Target detector and construction method and application thereof

Abstract

The invention discloses a target detector and a construction method and application thereof, and the method comprises the steps: building a Faster R-CNN target detection model framework which comprises a regional suggestion network module RPN and a plurality of cascaded multi-core multi-background detection structures; adopting RPN to generate a training sample set; based on the training sample set and the weight distribution thereof, iteratively training a plurality of cascaded multi-core multi-background detection structures by adopting a loss function to obtain a Faster R-CNN target detection model; wherein after each multi-core multi-background detection structure is trained in each iterative training, the weight distribution is updated, the weight of the training sample with a large loss function value is large, and the cascaded next multi-core multi-background detection structure is trained based on the updated weight distribution and the regression sample generated by the current multi-core multi-background detection structure. According to the invention, a plurality of cascaded multi-core multi-background detection structures are introduced into the Faster R-CNN, and training is carried out based on weight distribution and updating thereof, so that the classification precision of the whole detector is improved, and the detector has relatively good detection performancein a complex background.

Description

technical field [0001] The invention belongs to the field of target detection, and more specifically relates to a target detector and its construction method and application. Background technique [0002] Object detection is a complex problem that needs to solve two main tasks, first the detector must solve the problem of recognition, distinguish the object from the background, and assign it a corresponding class label. Second, the detector must solve the localization problem (aka regression) to assign accurate bounding boxes to objects. These two tasks are particularly difficult because there are many suspected objects in the image that are very close to the target features, which will affect the judgment of the detector. Therefore, detectors must find real objects while suppressing these suspected objects. [0003] When the target (especially UAV) is in the complex background, it is difficult for the detector to detect the target correctly, and the performance of the det...

AI Technical Summary

Problems solved by technology

[0006] The present invention provides a target detector and its construction method and application, which are used to solve the technical problem that the target detection in the existing target detector is susceptible to background interference and the classification accuracy is not high

Images