With the evolution of video surveillance systems, the requirement of video storage grows rapidly; in addition, safe guards and forensic officers spend a great deal of time observing surveillance videos to find abnormal events. As most of the scene in the surveillance video are redundant and contains no information needs attention, we propose a video condensation method to summarize the abnormal events in the video by rearranging the moving trajectory and sort them by the degree of anomaly. Our goal is to improve the condensation rate to reduce more storage size, and increase the accuracy in abnormal detection. As the trajectory feature is the key to both goals, in this paper, a new method for feature extraction of moving object trajectory is proposed, and we use the SOINN (Self-Organizing Incremental Neural Network) method to accomplish a high accuracy abnormal detection. In the results, our method is able to shirk the video size to 10% storage size of the original video, and achieves 95% accuracy of abnormal event detection, which shows our method is useful and applicable to the surveillance industry. 相似文献
Journal of Porous Materials - In recent years, oil spills and industrial organic pollutants have caused irreparable damage to the environment and biological ecosystems. Therefore, the treatment of... 相似文献
An integrated model of ultrasonic vibration enhanced friction stir welding (UVeFSW) is developed by integrating the thermal-fluid model with the ultrasonic field model and tool torque model. The tool torque and the heat generation rate at tool/workpiece contact interfaces are coupled with the interfacial temperature, strain rate and ultrasonic energy density. The model is used in quantitatively analysing the effects of ultrasonic vibration on tool torque and thermal processes in friction stir welding (FSW). The results show that ultrasonic vibration reduces the flow stress, which results in a decreasing of tool torque, interfacial heat generation rate and interfacial temperature. The complicated interaction of ultrasonic energy with the thermal processes in FSW leads to a gentle thermal gradient and an enhanced plastic material flow in UVeFSW. The model is validated by a comparison of the calculated thermal cycles and tool torque at various welding parameters with the experimentally measured ones. 相似文献
Overland flow is an important hydrological response of catchments to rainstorms and contributes to soil erosion and nutrient loss. The kinematic wave model is known to describe the transformation of rainfall to overland flow. Through this, field studies were conducted on a hillslope to simulate water scouring from upstream with a complex surface condition, which was covered with different sizes and percentages of stones. Existing semi-analytical and numerical models were adopted to describe the overland flow in the field. Results indicate that both semi-analytical and numerical models could be applied to describe the process of overland flow. Furthermore, predicted outflow rates by the semi-analytical and the numerical model showed strong correlation with the field measured outflow rates, respectively (NS?=?(0.926, 0.942, 0.992), RE?=?(5.5%, 4.7%, 1.7%) for the semi-analytical model, and NS?=?(0.817, 0.952, 0.992), RE?=?(5.5%, 5.5%, 2.1%) for the numerical model). Besides, hydraulic parameters (Reynolds number-Re, Froude numbers-Fr, Darcy-Weisbach-f, hydraulic shear stress-τ, stream power-ω, water wave celerity-vw) at any time and distance could be described by the semi-analytical method, and the parameter n/h (an important factor indicating the energy of water and wave flow celerity) could successfully characterize the average hydraulic parameters, and all of the hydraulic parameters are fitted to the expression of y?=?a(n/h)b.