Papers by Author: Hai Ming Wu

Abstract: According to the principle of the digital camera’s forming image, we measure the distance between the points on the target and digital camera respectively, then we construct the limited equation, and calculate the position relation between target and digital camera through this limited equation, then by using the coordinate’s transformation, we transform the coordinate which takes digital camera as original points into the coordinate which takes target as original points. After that step, we could fix the coordinate which compare to the target. Finally, we finish the fixation task of the doubled-sight digital camera.

Abstract: Digital cameras have been widely used in the areas of road transportation, railway transportation as well as security system. To address the position of digital camera in these fields this paper proposed a geometry calibration method based on feature point extraction of arbitrary target. Under the meaning of the questions, this paper first defines four kinds of coordinate system, that is the world coordinate system. The camera's optical center of the coordinate system is the camera coordinate system, using the same point in different coordinate system of the coordinate transformation to determine the relationship between world coordinate system and camera coordinate. And thus determine the camera's internal parameters and external parameters, available transformation matrix and translation vector indicated by the camera's internal parameters of the external parameters and the establishment of a single camera location model. According to the model, using the camera's external parameters to be on the target circle center point in the image plane coordinates.

Abstract: Digital Cameras positioning has a wide range of application in the aspect of traffic monitoring (e-police). The introduction of space Cartesian coordinate system together with the principle of image formation of digital camera and the physical relations among image, camera, and the original picture is where the general linear space model, with the Gaussian formula, Physical optics imaging as the constraint condition, is built, putting forward the theoretical formula of pinpointed coordinates of the center of the circle in the target plane on the plane of camera. Then we can safely draw the conclusion that the track of the target plane formed on the plane of an oval track. Second, the use of graphic tools extracting the track of the edge can help to fit out of elliptic equations, showing the coordinates of the five centers.

Abstract: Because the choice and important of learning rate , the higher of η and the faster convergence it will be, but it may cause instability or function vibration if is too high; if is lower, although it may avoid instability, the speed of function convergence will reduce. In order to solve the contradiction, we introduce a variable of , and if the this time is the same as that of the previous time, the weighted summation value will increase and it results in the regulation speed of right value at the stable regulation; and if the this time is contrary to that of the previous time, it indicates that a certain vibration and now the result of summation will make the value of decrease to play a role in stability and increase the speed of function convergence.