Deep Part Features Learning by a Normalised Double-Margin-Based Contrastive Loss Function for Person Re-Identification

The selection of discriminative features that properly define a person appearance is one of the current challenges for person re-identification. This paper presents a three-dimensional representation to compare person images, which is based on the similarity, independently measured for the head, upper body, and legs from two images. Three deep Siamese neural networks have been implemented to automatically find salient features for each body part. One of the main problems in the learning of features for re-identification is the presence of intra-class variations and inter-class ambiguities. This paper proposes a novel normalized doublemargin-based contrastive loss function for the training of Siamese networks, which not only improves the robustness of the learned features against the mentioned problems but also reduce the training time. A comparative evaluation over the challenging PRID 2011 dataset has been conducted, resulting in a remarkable enhancement of the single-shot re-identification performance thanks to the use of our descriptor based on deeply learned features in comparison with the employment of low-level features. The obtained results also show the improvements generated by our normalized double-margin-based function with respect to the traditional contrastive loss function.

[1]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[2]  Horst Bischof,et al.  Relaxed Pairwise Learned Metric for Person Re-identification , 2012, ECCV.

[3]  Department of Electrical,et al.  Computational and Performance Aspects of PCA-Based Face-Recognition Algorithms , 2001, Perception.

[4]  Ying Zhang,et al.  Gabor-LBP Based Region Covariance Descriptor for Person Re-identification , 2011, 2011 Sixth International Conference on Image and Graphics.

[5]  Shengcai Liao,et al.  Deep Metric Learning for Person Re-identification , 2014, 2014 22nd International Conference on Pattern Recognition.

[6]  Slawomir Bak,et al.  Person Re-identification Using Spatial Covariance Regions of Human Body Parts , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[7]  Alessandro Perina,et al.  Person re-identification by symmetry-driven accumulation of local features , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Mubarak Shah,et al.  Human identity recognition in aerial images , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[11]  Bingpeng Ma,et al.  Discriminative Image Descriptors for Person Re-identification , 2014, Person Re-Identification.

[12]  Vittorio Murino,et al.  Symmetry-driven accumulation of local features for human characterization and re-identification , 2013, Comput. Vis. Image Underst..

[13]  Horst Bischof,et al.  Person Re-identification by Descriptive and Discriminative Classification , 2011, SCIA.

[14]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[15]  Thomas Mensink,et al.  Image Classification with the Fisher Vector: Theory and Practice , 2013, International Journal of Computer Vision.

[16]  Shaogang Gong,et al.  Attributes-Based Re-identification , 2014, Person Re-Identification.

[17]  Vittorio Murino,et al.  SDALF: Modeling Human Appearance with Symmetry-Driven Accumulation of Local Features , 2014, Person Re-Identification.