Learn More
For many human-robot interaction applications, accurate localization of the human, and in particular the endpoints such as the head, hands and feet, is crucial. In this paper, we propose a new Local Shape Context Descriptor specifically for describing the shape features of the endpoint body parts. The descriptor is computed from edge images obtained from(More)
Wireless sensor and actuator networks (WSAN) are increasingly popular due to their abilities to detect and react to interesting events in the physical world. In this paper, a new indoor WSAN system in the context of pursuit evasion games (PEGs) is designed and implemented. Our goal is to take advantage of the WSAN capabilities to perform target tracking and(More)
In this paper, we propose a marker-less full body human motion capture system designed for humanoid robot applications. The system is based on a stereo camera, and therefore has strong portability. Tracking is implemented within the particle filter framework, and the high dimensionality problem is solved through partitioned sampling. Taking advantage of the(More)
This paper proposes a particle filter based marker-less upper body motion capture system, capable of running in realtime. This system is designed for a humanoid robot application, and thus a monocular image sequence is used as input. We first set up a model of the human body, a sub-model which includes 11 Degrees of Freedom is used for the upper body(More)
Recovery of human pose from videos has become a highly active research area in the last decade because of many attractive potential applications, such as surveillance, nonintrusive motion analysis and natural human machine interaction. Video based full body pose estimation is a very challenging task, because of the high degree of articulation of the human(More)
Choosing the kernel and error penalty parameters for Support Vector Machine (SVM) is very important for the performance of classifiers. An improved grid-search algorithm is proposed to choose the optimal parameters of SVM. The battlefield multi-target SVM classifier is designed using this algorithm. Also three classifiers including K-nearest neighborhood(More)
Indoor positioning has wide prospects in emergency positioning, public safety, and exhibition services and has become a research focus. This paper presents a 2D indoor positioning system based on Wi-Fi and TDOA on USRP platform. Meanwhile, the sending and receiving of Wi-Fi signal are implemented for measurement and the algorithm of frequency offset(More)
  • 1