A multi-view AI video monitoring device adapted to weighbridge scenarios

By using a multi-view AI video monitoring device, the problem of misjudgment in the weighbridge weighing system of the steel industry has been solved, achieving accurate vehicle positioning, personnel identity control and security against unauthorized entry, improving the accuracy and safety of the weighing process, and supporting full-process traceability and unmanned management.

CN123123539APending Publication Date: 2026-11-17INNER MONGOLIA BAOTOU STEEL UNION
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611028914.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-07-10
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Weighbridge systems in the steel industry are susceptible to dust, fog, vehicle obstruction, and severe weather, resulting in a high rate of misjudgment, an inability to accurately determine whether a vehicle is fully on the weighbridge, and a lack of effective anti-cheating measures.

Method used

Employing a multi-view AI video monitoring device, including close-up cameras, wide-angle cameras, and security cameras, combined with an edge computing processing unit and an intelligent interlocking control module, it achieves accurate vehicle positioning, personnel identity/quantity control, and security against intrusion, and deeply integrates with the weighing system through AI algorithm analysis.

Benefits of technology

It achieves accuracy and stability in vehicle detection, prevents unauthorized intrusion and cheating, provides full-process traceability management, improves the accuracy and security of the weighing process, and realizes fully automated anti-cheating and unmanned management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123123539A_ABST
    Figure CN123123539A_ABST
Patent Text Reader

Abstract

This invention relates to a multi-view AI video monitoring device adapted for weighbridge scenarios, comprising: a close-range camera for capturing images of the driver's cab of a target vehicle; a wide-angle camera for capturing the tire positions of the target vehicle; and an edge computing processing unit, communicatively connected to the close-range camera, for determining whether the number of people in the driver's cab exceeds a preset threshold based on the images of the driver's cab, and blocking the weighing process when the number of people in the driver's cab exceeds the preset threshold; the edge computing processing unit is also communicatively connected to the wide-angle camera for determining whether the tire positions are within the effective area of ​​the weighbridge, and blocking the weighing process when the tire positions are not within the effective area of ​​the weighbridge. This invention, through multi-camera panoramic visual perception and AI intelligent algorithm analysis, achieves accurate vehicle positioning detection, personnel identity / quantity control, security against unauthorized entry, and deep integration with the weighing system, achieving fully automated anti-cheating and full-process traceability.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of weighbridge technology, specifically to a multi-view AI video monitoring device adapted to weighbridge scenarios. Background Technology

[0002] In the steel industry, the processes of raw material entry, finished product exit, and material transfer all rely on automated weighbridges for weighing and measurement. Weighing data is the core basis for enterprise material accounting, cost control, trade settlement, and production scheduling. The accuracy, standardization, and safety of the weighing process directly affect the enterprise's economic benefits and production management order. Due to the special environment of steel production plants, characterized by high dust concentrations, heavy fog, complex operating conditions, frequent vehicle traffic, and chaotic personnel flow, extremely high requirements are placed on the stability and accuracy of vehicle weighing and detection.

[0003] Currently, truck scale weighing systems in the steel industry generally use infrared beam detectors and inductive loop detectors to detect vehicle positions. These devices are susceptible to dust, fog, vehicle obstructions, and inclement weather, resulting in a high false alarm rate and an inability to accurately determine whether a vehicle has fully entered the weighbridge. Summary of the Invention

[0004] To address the aforementioned issues, the purpose of this invention is to provide a multi-view AI video monitoring device adapted to weighbridge scenarios.

[0005] A multi-view AI video monitoring device adapted for weighbridge scenarios includes:

[0006] A close-up camera is used to capture images of the driver's cab of the target vehicle;

[0007] A wide-angle camera is used to capture the tire position of the target vehicle;

[0008] An edge computing processing unit is communicatively connected to the near-field camera and is used to determine whether the number of people in the driver's cab exceeds a preset threshold based on the image inside the target vehicle's cab. When the number of people in the driver's cab exceeds the preset threshold, the weighing process is blocked. The edge computing processing unit is also communicatively connected to the wide-angle camera and is used to determine whether the tire position is within the effective area of ​​the weighing platform. When the tire position is not within the effective area of ​​the weighing platform, the weighing process is blocked.

[0009] Preferred options also include:

[0010] A security camera is used to collect images of the weighing area; the edge computing processing unit is communicatively connected to the security camera and is used to determine whether there is unauthorized intrusion into the weighing area based on the images of the weighing area, and to block the weighing process when unauthorized intrusion occurs.

[0011] Preferred options also include:

[0012] The LED fill light automatically wakes up when close-up cameras, wide-angle cameras, and security cameras are in use.

[0013] Preferred options also include:

[0014] The intelligent interlocking control module is communicatively connected to the edge computing processing unit. When the edge computing processing unit outputs an interruption to the weighing process, it controls the barrier gate to close, the traffic lights to flash, and the audible and visual alarms to activate.

[0015] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0016] This invention relates to a multi-view AI video monitoring device adapted to weighbridge scenarios. Compared with existing technologies, this invention achieves accurate vehicle positioning detection, personnel identity / quantity control, security against intrusion, and deep linkage with the weighing system through multi-camera panoramic visual perception and AI intelligent algorithm analysis, thus achieving fully automatic anti-cheating and full-process traceability.

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This invention provides a working principle diagram of a multi-view AI video monitoring device adapted to weighbridge scenarios;

[0020] Figure 2 This is a schematic diagram of a multi-view AI video monitoring device adapted to weighbridge scenarios provided by the present invention.

[0021] Symbol explanation:

[0022] 1. First security camera; 2. Second security camera; 3. First wide-angle camera; 4. Second wide-angle camera; 5. Close-up camera. Detailed Implementation

[0023] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0024] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0025] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0026] Please see Figure 1-2 This invention provides a multi-view AI video monitoring device adapted to weighbridge scenarios, comprising:

[0027] A close-up camera is used to capture images of the driver's cab of the target vehicle;

[0028] A wide-angle camera is used to capture the tire position of the target vehicle;

[0029] An edge computing processing unit is communicatively connected to the near-field camera and is used to determine whether the number of people in the driver's cab exceeds a preset threshold based on the image inside the target vehicle's cab. When the number of people in the driver's cab exceeds the preset threshold, the weighing process is blocked. The edge computing processing unit is also communicatively connected to the wide-angle camera and is used to determine whether the tire position is within the effective area of ​​the weighing platform. When the tire position is not within the effective area of ​​the weighing platform, the weighing process is blocked.

[0030] A security camera is used to collect images of the weighing area; the edge computing processing unit is communicatively connected to the security camera and is used to determine whether there is unauthorized intrusion into the weighing area based on the images of the weighing area, and to block the weighing process when unauthorized intrusion occurs.

[0031] Furthermore, it also includes:

[0032] The LED fill light automatically wakes up when close-up cameras, wide-angle cameras, and security cameras are in use.

[0033] The intelligent interlocking control module is communicatively connected to the edge computing processing unit. When the edge computing processing unit outputs an interruption to the weighing process, it controls the barrier gate to close, the traffic lights to flash, and the audible and visual alarms to activate.

[0034] The principle of the present invention will be further explained below with reference to a specific embodiment:

[0035] This device consists of three main parts: "perception layer hardware, computing power layer core, and interaction layer software," with the specific structure as follows:

[0036] (1) Hardware perception layer (multi-view camera matrix)

[0037] Close-up camera 5 in the driver's cab: Installed directly in front or to the side of the driver's cab, using a wide dynamic range lens with a resolution of 4 megapixels or higher. Specifically designed to capture images inside the driver's cab, using AI algorithms to identify the number of people inside and extract the driver's facial features.

[0038] Two cameras are installed to identify tire positions in the weighing area: a first wide-angle camera 3 and a second wide-angle camera 4, positioned at opposite ends of the weighbridge (platform), covering the positions of the front and rear tires. These cameras identify tire positions and determine whether the vehicle has fully entered the effective weighing area.

[0039] Security cameras around the weighing area: Security camera 1 and security camera 2 are installed diagonally opposite the scale for intrusion detection, establishing a virtual warning zone. Real-time monitoring of the weighing area is conducted to check for unauthorized intrusion.

[0040] Intelligent supplementary lighting device: Equipped with LED intelligent supplementary lighting, synchronized with the camera trigger signal to ensure clear imaging 24 hours a day.

[0041] (2) Computing power and control core layer

[0042] The industrial-grade edge computing box, model NF5468M6, is a server with a built-in high-performance AI inference chip and integrated GPU acceleration module. It includes a built-in algorithm library (containing human detection, face recognition, vehicle contour recognition, and intrusion detection analysis algorithms). It performs real-time AI analysis of video streams locally, outputting low-latency judgment results (whether there is a person, whether it is the same person, whether it is being weighed), avoiding the lag of cloud processing.

[0043] Data storage module: Built-in high-capacity solid-state drive (SSD) or external NAS network storage. Used to store video streams, AI-captured images, weighing data, and facial feature databases, supporting timestamp-synchronized archiving.

[0044] (3) Data interaction and software interface layer

[0045] Multi-protocol communication interfaces: Equipped with multiple industrial communication interfaces such as RS485 / RS232, TCP / IP, Modbus, and HTTP. One end connects to the existing weighing control system (host computer), and the other end connects to the ERP system / enterprise management cloud platform.

[0046] Intelligent interlocking control module: Built-in logic judgment unit, configurable interlocking rules (e.g., number of people > 1 || face recognition failure || not fully on the scale = weighing prohibited). Outputs switch signals (IO signals) to directly control the operation of the barrier gate, traffic lights, and audible and visual alarms.

[0047] Based on the above structure, this device achieves intelligent monitoring and control of the weighbridge through the following steps:

[0048] 1. Video Acquisition and Triggering: When a vehicle approaches the weighbridge, the system camera automatically wakes up, the supplementary light turns on, and the real-time video stream is acquired and transmitted to the edge computing box.

[0049] 2. AI Intelligent Analysis:

[0050] (1) Personnel analysis: The close-range camera identifies the number of people in the driver's cab. If the number exceeds the threshold (e.g., >1 person), a violation signal is sent.

[0051] (2) Identity verification: When an empty vehicle is weighed, facial features are recorded, and when a loaded vehicle is weighed, the facial features are compared in real time to determine whether the driver is the same person.

[0052] (3) Position detection: The panoramic camera analyzes the edge of the vehicle to determine whether the tires are completely within the weighing platform.

[0053] (4) Intrusion detection: Continuously analyze the virtual area of ​​the weighbridge to identify whether any unauthorized personnel have entered.

[0054] 3. Weighing interlock control:

[0055] (1) The box performs a logical AND operation between the above AI analysis results and the weighing program.

[0056] (2) Normal process: All inspection items pass -> Computer reads weight data -> Saves document -> LED screen prompts and voice broadcast release.

[0057] (3) Abnormal process: If any detection item fails (such as face mismatch) -> the box outputs an interlock blocking signal -> the LED screen prompts and the voice broadcast prohibits the generation of weighing slips.

[0058] 4. Data traceability and reporting:

[0059] (1) All videos, images, weight data, and AI results are packaged and stored according to timestamps.

[0060] (2) Regularly synchronize the data to the ERP system and conduct weight deviation comparison analysis.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] 1. High accuracy and strong stability: Using AI vision algorithms to replace traditional physical sensors, it is not affected by dust, rain, snow, or strong light, solving the industry problems of "incomplete weighing" and "false triggering by light source beam". The vehicle detection accuracy rate can reach over 99%.

[0063] 2. Enhanced anti-cheating features: Implements dual identity authentication for both vehicle and driver, effectively preventing violations such as driver switching and overloading, and ensuring the safety of enterprise material management.

[0064] 3. Full-process traceability: Video, images, and weight data are stored in a unified manner, providing tamper-proof evidence for auditing, inspection, and dispute resolution, thereby improving management compliance.

[0065] 4. Achieve intelligent closed-loop: Directly integrate AI recognition results into the weighing interlock to reduce manual monitoring costs and achieve fully automated, unmanned management of the weighing process.

[0066] 5. Good compatibility and scalability: The device has reserved standard industrial interfaces, which can be quickly connected to existing edge boxes (industrial control computers), weighing instruments and ERP systems, facilitating smooth upgrades in the future.

[0067] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A multi-view AI video monitoring device adapted to weighbridge scenarios, characterized in that, include: A close-up camera is used to capture images of the driver's cab of the target vehicle; A wide-angle camera is used to capture the tire position of the target vehicle; An edge computing processing unit is communicatively connected to the near-field camera and is used to determine whether the number of people in the driver's cab exceeds a preset threshold based on the image inside the target vehicle's cab. When the number of people in the driver's cab exceeds the preset threshold, the weighing process is blocked. The edge computing processing unit is also communicatively connected to the wide-angle camera and is used to determine whether the tire position is within the effective area of ​​the weighing platform. When the tire position is not within the effective area of ​​the weighing platform, the weighing process is blocked.

2. The multi-view AI video monitoring device adapted to weighbridge scenarios according to claim 1, characterized in that, Also includes: Security cameras are used to capture images of the weighing area; The edge computing processing unit is communicatively connected to the security camera and is used to determine whether there is unauthorized intrusion into the weighing area based on the image of the weighing area. When unauthorized intrusion into the weighing area occurs, the weighing process is blocked.

3. The multi-view AI video monitoring device adapted to weighbridge scenarios according to claim 2, characterized in that, Also includes: The LED fill light automatically wakes up when close-up cameras, wide-angle cameras, and security cameras are in use.

4. The multi-view AI video monitoring device adapted to weighbridge scenarios according to claim 3, characterized in that, Also includes: The intelligent interlocking control module is communicatively connected to the edge computing processing unit. When the edge computing processing unit outputs an interruption to the weighing process, it controls the barrier gate to close, the traffic lights to flash, and the audible and visual alarms to activate.

5. The multi-view AI video monitoring device adapted to weighbridge scenarios according to claim 1, characterized in that, The edge computing processing unit is a server with the model number NF5468M6.