Niki Martinel

Re-identify people in wide area camera network

Tracking individuals within a wide area camera network is a tough problem. Obtaining information across uncovered areas is an open issue that person re-identification methods deal with. A novel appearance-based method for person re-identification is proposed. The approach computes a novel discriminative signature by exploiting multiple local features. A novel signature distance measure is given by exploiting a body part division approach. The method has been compared to state-of-the-art methods using a re-identification benchmark dataset. A new dataset acquired from non-overlapping cameras has been built to validate the method against a real wide area camera network scenario. The method has proven to be robust against low resolution images, viewpoint and illumination changes, occlusions and pose variations. Results show that the proposed approach outperforms state-of-the-art methods used for comparison.

Re-Identification in the Function Space of Feature Warps

Person re-identification in a non-overlapping multicamera scenario is an open challenge in computer vision because of the large changes in appearances caused by variations in viewing angle, lighting, background clutter, and occlusion over multiple cameras. As a result of these variations, features describing the same person get transformed between cameras. To model the transformation of features, the feature space is nonlinearly warped to get the “warp functions”. The warp functions between two instances of the same target form the set of feasible warp functions while those between instances of different targets form the set of infeasible warp functions. In this work, we build upon the observation that feature transformations between cameras lie in a nonlinear function space of all possible feature transformations. The space consisting of all the feasible and infeasible warp functions is the warp function space (WFS). We propose to learn a discriminating surface separating these two sets of warp functions in the WFS and to re-identify persons by classifying a test warp function as feasible or infeasible. Towards this objective, a Random Forest (RF) classifier is employed which effectively chooses the warp function components according to their importance in separating the feasible and the infeasible warp functions in the WFS. Extensive experiments on five datasets are carried out to show the superior performance of the proposed approach over state-of-the-art person re-identification methods. We show that our approach outperforms all other methods when large illumination variations are considered. At the same time it has been shown that our method reaches the best average performance over multiple combinations of the datasets, thus, showing that our method is not designed only to address a specific challenge posed by a particular dataset.

Saliency Weighted Features for Person Re-identification

In this work we propose a novel person re-identification approach. The solution, inspired by human gazing capabilities, wants to identify the salient regions of a given person. Such regions are used as a weighting tool in the image feature extraction process. Then, such novel representation is combined with a set of other visual features in a pairwise-based multiple metric learning framework. Finally, the learned metrics are fused to get the distance between image pairs and to re-identify a person. The proposed method is evaluated on three different benchmark datasets and compared with best state-of-the-art approaches to show its overall superior performance.

Person Re-Identification Ranking Optimisation by Discriminant Context Information Analysis

Person re-identification is an open and challenging problem in computer vision. Existing re-identification approaches focus on optimal methods for features matching (e.g., metric learning approaches) or study the inter-camera transformations of such features. These methods hardly ever pay attention to the problem of visual ambiguities shared between the first ranks. In this paper, we focus on such a problem and introduce an unsupervised ranking optimization approach based on discriminant context information analysis. The proposed approach refines a given initial ranking by removing the visual ambiguities common to first ranks. This is achieved by analyzing their content and context information. Extensive experiments on three publicly available benchmark datasets and different baseline methods have been conducted. Results demonstrate a remarkable improvement in the first positions of the ranking. Regardless of the selected dataset, state-of-the-art methods are strongly outperformed by our method.

Camera Selection for Adaptive Human-Computer Interface

Video analytics has become a very important topic in computer vision. This paper introduces advanced video analytics human-computer interfaces for a video surveillance system to ease the tasks of security operators. The visualization of the most relevant views is provided by the human-computer interface module that preemptively activates cameras that will probably cover the motion of interesting objects. Human-computer interaction principles have been considered to develop the novel user interface. Four prototypes have been designed and usability performance has been evaluated, exploiting standard methods. Results obtained from such evaluations show the efficiency of the novel information visualization technique.

Temporal Model Adaptation for Person Re-identification

Person re-identification is an open and challenging problem in computer vision. Majority of the efforts have been spent either to design the best feature representation or to learn the optimal matching metric. Most approaches have neglected the problem of adapting the selected features or the learned model over time. To address such a problem, we propose a temporal model adaptation scheme with human in the loop. We first introduce a similarity-dissimilarity learning method which can be trained in an incremental fashion by means of a stochastic alternating directions methods of multipliers optimization procedure. Then, to achieve temporal adaptation with limited human effort, we exploit a graph-based approach to present the user only the most informative probe-gallery matches that should be used to update the model. Results on three datasets have shown that our approach performs on par or even better than state-of-the-art approaches while reducing the manual pairwise labeling effort by about \(80\,\%\).

Modeling feature distances by orientation driven classifiers for person re-identification

Display Omitted The person orientation is used to learn different inter-camera transformations.We propose a method to retrieve images of the person with different orientations.The pairwise feature dissimilarities space is used to create two regions according to the orientation.We train a binary classifier to capture the inter-camera transformation for each region. To tackle the re-identification challenges existing methods propose to directly match image features or to learn the transformation of features that undergoes between two cameras. Other methods learn optimal similarity measures. However, the performance of all these methods are strongly dependent from the person pose and orientation. We focus on this aspect and introduce three main contributions to the field: (i) to propose a method to extract multiple frames of the same person with different orientations in order to capture the complete person appearance; (ii) to learn the pairwise feature dissimilarities space (PFDS) formed by the subspaces of similar and different image pair orientations; and (iii) within each subspace, a classifier is trained to capture the multi-modal inter-camera transformation of pairwise image dissimilarities and to discriminate between positive and negative pairs. The experiments show the superior performance of the proposed approach with respect to state-of-the-art methods using two publicly available benchmark datasets.

Classification of Local Eigen-Dissimilarities for Person Re-Identification

The task of re-identifying a person that moves across cameras fields-of-view is a challenge to the community known as the person re-identification problem. State-of-the art approaches are either based on direct modeling and matching of the human appearance or on machine learning-based techniques. In this work we introduce a novel approach that studies densely localized image dissimilarities in a low dimensional space and uses those to re-identify between persons in a supervised classification framework. To achieve the goal: i) we compute the localized image dissimilarity between a pair of images; ii) we learn the lower dimensional space of such localized image dissimilarities, known as the “local eigen-dissimilarities” (LEDs) space; iii) we train a binary classifier to discriminate between LEDs computed for a positive pair (images are for a same person) from the ones computed for a negative pair (images are for different persons). We show the competitive performance of our approach on two publicly available benchmark datasets.

Sparse Matching of Random Patches for Person Re-Identification

Most of the open challenges in person re-identification are introduced by the large variations of human appearance and from the different camera views deployed to monitor the environment. To tackle these challenges, almost all state-of-the-art methods assume that all image pixels are equally relevant to the task, hence they are used in the feature extraction procedure. However, it is not guaranteed the a pixel sensed by one camera is viewed by a different one, so computing the person signature using such pixel might bring uninformative data in the feature matching phase. We believe that only some portions of the image are relevant to the re-identification task. Inspired by this, we introduce a novel algorithm that: (i) randomly samples a set of image patches to compute the person signature; (ii) uses the correlation matrix computed between such patches as a weighing tool in the signature matching process; (iii) brings sparsity in the correlation matrix so as only relevant patches are used in the matching phase. To validate the proposed approach, we have compared our performance to state-of-the-art methods using two publicly available benchmark datasets. Results show that superior performance to existing approaches are achieved.

Learning pairwise feature dissimilarities for person re-identification

This paper deals with person re-identification in a multi-camera scenario with non-overlapping fields of view. Signature based matching has been the dominant choice for state-of-the-art person re-identification across multiple non-overlapping cameras. In contrast we propose a novel approach that exploits pairwise dissimilarities between feature vectors to perform the re-identification in a supervised learning framework. To achieve the proposed objective we address the person re-identification problem as follows: i) we extract multiple features from two persons images and compare them using standard distance metrics. This gives rise to what we called distance feature vector; ii) we learn the set of positive and negative distance feature vectors and perform the re-identification by classifying the test distance feature vectors. We evaluate our approach on two publicly available benchmark datasets and we compare it with state-of-the-art methods for person re-identification.