Dangerous article detection method and system based on deep learning model

Abstract

The invention belongs to the technical field of dangerous goods detection, and relates to a deep learning model-based dangerous goods detection method and system. The method comprises the following steps of: simultaneously carrying out image acquisition through an optical lens and an infrared lens, and fusing an optical image and an infrared image to obtain a fused image; calibrating the fused image, and giving a corresponding label; setting initial parameters of a model according to the label, and pre-training the model by adopting the calibrated fusion image; verifying the trained model, counting a fused image with detection errors, supplementing the image according to the characteristics of the fused image, and carrying out secondary training on the model by adopting the fused image and the supplemented image to obtain an optimal detection model; and fusing images collected by the optical lens and the infrared lens in an actual scene , and then inputting the optimal detection model to obtain a hazardous article detection result. The infrared lens and the optical lens are combined, so that the problem that an image cannot be captured when light is dark is solved, and all-weather target detection is realized.

Description

technical field [0001] The invention relates to a dangerous goods detection method and system based on a deep learning model, which belongs to the technical field of intelligent detection, in particular to the technical field of intelligent detection of dangerous goods. Background technique [0002] At present, target detection algorithms based on deep learning can be roughly divided into two types: the first is a two-stage (two-stage) algorithm: first generate a candidate area, and then perform CNN or RCNN classification; the second is a single-stage (one-stage) algorithm. -stage) algorithm: directly applies the algorithm to the input image and outputs the class and corresponding localization. The YOLO (You Only Look Once) model is another target detection algorithm model proposed by Ross Girshick for deep learning target detection speed after RCNN, Fast-RCNN and Faster-RCNN. [0003] The YOLO model converts the target detection problem into a regression problem, directly ...

AI Technical Summary

Problems solved by technology

[0008] In response to the above problems, the object of the present invention is to provide a dangerous goods detection method and system based on a deep learning model, which solves the problem that the optical lens cannot capture The problem of the image has realized the all-weather target detection of the YOLO model

Images