A personnel detection and safety control system based on YOLO algorithm
By using a YOLO-based personnel detection and safety control system, which utilizes wide-angle network cameras and PLC control, the problems of low accuracy and high latency in personnel detection in industrial automated production lines have been solved, achieving high-precision, low-latency personnel detection and safety control.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- QINGDAO HICORP GRP HEAVY IND SCI&TECH CO LTD
- Filing Date
- 2025-07-22
- Publication Date
- 2026-07-24
AI Technical Summary
Existing personnel detection systems in industrial automated production lines suffer from low accuracy and high latency. Traditional methods such as infrared sensors and lidar have blind spots and cannot identify dynamic postures, while image recognition algorithms are easily affected by changes in lighting.
The personnel detection and safety control system based on the YOLO algorithm includes a sensing module, an analysis module, and an execution module. It uses a wide-angle network camera to collect images, performs real-time detection through the YOLO model, and controls the production line to slow down or stop via PLC.
It achieves high-precision, low-latency personnel detection, directly links with production line control equipment, enables proactive risk avoidance, and improves the real-time performance and accuracy of safety control.
Smart Images
Figure CN224553682U_ABST
Abstract
Description
Technical Field
[0001] This utility model relates to the field of industrial automation safety control, specifically to a personnel detection and safety control system based on the YOLO algorithm. Background Technology
[0002] During production line operation, it is necessary to detect whether personnel are close to the production line to avoid safety accidents. Traditional industrial automated production line personnel safety detection relies on infrared sensors or lidar, which has shortcomings such as blind spots, high false trigger rate, and inability to recognize dynamic postures.
[0003] Conventional image recognition algorithms (such as OpenCV background subtraction) are easily affected by changes in lighting and equipment occlusion in complex industrial scenarios, and their response delays are difficult to meet the requirements of real-time control.
[0004] Therefore, there is a need for a high-precision, low-latency personnel detection and safety control system based on the YOLO algorithm. Utility Model Content
[0005] The main objective of this invention is to provide a personnel detection and safety control system based on the YOLO algorithm, in order to solve the problems of low accuracy and delay in existing safety control systems.
[0006] To achieve the above objectives, this utility model provides a personnel detection and safety control system based on the YOLO algorithm. The system comprises a sensing module, an analysis module, and an execution module. The sensing module acquires real-time images of the production line, the analysis module analyzes the real-time images, and when a personnel is within the designated detection area of the real-time image, the analysis module issues an alarm signal. Upon receiving the alarm signal, the execution module controls the segment production line to decelerate and stop or cease operation.
[0007] Furthermore, the sensing module includes a monitoring switch and multiple wide-angle network cameras. The monitoring switch is connected to each wide-angle network camera, and the multiple wide-angle network cameras cover the entire operating area of the production line.
[0008] Furthermore, the analysis module includes: multiple detection modules, a display module, and an alarm module. Each wide-angle network camera is connected to one detection module, and the wide-angle network camera transmits the images it reads to the detection module. The detection module detects in real time whether a person is within the designated detection area. The display module is used to draw the detection area of the wide-angle network camera and to display the real-time detection images, summarizing the results from multiple detection modules into a single window. The alarm module communicates with the execution module, sending the judgment results from the detection modules to the execution module.
[0009] Furthermore, all detection modules are connected to a display module, and all detection modules are also connected to an alarm module.
[0010] Furthermore, the detection module integrates the YOLO model.
[0011] Furthermore, the execution module includes a PLC and a production line driver. The PLC receives detection signals and controls the segment production line to decelerate, stop, or cease operation.
[0012] Furthermore, the wide-angle network camera should be installed 3-5 meters above the ground at a tilt angle of 30°.
[0013] Furthermore, wide-angle network cameras are deployed on the top and sides of the production line operating area.
[0014] This utility model has the following beneficial effects:
[0015] When the video stream is input to the detection module, the module uses the integrated YOLO model for image recognition. When a person is detected within the designated detection area, the module outputs a person bounding box and sends a detection signal to the PLC. The PLC then executes logic control to decelerate and stop the vehicle. The system provided by this invention achieves high-precision, low-latency personnel detection and directly links with production line control equipment to achieve proactive risk avoidance. Attached Figure Description
[0016] To more clearly illustrate the specific embodiments of this utility model or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this utility model. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:
[0017] Figure 1 The schematic diagram of the personnel detection and safety control system based on the YOLO algorithm of this utility model is shown. Detailed Implementation
[0018] The technical solution of this utility model will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this utility model. Based on the embodiments of this utility model, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this utility model.
[0019] like Figure 1The personnel detection and safety control system based on the YOLO algorithm shown includes a sensing module, an analysis module, and an execution module. The sensing module collects real-time images of the production line, the analysis module analyzes the real-time images, and when a person is in the designated detection area of the real-time image, the analysis module issues an alarm signal. After receiving the alarm signal, the execution module controls the segment production line to decelerate and stop or cease operation.
[0020] Specifically, the sensing module includes a monitoring switch and multiple wide-angle network cameras. The monitoring switch is connected to each wide-angle network camera, and the multiple wide-angle network cameras cover the entire operating area of the production line.
[0021] Specifically, the analysis module includes: multiple detection modules, a display module, and an alarm module. Each wide-angle network camera is connected to one detection module, and the wide-angle network camera transmits the images it reads to the detection module. The detection module detects in real time whether a person is within the designated detection area. The display module is used to draw the detection area of the wide-angle network camera and to display the real-time detection images, summarizing the results from multiple detection modules into a single window. The alarm module communicates with the execution module, sending the judgment results from the detection modules to the execution module.
[0022] Specifically, all detection modules are connected to a display module, and all detection modules are also connected to an alarm module.
[0023] Specifically, the detection module integrates the YOLO model.
[0024] Specifically, the execution module includes a PLC and a production line driver. The PLC receives detection signals and controls the segment production line to decelerate, stop, or cease operation to ensure personnel safety.
[0025] Specifically, wide-angle network cameras should be installed 3-5 meters above the ground at a tilt angle of 30°.
[0026] Specifically, wide-angle network cameras are deployed on the top and sides of the production line operating area.
[0027] Specifically, the wide-angle network camera selected is the Hikvision DS-2CD3 series, with 4 megapixels and IP66 protection.
[0028] When the video stream is input to the detection module, the module uses the integrated YOLO model for image recognition. When a person is detected within the designated detection area, the module outputs a person bounding box and sends a detection signal to the PLC. The PLC then executes logic control to decelerate and stop the vehicle. The system provided by this invention achieves high-precision, low-latency personnel detection and directly links with production line control equipment to achieve proactive risk avoidance.
[0029] Of course, the above description is not intended to limit the present utility model, and the present utility model is not limited to the examples given above. Any changes, modifications, additions or substitutions made by those skilled in the art within the scope of the present utility model should also fall within the protection scope of the present utility model.
Claims
1. A personnel detection and safety control system based on the YOLO algorithm, characterized in that, include: The system consists of a sensing module, an analysis module, and an execution module. The sensing module collects real-time images of the production line, the analysis module analyzes these images, and when a person is within the designated detection area of the real-time image, the analysis module issues an alarm signal. Upon receiving the alarm signal, the execution module controls the production line to slow down, stop, or cease operation.
2. The personnel detection and safety control system based on the YOLO algorithm according to claim 1, characterized in that, The sensing module includes a monitoring switch and multiple wide-angle network cameras. The monitoring switch is connected to each wide-angle network camera, and the multiple wide-angle network cameras cover the entire operating area of the production line.
3. The personnel detection and safety control system based on the YOLO algorithm according to claim 1, characterized in that, The analysis module includes multiple detection modules, a display module, and an alarm module. Each wide-angle network camera is connected to one detection module, and the wide-angle network camera transmits the images it reads to the detection module. The detection module detects in real time whether a person is within the designated detection area. The display module is used to draw the detection area of the wide-angle network camera and to display the real-time detection images, summarizing the results from multiple detection modules into a single window. The alarm module communicates with the execution module, sending the judgment results from the detection modules to the execution module.
4. A personnel detection and safety control system based on the YOLO algorithm according to claim 3, characterized in that, All detection modules are connected to a display module, and all detection modules are also connected to an alarm module.
5. A personnel detection and safety control system based on the YOLO algorithm as described in claim 4, characterized in that, The detection module integrates the YOLO model.
6. A personnel detection and safety control system based on the YOLO algorithm as described in claim 1, characterized in that, The execution module includes a PLC and a production line driver. The PLC receives detection signals and controls the segment production line to decelerate, stop, or cease operation.
7. A personnel detection and safety control system based on the YOLO algorithm as described in claim 3, characterized in that, Wide-angle network cameras should be installed 3-5 meters above the ground at a tilt angle of 30°.
8. A personnel detection and safety control system based on the YOLO algorithm as described in claim 3, characterized in that, Wide-angle network cameras are deployed on the top and sides of the production line operating area.