CN-122024168-A - Intrusion monitoring system and intrusion monitoring method

Abstract

The invention provides an intrusion monitoring system and an intrusion monitoring method. The intrusion monitoring system is adapted to monitor the bridge crane. The intrusion monitoring system comprises an image acquisition device, a storage device and a processor. The image acquisition device is used for acquiring a plurality of images of the bridge crane. The storage device is used for storing the calculation module and the control module. The processor is coupled with the image acquisition device and the storage device and is used for executing the calculation module and the control module. The computing module generates a three-dimensional contour of a suspended object of the bridge crane according to the plurality of images, and determines a safety area boundary according to the three-dimensional contour of the suspended object. The computing module also carries out character recognition and judges whether a character invasion event occurs according to the boundary of the safety area so as to inform the control module of carrying out early warning operation. The invention can effectively monitor whether a person approaches to a hanging object of the bridge crane.

Inventors

• YUAN CHENGCHENG
• XU SUJUN
• GUO ZHENXI
• LI HAO

Assignees

• 威盛电子(深圳)有限公司

Dates

Publication Date

20260512

Application Date

20260212

Claims (20)

1. 1. An intrusion monitoring system adapted to monitor a bridge crane, the intrusion monitoring system comprising: The image acquisition device is used for acquiring a plurality of images of the bridge crane; A storage device for storing the calculation module and the control module, and A processor coupled to the image acquisition device and the storage device and configured to execute the computing module and the control module, Wherein the computing module generates a three-dimensional profile of a suspended object of the bridge crane according to the plurality of images, and determines a safety area boundary according to the three-dimensional profile of the suspended object, And the computing module also performs character recognition, and judges whether a character invasion event occurs according to the boundary of the safety area so as to inform the control module of performing early warning operation.
2. 2. The intrusion monitoring system of claim 1, wherein the computing module comprises: the data processing module is used for generating three-dimensional space data according to the plurality of images and the corresponding depth information; An artificial intelligence model coupled to the data processing module and configured to generate the three-dimensional profile of the hanger from the three-dimensional spatial data, and The marking module is coupled with the artificial intelligence model and used for determining the safety area boundary according to the two-dimensional projection area of the three-dimensional outline of the hanging object on the ground.
3. 3. The intrusion monitoring system of claim 2, wherein the image acquisition device comprises an infrared projector and at least two infrared cameras, and the data processing module calculates corresponding depth data as the three-dimensional spatial data from the plurality of images provided by the at least two infrared cameras.
4. 4. The intrusion monitoring system of claim 2, wherein the image acquisition device comprises two visible light cameras and the data processing module calculates corresponding depth data as the three-dimensional spatial data from the plurality of images provided by the two visible light cameras.
5. 5. The intrusion monitoring system of claim 2, wherein the artificial intelligence model is to segment a hang contour of the hang in the plurality of images and calculate the three-dimensional contour of the hang from the hang contour and the three-dimensional spatial data.
6. 6. The intrusion monitoring system of claim 2, wherein the marking module expands the boundaries of the two-dimensional projection area outwardly by a buffer distance to determine the safe area boundaries.
7. 7. The intrusion monitoring system of claim 6, further comprising: an inertial measurement unit disposed on the pendant and in communication with the processor, wherein the processor calculates a swing amplitude of the pendant from measurement data provided by the inertial measurement unit and calculates a maximum horizontal offset from the swing amplitude, Wherein the marking module takes the maximum horizontal offset as the buffer distance to dynamically adjust the safe area boundary.
8. 8. The intrusion monitoring system of claim 2, wherein the artificial intelligence model is further configured to determine whether the person intrusion event occurs in the plurality of images, and the processor determines whether to notify the control module to perform the pre-warning operation based on the determination of the person intrusion event.
9. 9. The intrusion monitoring system of claim 8, further comprising: an audible and visual alarm coupled to the processor, The early warning operation comprises that the control module controls the audible and visual alarm to send out audible and visual alarm information.
10. 10. The intrusion monitoring system of claim 8, further comprising: a bridge crane controller coupled to the processor, Wherein the early warning operation comprises the control module controlling the bridge crane controller to operate the bridge crane.
11. 11. An intrusion monitoring method suitable for monitoring a bridge crane, the intrusion monitoring method comprising: Acquiring a plurality of images of the bridge crane through an image acquisition device, and executing a calculation module and a control module through a processor; generating a three-dimensional outline of a suspended object of the bridge crane according to the plurality of images through the computing module; determining a safety area boundary according to the three-dimensional outline of the hanging object by the computing module and And carrying out person identification through the computing module, and judging whether a person intrusion event occurs according to the safety area boundary so as to inform the control module of carrying out early warning operation.
12. 12. The intrusion monitoring method according to claim 11, wherein the computing module comprises: the data processing module is used for generating three-dimensional space data according to the plurality of images and the corresponding depth information; an artificial intelligence model for generating the three-dimensional profile of the hanging object according to the three-dimensional space data, and The marking module is used for determining the boundary of the safety area according to the two-dimensional projection area of the three-dimensional contour of the hanging object on the ground.
13. 13. The intrusion monitoring method according to claim 12, wherein the image capturing device comprises an infrared projector and at least two infrared cameras, Wherein the step of generating the three-dimensional spatial data comprises: And calculating corresponding depth data serving as the three-dimensional space data according to the images provided by the at least two infrared cameras through the data processing module.
14. 14. The intrusion monitoring method according to claim 12, wherein the image capturing device comprises two visible light cameras, Wherein the step of generating the three-dimensional spatial data comprises: And calculating corresponding depth data according to the plurality of images provided by the two visible light cameras by the data processing module to serve as the three-dimensional space data.
15. 15. The intrusion monitoring method according to claim 12, wherein the step of generating the three-dimensional profile of the hangings comprises: segmenting a hanging outline of the hanging in the plurality of images by the artificial intelligence model, and Calculating, by the processor, the three-dimensional profile of the pendant from the pendant profile and the three-dimensional spatial data.
16. 16. The intrusion monitoring method according to claim 12, wherein the step of determining the security zone boundary comprises: And the marking module expands the boundary of the two-dimensional projection area outwards by a buffer distance to determine the boundary of the safety area.
17. 17. The intrusion monitoring method according to claim 16, further comprising: Providing measurement data by an inertial measurement unit arranged on the hanging object; calculating the swing amplitude of the hanging object through the processor; calculating, by the processor, a maximum horizontal offset from the wobble amplitude, and And taking the maximum horizontal offset as the buffer distance through the marking module so as to dynamically adjust the safety area boundary.
18. 18. The intrusion monitoring method according to claim 12, wherein the step of performing the pre-warning operation comprises: Judging whether the human invasion event occurs to the multiple images through the artificial intelligent model, and And determining whether to inform the control module to perform the early warning operation according to the judging result of the person invasion event by the processor.
19. 19. The intrusion monitoring method according to claim 18, wherein the step of performing the pre-warning operation further comprises: And the control module controls the audible and visual alarm to send out audible and visual alarm information.
20. 20. The intrusion monitoring method according to claim 18, wherein the step of performing the pre-warning operation further comprises: and controlling a bridge crane controller to operate the bridge crane through the control module.

Description

Intrusion monitoring system and intrusion monitoring method Technical Field The present invention relates to a monitoring system, and more particularly, to an intrusion monitoring system and an intrusion monitoring method. Background The traditional bridge crane safety monitoring system mainly adopts a fixed area monitoring (such as a static rectangular or circular guard zone) or a mechanical limiting device. However, the static safety area cannot be adapted to the dynamic changes of the size, the profile and the position of the suspended objects during the operation, so that the conventional safety monitoring system of the bridge crane is mainly problematic in that the actual dangerous range cannot be covered, and the protection is insufficient. Moreover, the traditional safety monitoring system of the bridge crane can easily cause excessive alarm or false alarm, thereby reducing the practical benefit of safety monitoring. Disclosure of Invention The invention provides an intrusion monitoring system and an intrusion monitoring method, which can effectively monitor whether a person approaches to a suspended object of a bridge crane. The intrusion monitoring system of the invention is suitable for monitoring bridge cranes. The intrusion monitoring system comprises an image acquisition device, a storage device and a processor. The image acquisition device is used for acquiring a plurality of images of the bridge crane. The storage device is used for storing the calculation module and the control module. The processor is coupled with the image acquisition device and the storage device and is used for executing the calculation module and the control module. The computing module generates a three-dimensional contour of a suspended object of the bridge crane according to the plurality of images, and determines a safety area boundary according to the three-dimensional contour of the suspended object. The computing module also carries out character recognition and judges whether a character invasion event occurs according to the boundary of the safety area so as to inform the control module of carrying out early warning operation. The intrusion monitoring method is suitable for monitoring the bridge crane. The intrusion monitoring method comprises the following steps of obtaining a plurality of images of the bridge crane through an image acquisition device, executing a calculation module and a control module through a processor, generating a three-dimensional outline of a hanging object of the bridge crane according to the plurality of images through the calculation module, determining a safety area boundary according to the three-dimensional outline of the hanging object through the calculation module, carrying out person identification through the calculation module, judging whether a person intrusion event occurs according to the safety area boundary, and informing the control module of early warning operation. Based on the above, the intrusion monitoring system and the intrusion monitoring method of the present invention can generate a three-dimensional profile of the suspended object, and determine the corresponding safety area boundary, so as to effectively determine whether a person intrusion event occurs, so as to perform an early warning operation. The foregoing features and advantages of the invention will be apparent from the following more particular description of the invention, as illustrated in the accompanying drawings. Drawings FIG. 1 is a schematic diagram of an intrusion monitoring system of an embodiment of the present invention. FIG. 2 is a schematic diagram of a plurality of modules of an embodiment of the present invention. Fig. 3 is a flow chart of an intrusion monitoring method of an embodiment of the invention. Fig. 4 is a schematic view of a bridge crane according to an embodiment of the invention. Wherein the symbols in the drawings are briefly described as follows: 40, the ground; 100 parts of an intrusion monitoring system, 110 parts of a processor, 120 parts of a storage device, 121 parts of a calculation module, 1211 parts of a data processing module, 1212 parts of an artificial intelligent model, 1213 parts of a marking module, 122 parts of a control module, 130 parts of an image acquisition device, 140 parts of a controller, 150 parts of an inertia measurement unit, 400 parts of a bridge crane, 410 parts of a hanging object, theta parts of an angle, L parts of a swing length, dmax parts of a maximum horizontal offset, R1 and R2 parts of a boundary, S310-S350 parts of the step, and P1, P2 and P3 parts of a direction. Detailed Description In order that the invention may be more readily understood, the following specific examples are provided as illustrations of the true practice of the invention. In addition, wherever possible, the same reference numbers will be used throughout the drawings and the description to refer to the same or like parts. FIG. 1 is a schematic diagram of an in