People silhouette extraction from people detection bounding boxes in images

Abstract

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.

Polygonized Silhouettes and Polygon Coding Based Feature Representation for Human Action Recognition

“…The polygonization step is adaptive and works completely onthe-fly for each binary image. One of the novelties of this study is that; instead of using conventional methods such as the difference between video images and background subtraction techniques to determine the silhouette [44], [45], [46], [47], a deep learning architecture, Yolact++, is modified, and the image information obtained from the middleware is used. This step exploits the power of the architecture to represent the silhouette as a whole with greater accuracy than that of conventional methods.…”

“…On the other hand, motionbased feature extraction methods focus on extracting information related to the motion of objects or people in the video and these methods extract features that describe the temporal changes in the position, velocity, and acceleration of body parts in the video [5], [6], [7], [8], [9]. They are also well-suited for recognizing actions that involve significant motion, such as waving, punching, and kicking [44], [51], [52], [53], [54], [55], [56], [57].…”

Estimation of left behind subway passengers through archived data and video image processing

“…Finally, the bounding boxes are refined by the elimination of duplicate detections and rescoring the boxes based on other objects on the scene using SVMs ( Girshick et al, 2014 ). The bounding box is a rectangular box located around the objects in order to represent their detection ( Coniglio et al, 2017 , Lézoray and Grady, 2012 ). The resulting object detection datasets are images with tags used to classify different categories ( Deng et al, 2009 , Everingham et al, 2010 ).…”

People Detection and Pose Classification Inside a Moving Train Using Computer Vision

“…Truong Cong et al [14,15] report a foreground estimation and person re-identification approach, but it is not clear how it can deal with stationary people, nor they consider different postures. More recently Coniglio et al [16] present an interesting approach based on shape priors, HOG and multiple SVMs but it is not clear how they deal with different poses.…”