Search

CN-122023382-A - Visual processing-based consignment baggage assessment method, controller, medium and product

CN122023382ACN 122023382 ACN122023382 ACN 122023382ACN-122023382-A

Abstract

A consignment luggage evaluation method, a controller, a medium and a product based on visual processing relate to the field of intelligent control. The method comprises the steps of generating a three-dimensional digital model of luggage to be checked based on acquired three-dimensional point cloud and image data, identifying and marking a local area of the model as a rigid abrupt change area or a flexible transition area according to the extracted geometric and texture characteristics, inputting the model into a virtual channel model to calculate an intersecting volume, judging that blocking risks exist and rejecting check-in if the intersecting volume is out of limit and the corresponding local area attribute is the rigid abrupt change area, and allowing check-in if the attribute is the flexible transition area and the intersecting volume ratio is smaller than a preset deformation threshold value. According to the application, the rigid interference and the flexible deformation are distinguished through virtual simulation, so that the problem that the irregular luggage misjudgment rate is high only by static comparison of the size extremum in the related technology is solved, and the recognition accuracy and the passing rate of the self-service consignment system are improved.

Inventors

  • XIN YING
  • WANG JINFENG

Assignees

  • 中嘉锦诚(北京)科技有限公司

Dates

Publication Date
20260512
Application Date
20260228

Claims (10)

  1. 1. A visual processing-based method of evaluating checked-in baggage, applied to a controller of a self-service check-in system, comprising: Generating a three-dimensional digital model of the luggage to be checked based on the acquired three-dimensional point cloud data and image data of the luggage to be checked; Identifying and marking local region attributes of the three-dimensional digital model according to geometric feature data and texture feature data extracted from the three-dimensional digital model, wherein the local region attributes comprise rigid abrupt change regions or flexible transition regions; inputting the marked three-dimensional digital model into a preset virtual channel model, and calculating the intersection volume between the three-dimensional digital model and the virtual channel model; when the intersecting volume is larger than a preset intersecting threshold value, acquiring a local area attribute of a local area corresponding to an intersecting part in the three-dimensional digital model; If the local area attribute is the rigidity abrupt change area, judging that the luggage to be checked has a blocking risk, and generating a check-out instruction; If the local area attribute is the flexible transition area, calculating the ratio of the intersecting volume to the total volume of the three-dimensional digital model to obtain the intersecting volume ratio; And when the intersecting volume ratio is smaller than a preset deformation threshold value, generating an allowable consignment instruction of the luggage to be consigned.
  2. 2. The method according to claim 1, characterized in that said geometric feature data and texture feature data extracted from said three-dimensional digital model, in particular comprise: Extracting texture feature data of the three-dimensional digital model according to the image data; and extracting geometric feature data of a plurality of section outlines of the three-dimensional digital model along the preset advancing direction of the luggage to be checked.
  3. 3. The method according to claim 2, wherein the identifying and marking local region attributes of the three-dimensional digital model based on geometric feature data and texture feature data extracted from the three-dimensional digital model specifically comprises: Identifying the material type of the luggage to be checked according to the texture characteristic data, wherein the material type comprises hard materials and soft materials; When the material type is hard material, marking the local area of the three-dimensional digital model as a rigid mutation area; When the material type is soft material, calculating the change rate of the geometric moment characteristics between the adjacent section profiles according to the geometric moment characteristics of each section profile; If the geometric moment characteristic change rate is larger than a preset change threshold value, and the point cloud space dispersion of a local area of the three-dimensional digital model corresponding to the section profile is larger than a preset dispersion threshold value, marking the local area as a rigid abrupt change area; And if the geometric moment characteristic change rate is smaller than or equal to a preset change threshold value, marking the local area of the three-dimensional digital model corresponding to the section profile as a flexible transition area.
  4. 4. A method according to claim 3, wherein if the geometric moment feature change rate is greater than a preset change threshold, and the point cloud spatial dispersion of the local area of the three-dimensional digital model corresponding to the cross-sectional profile is greater than a preset dispersion threshold, marking the local area as a rigid abrupt change area specifically includes: If the geometric moment characteristic change rate is larger than a preset change threshold, calculating the point cloud space dispersion of the local area of the three-dimensional digital model corresponding to the section profile; when the point cloud space dispersion is smaller than or equal to a preset dispersion threshold value, marking the local area as a flexible transition area; And when the point cloud space dispersion is larger than a preset dispersion threshold value, marking the local area as a rigid mutation area.
  5. 5. The method according to claim 1, wherein the inputting the marked three-dimensional digital model into a preset virtual channel model, calculating the intersection volume between the three-dimensional digital model and the virtual channel model, specifically comprises: Calculating the area of an overlapping area between the section outlines of the three-dimensional digital model at different positions and corresponding boundary constraint sections in the virtual channel model one by one along a preset conveying path, wherein the boundary constraint sections are space boundaries allowing baggage to be checked to pass, and the area of the overlapping area is the area of the section outlines exceeding the space boundary; And carrying out integral calculation on the area of each overlapping area along the preset conveying path to obtain the intersection volume between the three-dimensional digital model and the virtual channel model.
  6. 6. The method of claim 5, wherein prior to the step of calculating the area of the overlapping region between the cross-sectional profile of the three-dimensional digital model at different locations and the corresponding boundary-constrained cross-section in the virtual channel model one by one along the predetermined conveyance path, the method further comprises: acquiring an edge coordinate extremum of the section profile and a boundary coordinate limiting range preset by the boundary constraint section; If the edge coordinate extremum does not exceed the limit range of the boundary coordinate, determining that the area of an overlapping area of the section outline of the current position and the boundary constraint section is zero; and if the edge coordinate extremum exceeds the limit range of the boundary coordinate, executing the step of overlapping area between the section profile and the corresponding boundary constraint section in the virtual channel model.
  7. 7. The method of claim 1, wherein after the step of calculating the ratio of the intersection volume to the total volume of the three-dimensional digital model to obtain an intersection volume ratio, the method further comprises: And when the intersecting volume ratio is larger than or equal to a preset deformation threshold value, generating a refusing delivery instruction of the luggage to be delivered.
  8. 8. A controller of a self-service baggage claim system, said controller comprising one or more processors and memory, said memory coupled to said one or more processors, said memory for storing computer program code, said computer program code comprising computer instructions, said one or more processors invoking said computer instructions to cause said controller to perform the method of any of claims 1-7.
  9. 9. A computer readable storage medium storing computer instructions which, when run on a controller, cause the controller to perform the method of any one of claims 1-7.
  10. 10. A computer program product comprising a computer program or instructions which, when run on a controller, cause the controller to perform the method of any of claims 1-7.

Description

Visual processing-based consignment baggage assessment method, controller, medium and product Technical Field The application relates to the field of intelligent control, in particular to a visual processing-based consignment baggage assessment method, a controller, a medium and a product. Background The self-service baggage consignment system conveys passenger baggage to a subsequent processing area through automatic conveying equipment, but because the consignment baggage contains regular boxes as well as irregular baggage such as soft bags, special-shaped backpacks and the like, the baggage can be blocked or unstable in posture when passing through a turning part of a conveying line or entering a passage of a security inspection machine, and equipment shutdown and manual intervention are caused. In order to solve the above problems, a volume measurement subsystem is generally arranged at the front end of a conveying device in the related art, a three-dimensional scanning device is used for acquiring baggage point cloud data and calculating the length, width and height values of the smallest circumscribed rectangle of baggage, the values are compared with a limit threshold value of a conveying line, and if the values exceed the limit, delivery is refused, so that the overdriven baggage is intercepted. However, in the related art, the calculation of the external rectangle essentially regards the irregular areas such as the concave area and the hollowed-out area of the luggage as solid filling and is equivalent to a regular cuboid, and whether the luggage passes through the external rectangle in the actual conveying process is not completely dependent on the extreme value of the length, width and height of the external rectangle obtained by calculation, and is further dependent on whether the specific surface profile of the external rectangle can spatially interfere with the boundary of the equipment in the motion track, so that the fact that the dimension exceeding is caused by compatible gesture inclination or caused by a rigid structure with blocking risk is difficult to distinguish by static comparison only with the extreme value of the dimension, and further misjudgment risk of an automatic consignment system on the irregular consignment luggage is increased and passing efficiency is reduced. Disclosure of Invention The application provides a visual processing-based checked-in luggage evaluation method, a controller, a medium and a product, which are used for improving the identification accuracy of a self-service checked-in system on irregular checked-in luggage and the passing rate of the irregular checked-in luggage. The application provides a visual processing-based check-in baggage assessment method, which is applied to a controller of a self-service baggage check-in system and comprises the steps of generating a three-dimensional digital model of baggage to be checked in based on acquired three-dimensional point cloud data and image data of the baggage to be checked in, identifying and marking local area attributes of the three-dimensional digital model according to geometric feature data and texture feature data extracted from the three-dimensional digital model, wherein the local area attributes comprise rigid abrupt change areas or flexible transition areas, inputting the marked three-dimensional digital model into a preset virtual channel model, calculating the intersecting volume between the three-dimensional digital model and the virtual channel model, acquiring the local area attributes of local areas corresponding to intersecting parts in the three-dimensional digital model when the intersecting volume is larger than a preset intersecting threshold, judging that the baggage to be checked in has a blocking risk if the local area attributes are rigid abrupt change areas, generating a check-in instruction, calculating the ratio of the intersecting volume to the total volume of the three-dimensional digital model according to the geometric feature data and the texture feature data extracted from the three-dimensional digital model, obtaining the intersecting volume ratio, and generating an allowable check-in instruction of the baggage to be checked in when the intersecting volume ratio is smaller than the preset deformation threshold. By adopting the technical scheme, the controller firstly utilizes three-dimensional point cloud data and image data to construct a high-precision three-dimensional digital model, then does not directly judge according to an external size extremum, but utilizes a virtual channel model to dynamically simulate and position the intersection part of the luggage and the boundary of the conveying equipment, then, the controller performs attribute differentiation on the intersection part, namely, directly intercepts the part marked as a rigid abrupt change area to protect the equipment, and quantifies the deformation requirement of the flexible transition area by calcul