Human-vehicle weight recognition and model training method and device, equipment and storage medium

Abstract

The invention discloses a human-vehicle weight recognition and model training method and device, equipment and a storage medium, and the method comprises the steps: obtaining a plurality of training samples, wherein each training sample comprises a first sample image and a second sample image; training a pre-established initial human-vehicle weight recognition model by using the training sample until a loss value of a loss function in the initial human-vehicle weight recognition model meets a preset condition to obtain a target human-vehicle weight recognition model; wherein the initial human-vehicle weight recognition model comprises a target detection model, a first initial multi-layer sensor and a second initial multi-layer sensor. According to the embodiment of the invention, when theinitial pedestrian and vehicle re-identification model is trained, the at least two sample images can be used for feature mutual enhancement, and the feature information of the first object in different sample images is fully utilized to improve the loss of the feature information caused by the change of the shooting state, thereby facilitating the improvement of the re-identification effect of pedestrians and vehicles.

Description

technical field [0001] The present application belongs to the field of information technology, and in particular relates to a method, device, equipment and storage medium for human-vehicle recognition and model training thereof. Background technique [0002] With the development of artificial intelligence technology, machine vision recognition is increasingly used in daily life, for example, pedestrian recognition based on video images collected by imaging equipment. In order to obtain pedestrian activity trajectories, pedestrian re-identification technology is usually used, that is, pedestrian recognition may be performed based on images collected by different imaging devices. [0003] Since the shooting angles of different imaging devices may be different, the state (such as length, width, or angle) of the same pedestrian in different images may be different. When the pedestrian is riding a bicycle, the combination of pedestrian and vehicle (hereinafter referred to as the ...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides a method, device, equipment and storage medium for the identification of the weight of people and vehicles and its model training, which solves the problem of poor recognition effect in the prior art when identifying the weight of people and vehicles

Images