CN-120356148-B - Material detection method, system, medium and product of material stacking area

CN120356148BCN 120356148 BCN120356148 BCN 120356148BCN-120356148-B

Abstract

The application provides a material detection method, a system, a medium and a product of a material stacking area, and relates to the technical field of image equipment. The method is characterized in that firstly, a monitoring image of a test paper storage area is collected and subjected to differential definition processing, the operation enables the test paper bag area to be highlighted in the image, the definition of the test paper bag area is higher than that of a non-test paper bag area, different parts of the inside of the test paper bag are distinguished, the profile of the test paper bag is highest, the distinction degree of the test paper bag and the distinction degree of the boundary are required to be increased, meanwhile, the profile of the test paper bag is sampled according to the structural complexity, the resolution can be improved in a simple structure area, the profile can be captured more finely, the complexity area is obvious because the distinction is obvious, the resolution is reduced, the resource consumption and the interference are reduced, the profile information acquisition is optimized by the mutual cooperation of the two, and the risks of missed detection and false detection are reduced.

Inventors

FU FENGYUN
XIA XIANFENG
ZHANG YINHAO
DUAN CHENG
LIU JIANFENG
ZHOU YAN
FENG HUI

Assignees

重庆远大智诚包装科技有限公司

Dates

Publication Date: 20260508
Application Date: 20250328

Claims (10)

1. A method of material detection in a material stacking area, comprising: collecting a monitoring image of a test paper storage area, and carrying out differential definition processing on the monitoring image to obtain a characteristic image sequence, wherein the image definition of a test paper bag area is higher than that of a non-test paper bag area, and the definition of a test paper bag outline, other areas and a test paper bag body area in the test paper bag area are sequentially reduced; Under the condition that the position of the test paper bag is detected to change, carrying out space registration calculation on a characteristic image sequence from the previous position change to the current time and a dynamic reference model to obtain displacement of different test paper bags, wherein the dynamic reference model is a three-dimensional space map established for an initial stacking state when the test paper is put in storage; Determining a target test paper bag which is reduced or increased according to the displacement of the test paper bag; The method comprises the steps of collecting interaction data of a personnel moving track and a test paper bag area, and carrying out matching analysis on the interaction data and a preset operation rule, wherein the interaction data comprises data information generated in the process of contacting and carrying the test paper bag area by personnel; when the interaction data accords with a preset operation rule, judging the corresponding behavior as a normal event, and when the interaction data does not accord with the preset operation rule, judging the corresponding behavior as an abnormal event, wherein the preset operation rule comprises personnel with corresponding authority and information of a specific test paper bag allowing the interaction behavior to be generated with the personnel; judging a target test paper bag corresponding to the normal event and a preset working rule; When the access test paper bag specified by the preset working rules does not correspond to the target test paper bag, changing the corresponding normal event into an abnormal event; the abnormal event is marked.
2. The method according to claim 1, wherein the step of determining the target test paper bag to be decreased or increased according to the displacement amount of the test paper bag comprises the following steps: Determining the relative position relation between the test paper bag areas; establishing the association strength of different test paper bag stacks, wherein the association strength decays along with the increase of the interval of the test paper bag stacks, and the test paper bag stacks are all test paper bags in the test paper bag area; determining the change amount of the distance between the test paper bag which is reduced or increased in the test paper bag stack and the test paper bag stack which belongs to the test paper bag stack; determining a group behavior consistency index according to all transformation quantities; If the change of the distance between the test paper bag and the test paper bag stack is larger than a preset threshold value and is separated from the corresponding group behavior consistency index, determining the test paper bag as the target test paper bag.
3. The method of claim 1, wherein after the step of collecting interaction data of the activity track of the person and the area of the test paper bag and performing a matching analysis on the interaction data and a preset operation procedure, the method further comprises: the method comprises the steps of obtaining type identifiers of test paper bags, wherein the type identifiers are used for dividing the test paper bags together, and the type identifiers comprise one or more of schools, classes and printing product subject information; Grouping the activity tracks of the acquisition personnel through type identifiers; randomly selecting two acquisition personnel activity tracks from the same group of the acquisition personnel activity tracks, and judging the similarity; if the similarity is lower than a similarity threshold, extracting avoidance behavior characteristics from the activity tracks of the acquired personnel with the later extraction time sequence; the first test paper bag corresponding to the activity track of the acquisition personnel with the front time sequence and the second test paper bag corresponding to the activity track of the acquisition personnel with the rear time sequence are acquired; Judging whether the obstacle test paper bags are simultaneously met according to the preset operation rules, and carrying after the first test paper bag and before the second test paper bag; and if the behaviors of the obstacle test paper bags, the first test paper bags and the second test paper bags are not all met, judging the behaviors of the obstacle test paper bags, the first test paper bags and the second test paper bags as abnormal events.
4. The method of claim 3, wherein the step of extracting avoidance behavior features from the activity trajectories of the collection personnel with the later extraction sequence specifically comprises: Respectively acquiring a position sequence and a speed sequence of two acquisition personnel moving tracks; calculating curvature values corresponding to the position sequences of the two acquisition personnel moving tracks; In the motion trail of the acquisition personnel with a later time sequence, when the curvature value is larger than a first preset threshold value and the corresponding speed value is smaller than a second preset threshold value, determining candidate avoidance positions; Judging whether the activity track of the acquisition personnel with the front time sequence meets the condition that a curvature value is larger than a first preset threshold value and a speed value is smaller than a second preset threshold value at a corresponding space position; and under the condition that the candidate avoidance position is satisfied, determining the candidate avoidance position as the avoidance behavior characteristic.
5. The method of claim 3, wherein the step of identifying the obstacle test paper bag corresponding to the avoidance behavior feature specifically comprises: Constructing a search area on the avoidance behavior characteristics; determining a target area nearest to the search area in a preset operation procedure; And determining the test paper bag corresponding to the target area as an obstacle test paper bag.
6. The method according to claim 1, wherein the step of performing differential sharpness processing on the monitored image to obtain a feature map sequence specifically includes: Extracting boundaries of the test paper bags in the monitoring images to obtain the outlines of the preliminary test paper bags; judging whether the outline of the primary test paper bag meets the requirement of a simple region or not; if the test paper bag contour meets the standard, constructing a multi-scale feature pyramid, and extracting features with different scales from the test paper bag contour to obtain local fine features; and carrying out feature fusion on the local fine features and the outline of the preliminary test paper bag to obtain the outline structure of the test paper bag.
7. The method of claim 1, wherein after the step of marking the anomaly event, the method further comprises associating corresponding lot identification information, recording operator identity information, an operation time stamp, and spatial location coordinates.
8. A material detection system for a material stacking area, comprising one or more processors and a memory coupled to the one or more processors, the memory for storing computer program code comprising computer instructions that the one or more processors invoke to cause the material detection system for a material stacking area to perform the method of any of claims 1-7.
9. A computer program product containing instructions which, when run on a material detection system of a material stacking area, cause the material detection system of the material stacking area to perform the method of any one of claims 1-7.
10. A computer readable storage medium comprising instructions which, when run on a material detection system of a material stacking area, cause the material detection system of the material stacking area to perform the method of any one of claims 1-7.

Description

Material detection method, system, medium and product of material stacking area Technical Field The application relates to the technical field of image equipment, in particular to a material detection method, a system, a medium and a product of a material stacking area. Background In the educational field, mass printed products such as test papers, problem books, etc. have clear distribution requirements, which require sub-packaging according to various factors such as different areas, schools, and specific classes, etc., to ensure accurate supply into corresponding usage scenarios. For example, primary schools of different scales have different numbers of classes, the number of the classes is different, like the class A is accumulated for 4 classes, the class A is accumulated for 28 persons, the class A2 is accumulated for 32 persons, the class A is accumulated for 31 persons, the class A is accumulated for 25 persons, the class B is accumulated for 3 classes, the class B is accumulated for 22 persons, the class B is accumulated for 32 persons and the class B is accumulated for 28 persons, and the papers are required to be transported to appointed places such as examination rooms in a sealing way in many times, therefore, after printing, the test paper bags and the test papers are transported in a sealed split manner strictly according to the class condition, split-packaged and rechecked, and are stored in a designated area, and materials in the designated area are monitored in real time by a detection system, so that the conditions of loss, omission and the like of the rechecked test paper bags are prevented. In the related art, in the process of detecting the test paper bags, because all test paper bags are packaged by using kraft paper with uniform specification, the following technical difficulties are caused that 1) the test paper bags lack obvious visual characteristic differences, because the kraft paper with the same material makes all the test paper bags present consistent beige color, the volume and the shape of the test paper bags are almost identical due to the same packaging specification, so that an image recognition system is difficult to extract reliable distinguishing information from appearance characteristics, 2) when a plurality of batches of test paper bags are stacked, the boundary between the test paper bags is fuzzy, and the interference of illumination and shadow causes poor effect of an image segmentation algorithm based on contour detection, so that the space range of each test paper bag cannot be accurately defined, the problems cause that the related image recognition technology cannot realize accurate recognition of the test paper batches, the risks of missed detection and false detection exist, and the influence is obvious under the scene of education on missed detection and false detection tolerance. Disclosure of Invention The application provides a material detection method, a system, a medium and a product of a material stacking area, which are used for reducing risks of missed detection and false detection. The application provides a material detection method of a material stacking area, which comprises the steps of collecting a monitoring image of a test paper storage area, carrying out differential definition processing on the monitoring image to obtain a characteristic image sequence, determining a reduced or increased target test paper bag according to the displacement of the test paper bag, collecting interaction data of a moving track of a person and the test paper bag area, carrying out matching analysis on the interaction data and a preset operation rule, carrying out resolution sampling on a region with a simple structure of the test paper bag, carrying out resolution sampling on a complex region of the test paper bag, carrying out space registration calculation on the characteristic image sequence from the last position change to the current time and a dynamic reference model under the condition that the position of the test paper bag is detected to change, obtaining the displacement of different test paper bags, wherein the dynamic reference model is a three-dimensional space map established by an initial stacking state during the storage of the test paper, acquiring interaction data of the moving track of the person and the test paper bag area, carrying out matching analysis on the interaction data and the preset operation rule, judging that the interaction data corresponds to the preset operation rule when the interaction data accords with the preset operation rule, carrying out corresponding interaction data and judging that the interaction data corresponds to the preset operation rule, and the preset interaction rule does not correspond to the normal operation rule, and carrying out corresponding abnormal operation rule judging that the corresponding interaction rule is not met when the preset operation rule is corresponding to the preset operation rule, a