Pedestrian re-identification is a valuable problem that has enormous potential for practical applications like criminals monitoring and investigation,lost children search in the public area,personal photo album management,e-business,to name a few.Meanwhile,it is also very challenging since the appearance of the same person between camera views changes dramatically caused by illumination,viewpoint,pose,and background variations.Given a certain pedestrian feature space,because of the different discriminative ability of different feature components, learning a proper similarity is important for pedestrian re-identification.A dominant algorithm to learn a similarity is the metric learning that learns a Mahalanobis Similarity Function (MSF)to estimate the similarity of a pair of pedestrians.However,because MSF only projects a pair of pedestrians into the feature difference space and ignores the appearance of each individual,it is inadequate for modeling complex relationships of appearance variations from different cameras.In this paper,we propose to learn a Quadratic Similarity Function (QSF)that greatly strengthens the modeling ability of the similarity function.QSF is a generalization of MSF,and it not only represents the cross correlation relationship of a pair of pedestrians,but also describes the auto correlation relationship.So QSF is better to tackle large appearance variations of the same pedestrians than MSF.To learn a QSF,inspired from the classification perspective and the ranking perspective,we design two algorithms with different optimizing object functions.Experiments on the VIPeR dataset and the CUHK campus dataset show that both algorithms are effective to learn a QSF and their performance outperforms the previous algorithms.

In recent years, e-commerce has become an important way people shop. Among this, clothes and bags are extraordinarily important for customers. However, traditional online shopping modes only allow users to search with key words. Sometimes users may find it very hard to precisely describe what they want in words. Moreover, even if a user gives a detailed description, it may not agree with the description provided by the seller. Therefore, search-by-image without the help of semantic descriptions becomes a research focus in computer vision and multi-media processing. In this paper, we address the problem of object detection and retrieval and focus particularly on bags in street shots. First, we locate the bag region in an image by Pairwise Context based Convolutional Neural Network (PC-CNN). After that, we learn high-level descriptions of bag images based on attributes and build a retrieval system allowing for image search. We test our approach on the publicly available Fashionista Benchmark (FB) and a Pedestrian with Bags dataset (PB) collected by ourselves to demonstrate the effectiveness of the proposed method.

Bag detection in pedestrian images is a very practical visual surveillance problem. It is challenging because bag appearance may vary greatly. In this paper, we propose a novel two-stage approach for bag detection in pedestrian images. Firstly, we utilize two stripe vocabulary forests to check whether a pedestrian is with a bag. Secondly, we locate the bag location by ranking the generated bottom-up region proposals. The ranker is learned with a convolutional neural network (CNN). Experiments are performed on a subset of CUHK person re-identification dataset that show the effectiveness of our approach for bag detection in pedestrian images. Although developed for a specific problem, our approach could be applied to detect other carrying objects in pedestrian images.

Clothing attributes, of which color plays an important role, are receiving more and more interests in machine vision researches and applications because of their uses and effectiveness in tasks like pedestrian analysis. However, color description is a challenging problem due to complex environments such as illumination variations. Most prior works describe color attributes using only low-level features or mid-level descriptors, which results in a marked drop of the discriminative power or photometric invariance. In this paper we introduce a new efficient joint representation that aims to overcome the shortcomings of using low-level features or mid-level descriptors alone and present a novel hybrid approach to pedestrian clothing color attribute extraction. As a necessary preprocessing step, a novel processing pipeline is also proposed. We evaluate our approach on the task of color classification on both the public dataset VIPeR and our own newly-built pedestrian dataset. Experimental results have demonstrated the effectiveness of our approach and have shown its great potential for further researches and applications.

Person re-identification, identifying the same person’s images in an existing database come from non-overlapping camera views, is a valuable but challenging task. This paper proposes a statistical inference approach for person re-identification. A similarity measure of two person images is learned from a statistical inference perspective. Then the similarity measure is utilized to query a person from a gallery set. The proposed approach is demonstrated on VIPeR dataset, and the experiment shows that it outperforms the state-of-the-art approaches. Besides, it costs less time than the existing learning-based ones in training, and alleviates the over-fitting problem when there are few training data.

Person re-identification is an important problem in visual surveillance where appearance plays a key role. Color is one of the widely used appearance features and utilizing more color spaces doesn't imply benefit of performance enhancement. That's because the poor performance color spaces influence on the high ones. So it is significant to evaluate the performance of different color spaces for person re-identification. In this paper, we propose a novel approach, called as random ensemble of color features (RECF), where we build a random forest to learn the similarity function of pairs of person images using color features from 6 kinds of popular color spaces (RGB, normalized RGB (NRGB), HSV, YCbCr, CIE XYZ and CIE Lab). We carry out experiments on the challenging dataset VIPeR to show the performances of different color spaces and their combination. We find out that the combination of NRGB, HSV, YCbCr and CIE Lab color spaces achieves the best performance, and our approach alleviates the over-fitting problem when there are limited training data.

Text detection in natural scenes is fundamental for text image analysis. In this paper, we propose a context-based approach for robust and fast text detection. Our main contribution is that we introduce a new concept of key region, which is described with context according to stroke properties, appearance consistency and specific spatial distribution of text line. With such context descriptors, we adopt SVM to learn a context-based classifier to find key regions in candidate regions. Therein, candidate regions are connected components generated by local binarization algorithm in the areas, which are detected by an offline learned text patch detector. Experimental results on two benchmark datasets demonstrate that our approach has achieved competitive performances compared with the state-of-the-art algorithms including the stroke width transform (SWT) [1] and the hybrid approach based on CRFs [2] with speedup rates of about 1.7x~4.4x.

In this paper, we propose a method for dot text detection based on FAST points. This problem is different from general scene text detection because of discontinuous text stroke. Unlike many other methods which assume that text is horizontally oriented, our method is able to deal with slant dot text. We extract interesting patches from FAST points and define four features based on the stroke and gray value similarity of dot text to describe a patch. Then, we generate some candidate regions from these patches and utilize SVM to filter out non-dot text ones with the first and second order moments of FAST points in them. Experimental results show that the proposed method is effective and fast to detect dot text.