In order to perform cutting-edge research like AI model training, a large amount of data needs to be accessed. However, data providers are often reluctant to share their data with researchers as these might contain personal data and thereby sharing may introduce serious risks with significant personal, institutional or societal impacts. Apart from the need to control these risks, data providers must also comply with regulations like GDPR, which creates an additional overhead that makes data sharing even less appealing to data providers. Technologies like anonymization can play a critical role when sharing data that may contain personal information by offering privacy preservation measures like face or license plate anonymization. Therefore, we propose a framework to support data sharing of personal data for research by integrating anonymization, risk assessment and automatic licence agreement generation. The framework offers a practical and efficient solution for organisations seeking to enhance data-sharing practices without compromising information security.

Recent online multi-object tracking approaches combine single object trackers and affinity networks with the aim of capturing object motions and associating objects by using their appearance, respectively. Those affinity networks often build on complex feature representations (re-ID embeddings) or sophisticated scoring functions, whose objective is to match current detections with previous tracklets, known as short-term appearance information. However, drastic appearance changes during the object trajectory acquired by omnidirectional cameras causes a degradation of the performance since affinity networks ignore the variation of the long-term appearance information. In this paper, we deal with the appearance changes in a coherent way by proposing a novel affinity model which is able to predict the new visual appearance of an object by considering the long-term appearance information. Our affinity model includes a convolutional LSTM encoder-decoder architecture to learn the space-time appearance transformation metric between consecutive re-ID feature representations along the object trajectory. Experimental results show that it achieves promising performance on several multi-object tracking datasets containing omnidirectional cameras.

Existing approaches for person re-identification are mainly based on creating distinctive representations or on learning optimal metrics. The achieved results are then provided in the form of a list of ranked matching persons. It often happens that the true match is not ranked first but it is in the first positions. This is mostly due to the visual ambiguities shared between the true match and other "similar" persons. At the current state, there is a lack of a study of such visual ambiguities which limit the re-identification performance within the first ranks. We believe that an analysis of the similar appearances of the first ranks can be helpful in detecting, hence removing, such visual ambiguities. We propose to achieve such a goal by introducing an unsupervised post-ranking framework. Once the initial ranking is available, content and context sets are extracted. Then, these are exploited to remove the visual ambiguities and to obtain the discriminant feature space which is finally exploited to compute the new ranking. An in-depth analysis of the performance achieved on three public benchmark data sets support our believes. For every data set, the proposed method remarkably improves the first ranks results and outperforms the state-of-the-art approaches.

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.

Most of the open challenges in person re-identification arise from the large variations of human appearance and from the different camera views that may be involved, making pure feature matching an unreliable solution. To tackle these challenges state-of-the-art methods assume that a unique inter-camera transformation of features undergoes between two cameras. However, the combination of view points, scene illumination and photometric settings, etc., together with the appearance, pose and orientation of a person make the inter-camera transformation of features multi-modal. To address these challenges we introduce three main contributions. We propose a method to extract multiple frames of the same person with different orientation. We learn the pair wise feature dissimilarities space (PFDS) formed by the subspace of pair wise feature dissimilarities computed between images of persons with similar orientation and the subspace of pair wise feature dissimilarities computed between images of persons non-similar orientations. Finally, a classifier is trained to capture the multi-modal inter-camera transformation of pair wise images for each subspace. To validate the proposed approach we show the superior performance of our approach to state-of-the-art methods using two publicly available benchmark datasets.

People reidentification is one of the most challenging tasks in computer vision, and considerable efforts have been directed toward providing solutions to this problem. The existence of extensive camera networks and surveillance systems increases the amount of people images obtained, but, on the other hand, implies the need for new algorithms to enable reidentification of people captured by the cameras. There is no one optimal model that solves the entire problem, but a set of distinctive features can be used to help in the matching process. Our proposal consists of using the orientation of each person captured in the surveillance scene to considerably improve the reidentification process. An iterative algorithm maximizes the number of successful matches and speeds up the process. A comparison with other earlier relevant studies is presented using available datasets.

People counting systems are widely used in surveillance applications. In this paper, we present a solution to bidirectional people counting based on information provided by an overhead stereo system. Four fundamental aspects can be identified: the detection and tracking of human motion using an extended particle filter, the use of 3-D measurements in order to increase the system's robustness and a modified K-means algorithm to provide the number of hypotheses at each time, and, finally, trajectory generation to facilitate people counting in different directions. The proposed algorithm is designed to solve problems of occlusion, without counting objects such as shopping trolleys or bags. A processing ratio of around 30 frames/s is necessary in order to capture the real-time trajectory of people and obtain robust tracking results. We validated various test videos, achieving a hit rate between 95% and 99%, depending on the number of people crossing the counting area.