Abstract-We present a conditional random field approach to tracking-by-detection in which we model pairwise factors linking pairs of detections and their hidden labels, as well as higher order potentials defined in terms of label costs. To the contrary of previous papers, our method considers long-term connectivity between pairs of detections and models similarities as well as dissimilarities between them, based on position, color, and as novelty, visual motion cues. We introduce a set of feature-specific confidence scores, which aim at weighting feature contributions according to their reliability. Pairwise potential parameters are then learned in an unsupervised way from detections or from tracklets. Label costs are defined so as to penalize the complexity of the labeling, based on prior knowledge about the scene like the location of entry/exit zones. Experiments on PETS'09, TUD, CAVIAR, Parking Lot, and Town Center public data sets show the validity of our approach, and similar or better performance than recent state-of-the-art algorithms.
Temporal clustering of human motion into semantically meaningful behaviors is a challenging task. While unsupervised methods do well to some extent, the obtained clusters often lack a semantic interpretation. In this paper, we propose to learn what makes a sequence of human poses different from others such that it should be annotated as an action. To this end, we formulate the problem as weakly supervised temporal clustering for an unknown number of clusters. Weak supervision is attained by learning a metric from the implicit semantic distances derived from already annotated databases. Such a metric contains some low-level semantic information that can be used to effectively segment a human motion sequence into distinct actions or behaviors. The main advantage of our approach is that metrics can be successfully used across datasets, making our method a compelling alternative to unsupervised methods. Experiments on publicly available mocap datasets show the effectiveness of our approach.
Abstract-A method to obtain accurate hand gesture classification and fingertip localization from depth images is proposed. The Oriented Radial Distribution feature is utilized, exploiting its ability to globally describe hand poses, but also to locally detect likely fingertip positions. Hence, hand gesture and fingertip locations are characterized with a single feature calculation. We propose to divide the difficult problem of locating fingertips into two more tractable problems, taking advantage of hand gesture as an auxiliary variable. Besides, the ColorTip dataset is proposed, a dataset for hand gesture recognition and fingertip classification on depth data. ColorTip allows automatic fingertip annotation through a wieldy and not costly footage. The proposed method is evaluated against recent works and datasets, achieving promising results in both gesture classification and fingertip localization.
We present a novel method for upper body pose estimation with online initialization of pose and the anthropometric profile. Our method is based on a Hierarchical Particle\ud
Filter that defines its likelihood function with a single view depth map provided by a range sensor. We use Connected Operators on range data to detect hand and head candidates\ud
that are used to enrich the Particle filter’s proposal distribution, but also to perform an automated initialization\ud
of the pose and the anthropometric profile estimation. A GPU based implementation of the likelihood evaluation yields real-time performance. Experimental validation of\ud
the proposed algorithm and the real-time implementation are provided, as well as a comparison with the recently released\ud
OpenNI tracker for the Kinect sensor.Peer ReviewedPostprint (published version
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.