Spatial-temporal constraint-based target re-identification method

Abstract

The invention discloses a spatial-temporal constraint-based target re-identification method. The method includes the following steps that: a visual information probability-based preliminary ranking result is obtained based on the visual information of a target; based on a situation that the target which appears in one camera is impossible to appear in another camera, a Hinge loss function is utilized to construct a filter model to narrow a scope to be inquired; an inter-camera time probability model is realized through Wiebull distribution; inter-camera time preliminary probability is represented by the time interval probability of the target and a query target set, and therefore, an inter-camera time information and visual feature-based intermediate ranking result can be obtained based on the fusion of the inter-camera time probability model and visual information probability; and a target re-identification ranking result can be further optimized based on a situation that the probability of the same target appearing in two cameras which are close to each other spatially is larger than the probability of the target appearing in two cameras which are remote to each other spatially. With the method of the invention adopted, a target re-identification effect can be greatly promoted.

Description

technical field [0001] The invention belongs to the technical field of surveillance video retrieval, and relates to a target re-identification method, in particular to a target re-identification method based on time-space constraints. Background technique [0002] In actual video reconnaissance, investigators need to quickly troubleshoot, track and lock suspected targets based on the moving pictures and trajectories of designated objects under multiple cameras. The traditional video investigation mode based on manual browsing requires a lot of manpower and time, is inefficient, and easily delays the time to solve the case. Target re-recognition is a surveillance video automatic retrieval technology for specific objects, that is, matching the same target object that appears at different times under the camera. It is convenient for video investigators to quickly and accurately discover the activity pictures and trajectories of suspected targets, which is of great significance...

AI Technical Summary

Problems solved by technology

Three of the 4 patents involving the concept of space-time constraints did not involve the application of the concept of space-time to target re-identification. Carry out target recognition, but the spatial constraints and vehicle features in this patent are updated through each other, and finally the recognition is completed. In addition, the patent does not use a probability model

[0008] An analysis of all relevant patents leads to the following conclusions: there is currently no application of spatio-temporal constraints on target re-identification methods; there is currently no work using probabilistic models for target re-identification

Images