No abstract

This study introduces a totally unsupervised method for the detection and location of dense crowds in images without context-awareness. With the perspective of setting up fully autonomous video-surveillance systems, automatic detection and location of crowds is a crucial step that is going to point which areas of the image have to be analyzed. After retrieving multiscale texturerelated feature vectors from the image, a binary classification is conducted to determine which parts of the image belong to the crowd and which to the background. The algorithm presented can be operated on images without any prior knowledge of any kind and is totally unsupervised.

In this paper, we propose a pedestrian attribute recognition approach and a CNN-based person re-identification framework enhanced by pedestrian attributes. The knowledge of person attributes can help video surveillance tasks like person re-identification as well as person search, semantic video indexing and retrieval to overcome viewpoint changes with their robustness to the inherent visual appearance variations. Compared to previous approaches, our attribute recognition method using Local Maximal Occurrence (LOMO) features and a Multi-Label Multi-Layer Perceptron (MLMLP) classifier proves to be more robust to different view points and is computationally more efficient. The experiments on three public benchmarks show that the proposed method improves the state-of-the art on attribute recognition. Furthermore, we integrate our attribute recognition algorithm into a triplet CNN similarity learning framework for person re-identification fusing both learned CNN features and attributes. This fusion leads to an overall improvement, and we achieve state-of-the-art results on person re-identification.

In video surveillance, pedestrian attributes are defined as semantic descriptors like gender, clothing or accessories. In this paper, we propose a CNN-based pedestrian attribute-assisted person re-identification framework. First we perform the attribute learning by a part-specific CNN to model attribute patterns related to different body parts and fuse them with low-level robust Local Maximal Occurrence (LOMO) features to address the problem of the large variation of visual appearance and location of attributes due to different body poses and camera views. Our experiments on three public benchmarks show that the proposed method improves the state of the art on attribute recognition. Then we merge the learned attribute CNN embedding with another identification CNN embedding in a triplet structure to perform the person re-identification task.Both CNNs are pre-trained in a supervised way on attributes and person identities respectively, and then continue the training with a combined architecture for re-identification. We experimentally show that this fusion of "identity and attributes features" improves the overall re-identification.

Exemple d’une maison médiévale à Roissy-en-France, dotée d’un appentis à usage de porcherie, qui rappelle la proximité de l’humain avec le porc jusqu’au développement de l’hygiène à la fin du XIXe-début du XXe siècle.