Description

ABSTRACT

Matching people across multiple camera views known as person re-identification, is a challenging problem due to the change in visual appearance caused by varying lighting conditions. The perceived color of the subject appears to be different with respect to illumination. Previous works use color as it is or address these challenges by designing color spaces focusing on a specific cue. In this paper, we propose a data driven approach for learning color patterns from pixels sampled from images across two camera views. The intuition behind this work is that, even though pixel values of same color would be different across views, they should be encoded with the same values. We model color feature generation as a learning problem by jointly learning a linear transformation and a dictionary to encode pixel values. We also analyze different photometric invariant color spaces. Using color as the only cue, we compare our approach with all the photometric invariant color spaces and show superior performance over all of them. Combining with other learned low-level and high-level features. 

EXISTING METHOD

• Diagonal matrix transform(DMT)
• Brightness transform function(BTF)

DRAWBACKS OF EXISTING TECHNIQUE

• By BFT pixel level correspondence cannot be achieved
• Scale Invariant Transforms

PROPOSED METHOD

• Training patch collection tracking based
• Multi-view analysis extraction

BLOCK DIAGRAM

ADVANTAGES OF PROPOSED METHOD

• Greater performance Ratio.
• No handcrafted feature can be considered as universal, learning relations from data can be advantageous
• Modeling complex distributions and functions have been a bottleneck in machine learning 

SOFTWARE REQUIREMENTS

• Python
• Opencv
• Numpy 

APPLICATION

• Objective dectection Application
• Person identification Application

RESULT

This system will be majorly used in the field of video surveillance to identify the person in one video and to re-identify the same person in the other video.

REFERNCES

[1] Bedagkar Gala, A., Shah, S.K.: ‘A survey of approaches and trends in person reidentification’, Image Vis. Comput., 2014, 32, (4), pp. 270 286

[2] Gray, D., Tao, H.: ‘Viewpoint invariant pedestrian recognition with an ensemble of localized features’. European Conf. Computer Vision (ECCV

2008), 2008, pp. 262–275

[3] Farenzena, M., Bazzani, L., Perina, A., et al.: ‘Person reidentification by symmetry-driven accumulation of local features’. 2010 IEEE Conf. Computer Vision and Pattern Recognition (CVPR 2010), 2010, pp. 2360–2367

[4] Hirzer, M., Roth, P.M., Bischof, H.: ‘Person re-identification by efficient impostor-based metric learning’. 2012 IEEE Ninth Int. Conf. Advanced Video and Signal-Based Surveillance (AVSS), 2012, pp. 203–208

[5] Ma, B., Su, Y., Jurie, F.: ‘Covariance descriptor based on bio-inspired features for person re-identification and face verification’, Image Vis. Comput., 2014, 32, (6), pp. 379–390

[6] Satta, R., Fumera, G., Roli, F.: ‘Fast person re-identification based on dissimilarity representations’, Pattern Recognit. Lett., 2012, 33, (14), pp.

1838–1848

[7] Dutra, C.R., Schwartz, W.R., Souza, T., et al.: ‘Re-identifying people based on indexing structure and manifold appearance modeling’. IEEE 26^th SIBGRAPI – Brazilian Symp. Computer Graphics and Image Processing

(SIBGRAPI 2013), 2013, pp. 218–225

[8] Khedher, M.I., El Yacoubi, M.A.: ‘Two-stage filtering scheme for sparse representation based interest point matching for person re-identification’. Advanced Concepts for Intelligent Vision Systems, 2015, pp. 345–356

[9] Satta, R., Fumera, G., Roli, F., et al.: ‘A multiple component matching framework for person re-identification’. Image Analysis and Processing

(ICIAP 2011), 2011, pp. 140–149

[10] Liao, S., Hu, Y., Zhu, X., et al.: ‘Person re-identification by local maximal occurrence representation and metric learning’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2015, pp. 2197–2206