Object quantity estimation method and device

Abstract

The invention provides an object quantity estimation method and system. A depth map of a target scene including objects is generated, and a corresponding projection surface area graph is generated according to the depth map. Degree of shielding of the objects is estimated on the depth map. First weight is allocated for foreground pixels on the corresponding projection surface area graph according to the estimated degree of shielding. Quantity of the objects in the target scene is estimated on the basis of the first weight allocated for the foreground pixels on the projection surface area graph by utilizing a pre-established mapping model between weight and object quantity.

Description

technical field [0001] The present application relates to a method and device for estimating the number of objects, and more particularly, to a method and device for estimating the number of objects in a scene based on stereo vision. Background technique [0002] Estimating the number or density of objects in a certain scene, such as pedestrians, has important practical significance in the field of public security and economic consumption. For example, when the number of people in a public place changes suddenly, it often means that some emergencies have occurred; and for large department stores and supermarkets, if the flow, concentration and distribution of people can be mastered, it can be more accurate. Plan the berth layout of the store and supermarket well, and arrange the sales plan of the store more reasonably. In some developed countries in Europe and the United States, many companies have already carried out specialized research in this area, and call it video-bas...

AI Technical Summary

Problems solved by technology

The disadvantage is that the establishment of the statistical mapping relationship requires sufficient training samples, and the estimation accuracy is easily affected by factors such as shadows in the scene, occlusion between people and people, people and objects, and camera perspective distortion.

The disadvantage of this method of deploying the camera is that the field of view of the camera becomes smaller; at the same time, since only the top of the person's head can be photographed, the facial information of the person will be lost

Therefore, as the person moves in the scene and the distance from the camera changes, the number of image pixels he has will also change, which will affect the accuracy of the number of people or the density of people based on the mapping method.

Images