Accidental falls of elderly people are a major cause of fatal injuries, especially for those living alone. We present a novel vision-based fall detection approach that analyzes an extracted human body using described human postures. First, a human body extracted by a background subtraction technique is located by a minimum area-enclosing ellipse. Then, a normalized directional histogram is developed around the center of the ellipse to represent a human posture by multidirectional statistical analysis. After that, 12 static and 8 dynamic features are derived from the normalized directional histogram. These features are fed into a directed acyclic graph support vector machine to distinguish four closely related human postures (standing, crouching, lying, and sitting). A fall-like accident is detected by counting the occurrences of lying postures in a short temporal window. After conducting majority voting, a fall event is determined by immobility verification. From the experimental results, an overall accuracy of 97.1% is obtained for recognition of the four postures, and only 1.0% of postures are misclassified as lying postures. Our fall detection system achieves up to 95.2% fall detection accuracy on a public fall dataset.

Airflow structures within convective systems are important predictors of damaging convective disasters. To automatically recognize different kinds of airflow structures (the convergence, divergence, cyclonic rotation, and anticyclonic rotation) within convective systems, an airflow structure recognition method is proposed, in this paper, based on a regular hexagonal template. On the basis of single Doppler radar data, the template is designed according to the appearance model of airflows in radial velocity maps. The proposed method is able to output types and intensities of airflow structures within convective systems. In addition, the outputs of the proposed method are integrated into a projection map of the airflow field structure types and intensities (PMAFSTI), which is developed in this work to visualize three-dimensional airflow structures within convective cells. The proposed airflow structure automatic recognition method and the PMAFSTI were tested using three typical cases. Results of the tests suggest the following: (1) At different evolution stages of the convective systems, e.g., growth, split, and dissipation, the three-dimensional distribution of the airflow fields within convective systems could be clearly observed through the PMAFSTI and (2) on the basis of recognizing the structures of the airflow field, the complex airflow field, such as a squall line, could be further divided into several small parts making the analysis of convective systems more scientific and elaborate.

No abstract

No abstract

No abstract