Method of acquiring detection zone in image and method of determining zone usage
地域：
Shanghai
摘要
A method of acquiring detection zone in image, comprises: sequentially acquiring a plurality of images associated with an image acquiring scene by a camera, computing a plurality of moving traces of a plurality of objects in the plurality of images by a computing device, performing a clustering procedure to the moving traces by the computing device to obtain a detection zone, and displaying the detection zone and another image by a display device, with said another image different from the plurality of images and associated with the image acquiring scene.
說明書
This non-provisional application claims priority under 35 U.S.C. § 119(a) on Patent Application No(s). 201911136669.2 filed in China on Nov. 19, 2019, the entire contents of which are hereby incorporated by reference.
This disclosure relates to a method of acquiring detection zone in image and method of determining zone usage, particularly to a method of acquiring detection zone and method of determining zone usage based on multiple moving traces of multiple objects in an image.
In order to monitor the moving direction, travel time, and dwell time of vehicles on the road, various monitoring methods have been developed to monitor the behavior of vehicles. However, most monitoring methods still use surveillance cameras to capture multiple scenes for monitoring personnel to determine whether there are any abnormal activities in the scenes based on the images captured by the surveillance cameras. Besides, whenever a surveillance camera is set up in a new monitoring site, it is still necessary to manually determine the directions of every lane and circle the region of interest (ROI) in every lane.
權(quán)利要求
What is claimed is:1. A method of acquiring detection zone in image, comprising:sequentially acquiring a plurality of images associated with an image acquiring scene by a camera; computing a plurality of moving traces of a plurality of objects in the plurality of images by a computing device; performing a clustering procedure to the moving traces to obtain a detection zone by the computing device; and by a display device, displaying the detection zone and another image, with said another image different from the plurality of images and associated with the image acquiring scene, wherein the clustering procedure comprises: by the computing device, obtaining two boundary points of a confidence interval of a probability distribution function based on an intersection of the moving traces and a reference line, obtaining two boundary points of a confidence interval of another probability distribution function based on an intersection of the moving traces and another reference line, and using an area surrounded by the four boundary points as the detection zone. 2. The method of acquiring detection zone in image according to claim 1 , wherein the detection zone is a first detection zone, and the method comprises:by the computing device, comparing the first detection zone and a second detection zone obtained by performing another clustering procedure to obtain a comparison value, wherein the plurality of images are acquired prior to images used for obtaining the second detection zone; updating the first detection zone with the second detection zone when the computing device determines that the comparison value is lower than an overlapping threshold value; and outputting a notification for the display device to display. 3. The method of acquiring detection zone in image according to claim 1 , wherein computing the plurality of moving traces of the plurality of objects in the plurality of images by the computing device comprises: by the computing device, computing the moving traces according to a plurality of first locations of the objects at a first image acquiring time, and a plurality of second locations of the objects at a second image acquiring time. 4. The method of acquiring detection zone in image according to claim 1 , wherein computing the plurality of moving traces comprises:identifying the objects in the plurality of images using a neural network deep learning method and obtaining a plurality of confidence values associated with the objects; by the computing device, determining whether the confidence values reach a threshold value; and by the computing device, computing the moving traces of the objects in the plurality of images when the confidence values reach the threshold value. 5. A method of determining zone usage, comprising:sequentially acquiring a plurality of images associated with an image acquiring scene by a camera; computing a plurality of moving traces of a plurality of objects in the plurality of images by a computing device; performing a clustering procedure to the moving traces to obtain a detection zone by the computing device; performing an event detection procedure based on the detection zone by the computing device, wherein the event detection procedure determining whether a behavior of a detected object meets an event rule by the computing device; and outputting a detection result of the event detection procedure by the computing device, wherein the clustering procedure comprises: by the computing device, obtaining two boundary points of a confidence interval of a probability distribution function based on an intersection of the moving traces and a reference line, obtaining two boundary points of a confidence interval of another probability distribution function based on an intersection of the moving traces and another reference line, and using an area surrounded by the four boundary points as the detection zone. 6. The method of determining zone usage according to claim 5 , wherein the event rule is whether a time of one of the objects stays in the detection zone reaches a default time, and determining whether the behavior of the detected object meets the event rule based on the detection zone by the computing device comprises:determining whether a coordinate of the detected object falls in the detection zone by the computing device; and determining, by the computing device, whether the time of the coordinate of the detected object falling in the detection zone reaches the default time when the coordinate of the detected object falls in the detection zone. 7. The method of determining zone usage according to claim 5 , wherein the event rule is whether one of the objects in the detection zone moves in a default direction, and determining whether the behavior of the detected object meets the event rule based on the detection zone by the computing device comprises:determining whether a coordinate of the detected object falls in the detection zone by the computing device; and determining, by the computing device, whether the detected object moves in the default direction based on a plurality of coordinates of the detected object and a plurality of time points corresponding to the plurality of coordinates respectively when the coordinate of the detected object falls in the detection zone. 8. The method of determining zone usage according to claim 5 , wherein the event rule is whether a speed of one of the objects in the detection zone falls in a default speed interval, determining whether the behavior of the detected object meets the event rule based on the detection zone by the computing device comprises:determining whether a coordinate of the detected object falls in the detection zone by the computing device; and determining, by the computing device, whether the speed of the detected object falls in the default speed interval based on a plurality of coordinates of the detected object and a plurality of time points corresponding to the plurality of coordinates respectively when the coordinate of the detected object falls in the detection zone.
意見反饋
使用該功能遇到問題
該功能需要專業(yè)版企業(yè)版VIP權(quán)限，您可以：
您也可以聯(lián)系官方QQ: 2157717237 電話: 13264338900