Image file gathering method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an image file-gathering method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the feature extraction of two images to be subjected to file-gathering, determining the image features of the two images to be subjected to file-gathering, analyzing the corresponding target motion mode of a target object between the two images to be subjected to file-gathering based on each determined image feature, and carrying out the file-gathering of the two images to be subjected to file-gathering. Therefore, based on the target motion speed corresponding to the target motion mode, the corresponding distance threshold value is determined in the corresponding acquisition time range of the two images to be subjected to file gathering, on one hand, the space-time relevance between the corresponding clustering results is ensured, and the accuracy of image file gathering is further improved; and on the other hand, the determined distance threshold value is more suitable for the movement distance of the corresponding target object in the actual scene, so that the image file gathering accuracy is higher.

Description

technical field [0001] The present invention relates to the technical field of image processing, and in particular, to an image file gathering method, device, electronic device and storage medium. Background technique [0002] With the continuous development of modern information technology and the new situation of smart construction, for example, by constructing an image recognition system covering public areas, the target objects in a certain coverage area can be captured and recognized, so as to identify the target objects according to the identity characteristics. The development of related security business plays an immeasurable role in security defense, smart access control and other fields. [0003] Specifically, in order to ensure the recognition accuracy of the identity features of the target object, it is usually necessary to use the Image Clustering (IC) technology to cluster the massive target images captured in the system coverage area, and then according to the...

AI Technical Summary

Problems solved by technology

[0006] In related technologies, based on the method of determining the similarity of features, it is easy to cause spatiotemporal contradictions among the corresponding target images in the image archives. For example, when the number of images to be aggregated is large and the system coverage area is large, the The target images with similar capture time and relatively long capture distances belong to the same image file. As a result, in this image file, the target object has time and space to reach two distant capture positions in a short period of time. Contradictory phenomenon, affecting the accuracy of image aggregation

[0007] 2. There is a distance difference

[0008] In related technologies, in order to avoid spatio-temporal contradictions, the corresponding two target images are usually determined according to the capture distance between the two capture images corresponding to the adjacent capture time, for example, if the capture distance is less than the preset distance threshold, then determine the corresponding The two captured images are the target images. However, in actual situations, due to the different movement modes of the target object, the corresponding capture distance also has a large difference. For example, when the target object moves on foot, the corresponding capture distance is small, while When the target object is moving in a vehicle, the capture distance increases significantly within the same time frame. In this case, it is difficult to determine an accurate distance threshold, which affects the accuracy of image aggregation.

Images