IJRCS – Volume 5 Issue 4 Paper 1

Posted on by Researchscripteditor

PERSON DETECTION BASED ON FUSION HISTOGRAM OF GRADIENTS WITH TEXTURE (FHGT) LOCAL FEATURES

Author’s Name : Htet Htet Lin

Volume 05 Issue 04  Year 2018  ISSN No:  2349-3828  Page no: 1- 4

12

Abstract:

Proficient real time objects detection is complicated and still active areas in computer vision due to many challenges: object appearance variations, intra-class and inter-class differences, difference articulation, illumination, static/ dynamic occlusions, and aspect variations. Extract discriminative and accurate features is also challenging in order to precise statistical data on monitoring people that allows users to make strategic decisions. In the previous works, they have achieved remarkable development for some people body parts, but less performances for all the full body. To tackle this appearance issue, this paper proposes to merge kth gradient differential with tamura texture features together to get discriminative and robust features. Specifically, the k order features are used to extract by differentiating and then combined these feature easily due to their same cell based feature to form the G features. Moreover statistical tamura texture features are extracted by using Gray Level Difference Matrix detector. Then, the system introduces a new insight powerful local image features, FHGT is proposed to capture the stronger object edges and shading variations, and local coherence of object appearance. Then, features combine by Joint Histograms. The experimental result is tested on the public Pascal VOC 2007 Dataset and results are outperformed.

Keywords:

People Detection; Kth Differential Gradients Features; Tamura Texture Features; FHGT

References:

  1. N. Dalal. Finding people in images and videos. Institute National Poly technique de Grenoble-INPG, 2006.
  2. R. Filho, et al. Analysis of human tissue densities: A new approach to extract features from medical images. Pattern Recognition Letters, 2017.
  3. N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection”, in Proc. CVPR, 2005.
  4. M. Farhadi, S. A. Motamedi, and S. Sharifian, “Efficient human detection based on parallel implementation of gradient and texture feature extraction methods”, in Proc. IMVIP, 2011.
  5. N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in Proc. IEEE International Conference on Computer Vision and Pattern Recognition, Jun. 2005, pp. 886–893.
  6. Q. Zhu, S. Avidan, M. Yeh, and K. Cheng, “Fast human detection using a cascade of histograms of oriented gradients,” in Proc. IEEE International Conference on Computer Vision and Pattern Recognition, Jul. 2006, pp. 1491–1498.
  7. T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber, and T. Poggio, “Object recognition with cortex-like mechanisms,” in Proc. IEEE Transaction on Pattern Analyzing and Machine Intelligence, vol. 29, no. 3, pp. 411–426, Mar. 2007.
  8. Y. Mu, S. Yan, Y. Liu, T. Huang, and B. Zhou, “Discriminative local binary patterns for human detection in personal album,” in Proc. IEEE International Conference on Computer Vision and Pattern Recognition, Jun. 2008, pp. 1–8.
  9. P. Sabzmeydani and G. Mori, “Detecting pedestrians by learning shapelet features,” in Proc. IEEE International Conference on Computer Vision and Pattern Recognition, Jun. 2007, pp. 1–8.
  10. P. Viola, M. Jones, and D. Snow, “Detecting pedestrians using patterns of motion and appearance,” International Journal of Computer Vision, vol. 63, no. 2, pp. 153–161, 2005.
  11. Q. Ye, J. Jiao, and B. Zhang, “Fast pedestrian detection with multi-scale orientation features and two-stage classifiers,” in Proc. IEEE 17th International Conference on Image Processing, Sep. 2010, pp. 881–884.
  12. P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan, “Object detection with discriminatively trained part based models,” IEEE Transaction on Pattern Analyzing and Machine Intelligent, vol. 32, no. 9, pp. 1627–1645, Sep. 2010.
  13. X. Wang, T. X. Han, and S. Yan, “An HOG-LBP human detector with partial occlusion handling,” in Proc. IEEE International Conference Computer Vision, Oct. 2009, pp. 32–39.
  14. Q. Ye, Z. Han, J. Jiao, and J. Liu, “Human Detection in Images via Piecewise Linear Support Vector Machines,” in Proc. IEEE transactions on image processing, vol. 22, no. 2, February 2013.
  15. J. Stoble and S. Me, “Multi-posture human detection based on hybrid HOG-BO feature”, International Conference on Advances in Computing and Communications, 2015.
  16. R. B. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation”, in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
  17. Y. Jiang and J. Ma, “Combination Features and Models for Human Detection”, in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
  18. X. Ren and D. Ramanan, “Histograms of sparse codes for object detection”, in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.