram of oriented gradients (HOG) and integrate Scale Invariant Feature Transform (SIFT) within them. In HOG features an object's appearance is detected by the distribution of local intensity gradients or edge directions for different cells. In the proposed method we have computed the SIFT despite of computing intensity gradients for these cells. In this way, the proposed approach does not only provide more significant information than just providing intensity gradients but also proves to deal with following challenges: (i) scale invariance; (ii) rotation invariance; (iii) change in illumination; and (iv) change in view points. With qualitative and quantitative experimental evaluation on standard INRIA dataset, we have compared the proposed method with other state of the art object detection methods and demonstrated better performance over them.

[1]  Yan Ke,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[2]  Gertjan J. Burghouts,et al.  Performance evaluation of local colour invariants , 2009, Comput. Vis. Image Underst..

[3]  Andrew Zisserman,et al.  Scene Classification Via pLSA , 2006, ECCV.

[4]  Andrew Zisserman,et al.  Representing shape with a spatial pyramid kernel , 2007, CIVR '07.

[5]  Huimin Lu,et al.  Two novel real-time local visual features for omnidirectional vision , 2010, Pattern Recognit..

[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]  Koen E. A. van de Sande,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Stefano Soatto,et al.  Knowing a Good Feature When You See It: Ground Truth and Methodology to Evaluate Local Features for Recognition , 2010, Computer Vision: Detection, Recognition and Reconstruction.

[9]  Ivan Laptev,et al.  Local Descriptors for Spatio-temporal Recognition , 2004, SCVMA.

[10]  Swati Nigam,et al.  Curvelet transform based object tracking , 2010, 2010 International Conference on Computer and Communication Technology (ICCCT).

[11]  Hans Burkhardt,et al.  SHOG - Spherical HOG Descriptors for Rotation Invariant 3D Object Detection , 2011, DAGM-Symposium.

[12]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[13]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[14]  Ashish Khare,et al.  Curvelet transform-based technique for tracking of moving objects , 2012 .

[15]  Bernd Girod,et al.  Quantization schemes for low bitrate Compressed Histogram of Gradients descriptors , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[16]  Bernd Girod,et al.  CHoG: Compressed histogram of gradients A low bit-rate feature descriptor , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Huimin Lu,et al.  A Real-Time Local Visual Feature for Omnidirectional Vision Based on FAST and CS-LBP , 2010 .

[18]  Barbara Caputo,et al.  Local velocity-adapted motion events for spatio-temporal recognition , 2007, Comput. Vis. Image Underst..

[19]  Swati Nigam,et al.  On human activity recognition in video sequences , 2011, 2011 2nd International Conference on Computer and Communication Technology (ICCCT-2011).

[20]  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).

[21]  Swati Nigam,et al.  Automatic human activity recognition in video using background modeling and spatio-temporal template matching based technique , 2011, ACAI '11.

[22]  Thomas Brox,et al.  Fast Rotation Invariant 3D Feature Computation Utilizing Efficient Local Neighborhood Operators , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[24]  Andrew Zisserman,et al.  Image Classification using Random Forests and Ferns , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[25]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Marco Reisert,et al.  Circular Fourier-HOG features for rotation invariant object detection in biomedical images , 2012, 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI).