Target detection method, model training method, device and equipment

Abstract

The embodiment of the invention provides a target detection method, a model training method, a device and equipment. The detection method comprises the steps of obtaining a to-be-detected image, wherein the to-be-detected image comprises a to-be-detected target, and the to-be-detected target comprises a preset object located in a vehicle or attached to the inner surface and the outer surface of the vehicle; determining image feature information corresponding to the to-be-detected image; and processing the image feature information by using a first machine learning model to determine an attribute category of the to-be-detected target, the first machine learning model being trained to determine the attribute category of the to-be-detected target according to the image feature information. According to the technical scheme provided by the embodiment of the invention, the image feature information corresponding to the to-be-detected image is acquired, and the attribute category of the to-be-detected target is determined according to the image feature information, so that the to-be-detected target which cannot be exhaustively detected can be accurately detected and classified, the newly appearing target can be accurately and effectively detected, and the accuracy and reliability of target detection and classification are ensured.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a target detection method, a model training method, a device and equipment. Background technique [0002] With the rapid development of science and technology, the application of vehicles is becoming more and more extensive, and the supervision of vehicles is becoming more and more important. Generally speaking, the supervision of vehicles can include: detection of licensed vehicles, judgment of safe driving behavior, criminal investigation, etc. Wait. In the above-mentioned process of supervising vehicles, it is generally necessary to perform accurate and effective recognition operations on vehicles based on vehicle images. [0003] At present, when identifying a vehicle, it is usually based on whether the objects in the window are the same to identify whether it is the same vehicle, and the above-mentioned window object detection method often needs to know the ...

AI Technical Summary

Problems solved by technology

However, since the vehicle window objects cannot be exhaustive, the vehicle window objects that are not in a specific category cannot be detected or recognized, and the timely and accurate recognition operation cannot be performed on newly emerging object types.

Images