Abstract. In this paper, we present an approach for the segmentation of people silhouettes in images. Since in real-world images estimating pixel probabilities to belong to people or background is difficult, we propose to optimally combine several ones. A local window classifier based on SVMs with Histograms of Oriented Gradients features estimates probabilities from pixels' appearance. A shape template prior is also computed over a set of training images. From these two probability maps, color distributions relying on color histograms and Gaussian Mixture Models are estimated and the associated probability maps are derived. All these probability maps are optimally combined into a single one with weighting coefficients determined by a genetic algorithm. This final probability map is used within a graph-cut to extract accurately the silhouette. Experimental results are provided on both the INRIA Static Person Dataset and BOSS European project and show the benefit of the approach.

In many applications such as video surveillance or autonomous vehicles, people detection is a key element, often based on feature extraction and combined with supervised classification. Usually, output of these methods is in the form of a bounding-box containing an extracted people along with the background. But in specific application contexts, this bounding box information is not sufficient and a precise segmentation of people silhouette is needed inside the bounding box. For videos, this is actually solved by using background subtraction strategies. However, this cannot be considered for the case of still images that also occur in many video surveillance applications. To that aim, we propose to consider that issue in this paper. The principle is to devise a complete scheme for people segmentation inside people detection bounding boxes. Such a scheme relies on several steps: pre-processing, feature extraction and probability map computation to approximately locate people silhouette, and graph cut clustering to refine the silhouette from the map prior. Since many different methods can be considered, along with their associated parameters, tuning, we use a systematic approach towards determining the best combination scheme to conceive a segmentation scheme. The F-measure is used as a benchmark for evaluation. Experimental results show the benefit of the proposed approach that goes beyond the actual state-of-the-art.

In this paper, we present a new method for people extraction in complex transport environments. Many background subtraction methods exist in the literature but don't give satisfactory results on complex images acquired in moving trains that include several locks such as fast brightness changes, noise, shadow, scrolling background, etc. To tackle this problem, a new method for people extraction in images is proposed. It is based on an image superpixel segmentation coupled with graph cuts binary clustering, initialized by a stateof-the-art foreground detection method. The proposed strategy is composed of four blocks. A pre-processing block that uses filters and colorimetric invariants to limit the presence of artifacts in images. A foreground detection block that enables to locate moving people in images. A post-treatment block that removes shadow regions of no-interest. A people extraction block that segments the image into SLIC superpixels and performs a graph cut binary clustering to precisely extract people. Tests are realized on a real database of the BOSS European project and are evaluated with the standard Fmeasure criteria. Since many state-of-the-art methods can be considered in our three first blocks along with many associated parameters, a genetic algorithm is used to automatically find the best methods and parameters of the proposed approach.

No abstract