Recent development of per-frame motion extraction method can generate the skeleton of human motion in real-time with the help of RGB-D cameras such as Kinect. This leads to an economic device to provide human motion as input for real-time applications. As generated by a single-view image plus depth information, the extracted skeleton usually has problems of unwanted vibration, bone-length variation, self-occlusion, etc. This paper presents an approach to overcome these problems by synthesizing the skeletons generated by duplex Kinects, which capture the human motion in different views. The major technical difficulty of this synthesis comes from the inconsistency of two skeletons. Our algorithm is formulated under the constrained optimization framework by using the bone-lengths as hard constraints and the tradeoff between inconsistent joint positions as soft constraints. Schemes are developed to detect and re-position the problematic joints generated by per-frame method from duplex Kinects. As a result, we develop an easy, cheap and fast approach that can improve the skeleton of human motion at an average speed of 5 ms per frame.
This paper is the second part of our study on designing a new type of metal forming press. In the first part of the study (Du, R., and Guo, W. Z., 2003, ASME J. Mech. Des., 125(3), pp. 582–592), a new controllable mechanical press is introduced that consists of a large constant-speed motor (CSM) and a small variable-speed servomotor (VSM). The CSM provides up to 80% of the power while the VSM tunes the motion of the ram. This new design has a number of advantages: it is flexible (i.e., its ram motion is programable), fast (its speed is limited only by the mechanical motion), and energy efficient (the CSM can use a large flywheel to ease the large instantaneous metal forming force). This paper focuses on the motion control and experiment validation. First, the inverse kinematics is presented, which gives the relationship between the ram travel and (i) the input angular displacements, velocities, and accelerations of the two motors. Next, a trajectory-planning method is given. Then, the sensitivity analysis is carried out, which helps to determine the key dimensions of the press and the error compensation scheme. Finally, two experiments are shown to demonstrate that the new press can accomplish different tasks.
In this study, we applied the edge-detection method of oil-spill monitoring to extract oil-spill features observed by the ENVISAT Advanced Synthetic Aperture Radar (ASAR) images over the coastal waters of Hong Kong and vicinity in northern South China Sea. Two examples in 2007 and 2008 over the coastal waters of the study area show that oil spills can be successfully detected by ASAR images at wind speeds around 4∼6 m/s independent of wind direction. The study also shows that it could be helpful for evaluating the potential impacts of oil spills on the coastal environment in Hong Kong and vicinity.
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.