Real-time monitoring system for stockpiling workshop based on visual identification and visual identification method

Abstract

The invention discloses a real-time monitoring system for a stockpiling workshop based on visual identification and a visual identification method. The real-time monitoring system comprises a workshop module, a control module and a monitoring module. The workshop module comprises a gypsum stacking workshop, a cross beam, a bridge gripper guide rail, a bridge gripper cart and a bridge gripper, and the bridge gripper is provided with at least one pair of grab buckets and used for grabbing materials. The control module comprises a controller, a CPU and a displayer and is used for controlling bridge grabbing operation and processing monitoring data. The monitoring module comprises a plurality of cameras and is used for acquiring real-time video data of a workshop and identifying dangerous conditions. According to the system, a workshop is divided into a dangerous area and other areas, whether vehicles and personnel enter the dangerous area illegally or not is judged through the visual identification technology, and automatic alarming and shutdown are achieved. The system can monitor the total number of personnel and vehicles in the workshop, and the safety of the workshop is ensured by comparing the information of the personnel entering and exiting the workshop through the camera. The main shape and structure characteristics of the device comprise a cross beam, a bridge claw guide rail, a bridge claw cart, a bridge claw, a camera and the like, and the device is suitable for real-time monitoring of a stockpiling workshop.

Description

Technical Field

[0001] The present invention relates to the technical field, and in particular to a real-time monitoring system and a visual recognition method for a stockpile workshop based on visual recognition. Background Art

[0002] In traditional material storage workshop management, workshop safety is often ensured by manual on-site inspections or simple monitoring equipment. Although these methods can monitor workshop conditions to a certain extent, they have obvious shortcomings, such as low efficiency and poor real-time performance of manual inspections, and the inability to fully cover every corner of the workshop; simple monitoring equipment cannot intelligently identify dangerous situations and issue early warnings or alarm signals in a timely manner, resulting in a higher risk of accidents.

[0003] Although the existing patent solution has improved the monitoring effect of the stockpile workshop to a certain extent, it still has certain limitations. On this basis, this patent proposes a real-time monitoring system for the stockpile workshop based on visual recognition, which brings the following advantages by optimizing the system structure, improving the recognition accuracy and response speed: The system structure is more reasonable, covering the workshop module, control module and monitoring module, which can fully cover every corner of the workshop to ensure that there are no blind spots in monitoring; the use of visual recognition technology has improved the recognition accuracy and reduced the false alarm rate; it has realized real-time monitoring and early warning functions, effectively reducing the risk of accidents; the system has a fast response speed and can quickly send out alarm signals when dangerous situations occur to ensure the safety of the workshop; combined with face recognition technology, it realizes the management of personnel in the workshop and improves safety. Summary of the invention

[0004] Purpose of the invention: To solve the problems existing in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: A real-time monitoring system for a stockpiling workshop based on visual recognition, characterized in that it comprises: a workshop module, a control module and a monitoring module, wherein the workshop module comprises: a gypsum stockpiling workshop, a crossbeam, a bridge grab guide rail, a bridge grab trolley and a bridge grab, wherein the crossbeam is evenly arranged on the top of the gypsum stockpiling workshop, the bridge grab guide rail is arranged on the crossbeam, a bridge grab trolley is movably arranged on the bridge grab guide rail, the bridge grab trolley is connected to a bridge grab, and the bridge grab comprises at least one pair of grab buckets, and the pair of grab buckets encloses and forms a grabbing space; The control module includes: a controller, a CPU and a display, wherein the controller is used to control the bridge grabbing operation, the CPU is used to process and collect the controller control information and the monitoring module video information and feed back the processed information to the display, and the display is used to watch the collected video information; The monitoring module includes at least two first cameras, which are arranged on the crossbeam, and at least two first cameras are arranged at intervals. The monitoring module is communicatively connected to the control module, and the working steps of the monitoring module are as follows: Step 1: The first camera obtains real-time video data of the gypsum stacking workshop and forms a video stream; Step 2: The video stream is transmitted to the CPU for data processing, and the real-time working conditions of the gypsum stacking workshop are read out through the display; Step 3: The control center can automatically or manually determine whether a dangerous situation has occurred. When a dangerous situation exists, the control center will issue an alarm and shut down the machine, waiting for relevant personnel to intervene.

[0006] Furthermore, the gypsum stockpiling workshop is divided into the first dangerous area and other areas; The first dangerous area is located at the discharge point. When the control module controls the bridge grab to perform a grabbing operation, the vertical downward portion of the bridge grab trolley is divided into a second dangerous area.

[0007] Furthermore, in step 3, the control module visually recognizes and reads the following working conditions in the gypsum stacking workshop and determines it as a dangerous situation: 1) Vehicles or personnel enter the second danger zone; 2) Vehicles or personnel stay in the first danger zone for more than 10 minutes; When the above two situations occur, the control module issues an alarm to shut down, identifies the corresponding alarm target and issues a corresponding alarm signal.

[0008] Furthermore, it is characterized in that when the control module in step three visually recognizes that there are vehicles and personnel in other areas of the gypsum stacking workshop, it is determined as a warning situation. At this time, the control module sends a warning signal and increases the frequency of the control module capturing images from the video stream transmitted from the first camera.

[0009] Furthermore, the gypsum stacking workshop is provided with an entrance and exit, and the entrance and exit is provided with a second camera, the second camera is connected to the control module, and the control module reads the real-time entry and exit of personnel and vehicles in the gypsum stacking workshop through the video stream of the second camera, and the control module obtains the total number of personnel or vehicles located in the gypsum stacking workshop.

[0010] Furthermore, in step three, when the control module visually recognizes and reads that there is a working condition in the gypsum stacking workshop where the total number of personnel or vehicles in the gypsum stacking workshop obtained by the control center through the first camera is not equal to the total number of personnel or vehicles in the gypsum stacking workshop obtained by the control module through the second camera, it is determined to be a dangerous situation, and the control center then sends a corresponding alarm signal.

[0011] Furthermore, the control module reads and intercepts facial information of personnel entering and exiting the gypsum stacking workshop through the video stream of the second camera; the control module compares the intercepted facial information with the facial information of the staff pre-stored in the control module, and when it is determined that the personnel entering and exiting the gypsum stacking workshop does not match the entered staff, the control module sends a corresponding alarm signal.

[0012] Furthermore, the beam located above the first dangerous area is provided with a third camera, and the camera range of the third camera covers the entire first dangerous area; A fourth camera is arranged vertically below the bridge grab trolley, and the camera range of the fourth camera covers the entire operating range of the grab bucket.

[0013] The visual recognition method is applied to the above-mentioned real-time monitoring system for a stockpile workshop based on visual recognition, including: S1: Image acquisition: The CPU in the control module captures an image from the video stream of the first camera and / or the second camera and / or the third camera and / or the fourth camera and displays the image on a display; S2: Image acquisition: The CPU in the control module captures an image from the video stream of the first camera and / or the second camera and / or the third camera and / or the fourth camera and displays the image on the display; S3: Feature matching: The CPU compares the extracted features with the pre-learned features to find the most similar features. S4: Classification: The CPU performs classification matching based on the feature recognition results to determine which category the target object belongs to.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The real-time monitoring system for a stockpile workshop based on visual recognition provided by the present application has the following beneficial effects compared with the prior art: Firstly, by integrating workshop module, control module and monitoring module, the system can monitor the operation status of the gypsum stacking workshop in real time, effectively improving the operation safety. Specifically, by setting at least two first cameras, it can fully cover every corner of the workshop, ensure no blind spot monitoring, and timely detect and warn of various potential dangers, such as people or vehicles mistakenly entering dangerous areas, thereby greatly reducing the probability of safety accidents.

[0015] Secondly, the control module of this system has automatic or manual analysis functions. When a dangerous situation is detected, it can quickly issue an alarm shutdown signal to notify relevant personnel to intervene in time. This not only ensures the safety of operators, but also avoids equipment damage and productivity loss caused by accidents.

[0016] Thirdly, this system divides the gypsum stockpiling workshop into different areas and formulates corresponding monitoring strategies according to the characteristics of the areas, such as focusing on monitoring the first danger area and the second danger area, and conducting early warning monitoring on other areas, thereby realizing refined management and improving monitoring efficiency and accuracy.

[0017] In addition, this system also has a face recognition function. By comparing the facial information of people entering and leaving the workshop, it can effectively prevent unauthorized people from entering, further improving the safety management level of the workshop.

[0018] In terms of technical effects, the visual recognition method adopted by this system, including image acquisition, feature matching and classification, can accurately identify the target object and respond quickly. The application of this technology not only improves the real-time and accuracy of the monitoring system, but also reduces the false alarm rate and improves the operating efficiency.

[0019] Finally, the system is easy to maintain and expand. Its modular design makes it easy to replace and upgrade each component, meeting the needs of modern industrial production for flexibility and reliability.

[0020] In summary, the real-time monitoring system for stockpiling workshops based on visual recognition in this application has shown significant beneficial effects in improving operational safety, reducing accidents, improving monitoring efficiency, ensuring personnel safety, and improving operational efficiency. The realization of these effects not only helps to promote the development of stockpiling workshops towards intelligence and automation, but also provides new technical ideas for safety management in related industries. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a structural diagram of a gypsum stacking workshop; Figure 2 It is a schematic diagram of the three-dimensional structure of the bridge grab trolley and the bridge grab; Figure 3 This is a schematic diagram of the area division of the gypsum stockpiling workshop.

[0022] In the figure: 1. Gypsum stacking workshop; 11. Other areas; 12. First dangerous area; 13. Second dangerous area; 2. Crossbeam; 3. First camera; 4. Bridge grab trolley; 5. Bridge grab guide rail; 6. Bridge grab; 7. Third camera; 8. Fourth camera. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0024] In this article, the terms "upper, lower, inside, outside" and the like are established based on the positional relationships shown in the drawings. The corresponding positional relationships may also change depending on the drawings, and therefore cannot be understood as absolute limitations on the scope of protection; moreover, relational terms such as "first" and "second" and the like are merely used to distinguish one component from another with the same name, and do not necessarily require or imply any actual relationship or order between these components.

[0025] The applicant designs Figure 1-3 The real-time monitoring system for a stockpiling workshop based on visual recognition shown in the figure includes: a workshop module, a control module and a monitoring module. The workshop module includes: a gypsum stockpiling workshop 1, a crossbeam 2, a bridge grab 6 guide rail 5, a bridge grab 6 trolley 4 and a bridge grab 6. The crossbeam 2 is evenly arranged on the top of the gypsum stockpiling workshop 1. The bridge grab 6 guide rail 5 is arranged on the crossbeam 2. The bridge grab 6 trolley 4 is movably arranged on the bridge grab 6 guide rail 5. The bridge grab 6 trolley 4 is connected to the bridge grab 6. The bridge grab 6 includes at least one pair of grab buckets, and the pair of grab buckets enclose to form a grabbing space. The control module includes: a controller, a CPU and a display. The controller is used to control the operation of the bridge grab 6. The CPU is used to process and collect the control information of the controller and the video information of the monitoring module and feed back the processed information to the display. The display is used to watch the collected video information. The monitoring module includes at least two first cameras 3, the first cameras 3 are arranged on the beam 2, and the at least two first cameras are arranged at intervals. The monitoring module is communicatively connected to the control module, and the working steps of the monitoring module are as follows: Step 1: The first camera 3 obtains the real-time video data of the gypsum stacking workshop 1 and forms a video stream; Step 2: The video stream is transmitted to the CPU for data processing, and the real-time working conditions of the gypsum stacking workshop 1 are read out through the display; Step 3: The control center can automatically or manually judge whether there is a dangerous situation. When there is a dangerous situation, the control center issues an alarm and shuts down, waiting for relevant staff to intervene.

[0026] Specifically, several gypsum stacks are piled up in the gypsum stacking workshop 1. The control center operates in the gypsum stacking workshop 1 through the bridge grab 6 to transport gypsum. Two first cameras 3 are set at appropriate positions in the gypsum stacking workshop 11 so that the camera range covers the entire ground area of ​​the gypsum stacking workshop 11. Of course, when the camera range is not enough to cover the entire ground area of ​​the gypsum stacking workshop 1, several more first cameras 3 can be used appropriately. The video stream obtained by the first camera 3 is used to monitor the working conditions in the gypsum stacking workshop 1 in real time, accurately judge dangerous situations, and take remedial measures in time when dangerous situations occur, so as to nip the danger in the bud and enhance the operating safety in the gypsum stacking workshop 1.

[0027] Communication connection refers to a wired or wireless connection mode that can transfer information to each other, including but not limited to electrical connection, WiFi connection, etc. The control module is preferably a CPU. A visual recognition module is provided in the control module, and the visual recognition module performs the following functions: intercepting images, performing visual analysis, and obtaining analysis results. The visual recognition module and the control module are mature existing technologies, and their structures and working principles are not described in detail here.

[0028] The control module divides the gypsum stockpiling workshop 1 into a first danger zone 12 and other areas 11 according to the video stream of the gypsum stockpiling workshop 1; the first danger zone 12 is located at the discharge point, and when the control module controls the bridge grab 6 to perform a grabbing operation, the vertical lower part of the bridge grab 6 trolley 4 is divided into a second danger zone 13; the second danger zone 13 moves with the movement of the bridge grab 6 trolley 4, and the second danger zone 13 has the highest priority. When the second danger zone 13 overlaps with other areas 11, it is still designated as the second danger zone 13. When the second danger zone 13 overlaps with the first danger zone 12, the area is both the first danger zone 12 and the second danger zone 13.

[0029] In this embodiment, the control module in step 3 visually identifies and reads the following working conditions in the gypsum stacking workshop 1 and determines it as a dangerous situation: 1) Vehicles or personnel enter the second danger zone 13; 2) Vehicles or personnel stay in the first danger zone 12 for more than 10 minutes; When the above two situations occur, the control module issues an alarm and stops, identifies the corresponding alarm target and issues a corresponding alarm signal; situation 1) The corresponding alarm signal is "someone breaks into the second dangerous area 13". When the bridge grab 6 is operating, it is strictly forbidden for people or vehicles to break under it, which may easily cause safety accidents; situation 2) The corresponding alarm signal is "abnormal warning of the first dangerous area 12". The first dangerous area 12 is the discharging area. Long-term stay is likely to cause safety accidents and affect the discharging rate. The stay time can be changed in real time according to the working conditions.

[0030] In this embodiment, further, in step three, when the control module visually recognizes and reads that there are vehicles and personnel in other areas 11 in the gypsum stacking workshop 1, it is determined to be a warning situation. At this time, the control module sends a warning signal and increases the frequency of the control module capturing images from the video stream transmitted from the first camera 3.

[0031] Further, in this embodiment, the gypsum stacking workshop 1 is provided with an entrance and exit, and a second camera is provided at the entrance and exit. The second camera is connected to the control module, and the control module reads the real-time entry and exit of personnel and vehicles in the gypsum stacking workshop 1 through the video stream of the second camera, and the control module obtains the total number of personnel or vehicles located in the gypsum stacking workshop 1, and a warning sign is provided at the exit.

[0032] This embodiment goes one step further. In step three, the control module visually recognizes and reads that the total number of people or vehicles in the gypsum stockpiling workshop 1 obtained by the control center through the first camera 3 is not equal to the total number of people or vehicles in the gypsum stockpiling workshop 1 obtained by the control module through the second camera. It is determined to be a dangerous situation, and the control center sends a corresponding alarm signal. When the total number of people or vehicles is not equal, it can be determined according to the specific situation that someone has specially broken into the gypsum stockpiling workshop 1 or that someone is missing. At this time, a corresponding alarm signal needs to be issued, and the machine needs to be shut down when the situation is serious.

[0033] Furthermore, in this embodiment, the control module reads and intercepts the facial information of the personnel entering and exiting the gypsum stacking workshop 1 through the video stream of the second camera; the control module compares the intercepted facial information with the facial information of the staff pre-stored in the control module, and when it is determined that the personnel entering and exiting the gypsum stacking workshop 1 does not match the entered staff, the control module sends a corresponding alarm signal.

[0034] Furthermore, in this embodiment, the cross beam 2 located above the first dangerous area 12 is provided with a third camera 7, and the camera range of the third camera 7 covers the entire first dangerous area 12; the third camera 7 installed at a suitable position of the cross beam 2 covers the first dangerous area 12, further ensuring full coverage of the first dangerous area 12; a fourth camera 8 is provided vertically below the bridge grab 6 trolley 4, and the camera range of the fourth camera 8 covers the entire operating range of the grab bucket. The fourth camera 8 installed at a suitable position of the bridge grab 6 trolley 4 covers the operating area of ​​the grab bucket, fully considering the monitoring blind area that will be blocked by the grab bucket during the lifting process.

[0035] The visual recognition method is applied to the above-mentioned real-time monitoring system for a stockpile workshop based on visual recognition, and comprises the following steps: S1: Image acquisition: The CPU in the control module captures an image from the video stream of the first camera 3 and / or the second camera and / or the third camera 7 and / or the fourth camera 8 and displays the image on a display; S2: Image acquisition: The CPU in the control module captures an image from the video stream of the first camera 3 and / or the second camera and / or the third camera 7 and / or the fourth camera 8 and displays the image on the display; S3: Feature matching: The CPU compares the extracted features with the pre-learned features to find the most similar features. S4: Classification: The CPU performs classification matching based on the feature recognition results to determine which category the target object belongs to.

[0036] This application does not involve improvements in computer algorithms. The improved technical point is to divide the gypsum stockpiling workshop into a first dangerous area, a second dangerous area and other areas, so as to improve the alarm safety factor and avoid danger.

[0037] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A real-time monitoring system for a stockpile workshop based on visual recognition, characterized in that: include: A workshop module, a control module and a monitoring module, wherein the workshop module comprises: a gypsum stacking workshop, a crossbeam, a bridge grab guide rail, a bridge grab trolley and a bridge grab, wherein the crossbeam is evenly arranged on the top of the gypsum stacking workshop, the bridge grab guide rail is arranged on the crossbeam, a bridge grab trolley is movably arranged on the bridge grab guide rail, the bridge grab trolley is connected to a bridge grab, and the bridge grab comprises at least one pair of grab buckets, and the pair of grab buckets enclose a grabbing space; The control module includes: a controller, a CPU and a display, wherein the controller is used to control the bridge grabbing operation, the CPU is used to process and collect the controller control information and the monitoring module video information and feed back the processed information to the display, and the display is used to watch the collected video information; The monitoring module includes at least two first cameras, which are arranged on the crossbeam, and at least two first cameras are arranged at intervals. The monitoring module is communicatively connected to the control module, and the working steps of the monitoring module are as follows: Step 1: The first camera obtains real-time video data of the gypsum stacking workshop and forms a video stream; Step 2: The video stream is transmitted to the CPU for data processing, and the real-time working conditions of the gypsum stacking workshop are read out through the display; Step 3: The control center can automatically or manually determine whether a dangerous situation has occurred. When a dangerous situation exists, the control center will issue an alarm and shut down the machine, waiting for relevant personnel to intervene.

2. The real-time monitoring system for a stockpile workshop based on visual recognition according to claim 1 is characterized in that: Divide the gypsum stockpiling workshop into the first hazardous area and other areas; The first dangerous area is located at the discharge point. When the control module controls the bridge grab to perform a grabbing operation, the vertical downward portion of the bridge grab trolley is divided into a second dangerous area.

3. The real-time monitoring system for a stockpile workshop based on visual recognition according to claim 2 is characterized in that: In step 3, the control module visually recognizes and reads the following working conditions in the gypsum stacking workshop and determines it as a dangerous situation: 1) Vehicles or personnel enter the second danger zone; 2) Vehicles or personnel stay in the first danger zone for more than 10 minutes; When the above two situations occur, the control module issues an alarm to shut down, identifies the corresponding alarm target and issues a corresponding alarm signal.

4. The real-time monitoring system for a stockpile workshop based on visual recognition according to claim 2 is characterized in that: In step three, when the control module visually recognizes that there are vehicles and personnel in other areas of the gypsum stacking workshop, it is determined to be a warning situation. At this time, the control module sends a warning signal and increases the frequency of the control module capturing images from the video stream transmitted from the first camera.

5. The real-time monitoring system for a stockpile workshop based on visual recognition according to claim 1 is characterized in that: The gypsum stacking workshop is provided with an entrance and exit, and the entrance and exit is provided with a second camera, the second camera is connected to the control module, and the control module reads the real-time entry and exit of personnel and vehicles in the gypsum stacking workshop through the video stream of the second camera, and the control module obtains the total number of personnel or vehicles located in the gypsum stacking workshop.

6. The real-time monitoring system for a stockpile workshop based on visual recognition according to claim 5 is characterized in that: In step three, when the control module visually recognizes and reads that there is a working condition in the gypsum stacking workshop where the total number of personnel or vehicles in the gypsum stacking workshop obtained by the control center through the first camera is not equal to the total number of personnel or vehicles in the gypsum stacking workshop obtained by the control module through the second camera, it is determined to be a dangerous situation, and the control center sends a corresponding alarm signal.

7. The real-time monitoring system for a stockpile workshop based on visual recognition according to claim 5, characterized in that: The control module reads and intercepts facial information of personnel entering and exiting the gypsum stacking workshop through the video stream of the second camera; the control module compares the intercepted facial information with the facial information of the staff pre-stored in the control module, and when it is determined that the personnel entering and exiting the gypsum stacking workshop does not match the entered staff, the control module sends a corresponding alarm signal.

8. The real-time monitoring system for a stockpile workshop based on visual recognition according to claim 5, characterized in that: The crossbeam located above the first dangerous area is provided with a third camera, and the camera range of the third camera covers the entire first dangerous area; A fourth camera is arranged vertically below the bridge grab trolley, and the camera range of the fourth camera covers the entire operating range of the grab bucket.

9. A visual recognition method, applied to a real-time monitoring system for a stockpile workshop based on visual recognition according to any one of claims 1 to 8, characterized in that: include: S1: Image acquisition: The CPU in the control module captures an image from the video stream of the first camera and / or the second camera and / or the third camera and / or the fourth camera and displays the image on a display; S2: Image acquisition: The CPU in the control module captures an image from the video stream of the first camera and / or the second camera and / or the third camera and / or the fourth camera and displays the image on the display; S3: Feature matching: The CPU compares the extracted features with the pre-learned features to find the most similar features. S4: Classification: The CPU performs classification matching based on the feature recognition results to determine which category the target object belongs to.

Images