Target object positioning and labeling method and device based on sliding profile

Abstract

The invention relates to a target object positioning and labeling method and device based on a sliding profile, and belongs to the technical field of security check image processing, and the method comprises the steps: carrying out the CT scanning of an object, and constructing three-dimensional data; displaying a three-dimensional space body visual image with a changeable visual angle; determining a sliding section position and a breakpoint; generating a profile plane perpendicular to the profile axis based on the breakpoint; marking a target object based on the object cutting surface; extracting a three-dimensional area of the target object; and performing emphasized display processing on the target object to obtain a target object image. According to the method and the device provided by the invention, a series of profile maps are arranged on the profile axis, a better position of the profile of the target object in the profile maps can be searched in a sliding manner, the three-dimensional contour of the target object is fitted through an algorithm, and image emphasis processing is carried out, so that the target positioning speed and precision are improved; and the problems that an existing method is low in automation degree, inaccurate in target positioning and labeling, tedious in operation, long in time consumption and the like are solved, and the labeling quality of the target object is effectively guaranteed.

Description

technical field [0001] The technical field of security inspection image processing of the present invention, in particular, relates to a method and device for locating and marking targets based on sliding profiles. Background technique [0002] Compared with two-dimensional images, three-dimensional images can obtain more complete and intuitive object information, and it is easier to observe the objects contained in them, or the content that the observer is interested in. [0003] In the field of security inspection, the two-dimensional perspective images of traditional perspective security inspection equipment contain overlapping object information under its perspective, and it is difficult to distinguish a single object. However, security inspection CT (Computed Tomography, computer tomography) equipment can obtain the image of the scanned object. 3D image. [0004] At present, in the field of deep learning, a large amount of labeled sample data is required, and the accur...

AI Technical Summary

Problems solved by technology

Especially in the case of multiple items in the security package, the existing technology is very rough in locating and marking the target

Therefore, the final marked area may not only include multiple objects or parts of multiple items, but also contain redundant spatial information outside the object. At the same time, due to the limited range of viewing angles, it is not possible to accurately locate several items in an overlapping state. , distinguish and mark

Such marking results are used as sample data for machine learning training, resulting in a low actual recognition rate of the target object after training.

[0009] In addition, due to the inability of the current technology to overcome the problem of spatial misalignment, a single operation by the user cannot accurately locate multiple targets in different spatial positions, resulting in the problem of labeling multiple targets, and only a single target can be marked one by one. operation, undoubtedly increases the workload

Images