Image detection method and device thereof, equipment and storage medium

Abstract

The invention provides an image detection method and a device thereof, equipment and a storage medium, and the method comprises the steps: determining a plurality of images, of which the visual features and a target object meet the similarity requirement, from the images collected by a plurality of cameras, and determining a space-time point sequence according to the space-time points corresponding to the plurality of images; wherein the time-space point corresponding to any image is composed of the collection time corresponding to any image and the user position, corresponding to the collection time, of the target object, and the time-space points in the time-space point sequence are arranged according to the collection time sequence; performing Gaussian process modeling on the space-time point sequence to determine path smoothing indexes corresponding to the plurality of images, and filtering the images, which are not matched with the target object, in the plurality of images according to the path smoothing indexes, so that the remaining images after filtering are the images matched with the target object.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image detection method, device, equipment and storage medium. Background technique [0002] At present, cameras are deployed in many scenes to collect video of the surrounding environment, so as to achieve purposes such as video surveillance. [0003] For example, several cameras will be set on both sides of the road in the city. When it is necessary to find the moving track of a certain target object (such as a certain person, a certain car) within a certain period of time, the images collected by these cameras can be used (for the camera) The captured video is sampled by image frames) to find the target object, and further determine its moving track based on these images. [0004] However, in practical applications, these cameras are often set at relatively high heights and with low pixel resolution. It is difficult to obtain accurate and reliable detection...

AI Technical Summary

Problems solved by technology

[0004] However, in practical applications, these cameras are often set at relatively high heights and with low pixel resolution. It is difficult to obtain accurate and reliable detection results by directly detecting the target object from the image collected by the camera, which will affect the accuracy of the target. The determination result of the real moving track of the object

Images