A text-based fine-grained vehicle image retrieval system

Abstract

The present invention provides a text-based fine-grained retrieval system for vehicle images, which allows users to obtain the required information in a natural language retrieval manner, which reduces the retrieval threshold compared with the method of image retrieval by using images; The modal semantic matching task has been transformed into a more direct, interpretable, simple, and well-researched semantic matching task between texts; regularly analyze the retrieved text at the proximal time, extract interest words and interest degrees, and establish interest words Table, and use the interest vocabulary to predict the user's retrieval trend, generate fine-grained description text for the image that is more in line with the recent user's interest points, and realize the dynamic update of the image description text library, so as to improve the flexibility and retrieval performance of this method; It can accurately capture the fine-grained features of each part of the vehicle, so that different vehicles of the same model can be more accurately identified.

Description

technical field [0001] The invention relates to the field of traffic image processing, in particular to a text-based fine-grained vehicle image retrieval system. Background technique [0002] At present, cases of stealing vehicles and using vehicles to commit crimes have increased repeatedly, seriously affecting social stability. In order to evade police investigation, suspects often change vehicle license plates, remove or block vehicle locators and other behaviors. In this case, it is necessary to rely on vehicle appearance features to track and locate the target vehicle. Vehicle image retrieval is an important part of the intelligent transportation system. It retrieves images of vehicles whose appearance features match the retrieval conditions from the images captured by road monitoring to assist the police in tracking stolen, hit-and-run or other criminal-related vehicles. Measuring the semantic similarity between an image to be retrieved and a retrieval condition is a...

AI Technical Summary

Problems solved by technology

However, in actual situations, it is usually difficult to construct an image that meets the retrieval conditions, which limits the application scenarios of this type of method.

In addition, there are also some works to retrieve images by automatically generating text indexes, but the generated text lacks descriptions of fine-grained features of images

Images