According to the application scenarios of the size of the humanflow in different consumption places,to solve the problem of crowd detection,distance estimation between crowds and the inability to monitor and calculate ...According to the application scenarios of the size of the humanflow in different consumption places,to solve the problem of crowd detection,distance estimation between crowds and the inability to monitor and calculate the humanflow in real time,this paper designs a real-time crowd detection scheme for appli-cation scenarios where consumers pay attention to the size of the humanflow in consumption places.The main use of the YOLO algorithm with the Darknet53 net-work as the main network is to separate pedestrians from the background.Pedes-trians’central two-dimensional coordinates are converted into three-dimensional coordinates,realizing crowd detection and apart from the distance estimation of crowds,real-time monitoring of current regional traffic andflow density,and solv-ing the problem of being unable to monitor and calculate people in real time.It can be applied to many aspects,such as shop rating,traffic control andflow control of scenic spots.Existing monitors are affected by different lights and cannot provide accurate data.In addition,the processing algorithm of this scheme is stable and accurate,and preprocessing is performed before judging the humanflow and the position of the human body to reduce the interference of light.This scheme has the performance of real-time monitoring and calculation through experimental verification.展开更多
This paper described an improved underwater confrontation simulation method of naval amphibious operational training system. The initial position of submarine forces on the enemy is generated automatically, and the at...This paper described an improved underwater confrontation simulation method of naval amphibious operational training system. The initial position of submarine forces on the enemy is generated automatically, and the attacking distance model of torpedoes is established based on the kinematics theory, which is more flexible and reasonable to judge the launch condition compared to traditional method. The two kinds of confrontation behavior models on the enemy submarine are created to depict its tactical action from the defensive to the offensive as well as the contrary, ensuring that operational style is simulated more comprehensively and properly. The existing motion trajectory estimation and collision detection algorithms on operational platforms are also improved to reduce the iteration error and further enhance the detection accuracy of target hit.展开更多
文摘According to the application scenarios of the size of the humanflow in different consumption places,to solve the problem of crowd detection,distance estimation between crowds and the inability to monitor and calculate the humanflow in real time,this paper designs a real-time crowd detection scheme for appli-cation scenarios where consumers pay attention to the size of the humanflow in consumption places.The main use of the YOLO algorithm with the Darknet53 net-work as the main network is to separate pedestrians from the background.Pedes-trians’central two-dimensional coordinates are converted into three-dimensional coordinates,realizing crowd detection and apart from the distance estimation of crowds,real-time monitoring of current regional traffic andflow density,and solv-ing the problem of being unable to monitor and calculate people in real time.It can be applied to many aspects,such as shop rating,traffic control andflow control of scenic spots.Existing monitors are affected by different lights and cannot provide accurate data.In addition,the processing algorithm of this scheme is stable and accurate,and preprocessing is performed before judging the humanflow and the position of the human body to reduce the interference of light.This scheme has the performance of real-time monitoring and calculation through experimental verification.
基金Supported by the National Natural Science Foundation of China(61401496)
文摘This paper described an improved underwater confrontation simulation method of naval amphibious operational training system. The initial position of submarine forces on the enemy is generated automatically, and the attacking distance model of torpedoes is established based on the kinematics theory, which is more flexible and reasonable to judge the launch condition compared to traditional method. The two kinds of confrontation behavior models on the enemy submarine are created to depict its tactical action from the defensive to the offensive as well as the contrary, ensuring that operational style is simulated more comprehensively and properly. The existing motion trajectory estimation and collision detection algorithms on operational platforms are also improved to reduce the iteration error and further enhance the detection accuracy of target hit.
