Coal mine underground vehicle statistical system

Abstract

The embodiment of the invention discloses a coal mine underground vehicle statistical system. In a specific embodiment, the system comprises a network transmission module, a video analysis device, a monitoring terminal and a camera, the camera is configured with position information of a preset node of an underground roadway where the camera is located, and is used for shooting a to-be-recognized image; the video analysis device is used for acquiring the to-be-recognized images uploaded by the cameras, recognizing the vehicles in the to-be-recognized images, recognizing the advancing tracks, license plate numbers and cargo loading states of the vehicles, obtaining recognition results of the vehicles in the to-be-recognized images and uploading the recognition results to the monitoring terminal; the monitoring terminal is used for counting underground vehicles. According to the implementation mode, the cameras are arranged at important nodes such as the entrance and exit areas of the underground roadway, so that the information of the vehicles entering and exiting each area, the number of the current vehicles in each area and the specific vehicle information can be mastered in real time, the underground output capacity is mastered, scheduling is reasonable, the vehicle safety is improved, and the vehicles can be accurately recognized and counted.

Description

Technical Field

[0001] The present invention relates to the field of vehicle statistics, and more specifically, to a vehicle statistics system for underground coal mines. Background Art

[0002] At present, in the traditional underground working environment, due to the narrow space, insufficient light and complex environment, it is very difficult to monitor and track vehicles in real time. The underground production capacity is affected by many factors, including vehicle scheduling, transportation efficiency, etc. The lack of real-time and accurate data support makes it difficult to make scientific judgments on the evaluation of production capacity and scheduling decisions. In addition, the underground working environment is complex and changeable, and vehicle safety accidents occur from time to time. Vehicle safety hazards are difficult to discover and deal with in a timely manner.

[0003] On the other hand, the cleaning of coal mine inclined tunnels is done by mechanical and manual cleaning. The vehicles are transported to the ground for unloading by mining vehicles, and the cleaning of vehicles entering and leaving the mine is counted by a dedicated person. However, the counting efficiency of manual cleaning is low, it is easy to make mistakes, and it is a great waste of human resources. Summary of the invention

[0004] The object of the present invention is to provide a coal mine underground vehicle counting system for automatically counting underground vehicles, so as to solve at least one of the problems existing in the prior art.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A first aspect of the present invention provides a coal mine underground vehicle counting system, comprising:

[0007] A network transmission module, a video analysis device, a monitoring terminal, and cameras respectively arranged at a plurality of preset nodes in underground tunnels;

[0008] The camera is configured with the location information of the preset node of the underground tunnel where the camera is located, and is used to shoot and upload the image to be identified of the preset node of the underground tunnel where the camera is located to the video analysis device through the network transmission module; the image to be identified includes the location information of the preset node of the underground tunnel where the camera is located;

[0009] The video analysis device is used to obtain the images to be identified uploaded by each camera through the network transmission module, and determine the preset node of the underground tunnel where the camera that uploaded the image to be identified is located according to the image to be identified; identify the vehicle in each image to be identified and identify the vehicle's travel trajectory, license plate number and cargo status, obtain the identification result of the vehicle in each image to be identified and upload it to the monitoring terminal;

[0010] The monitoring terminal is used to store and output the recognition results of the vehicles in each image to be recognized uploaded by the video analysis device and count the underground vehicles according to the recognition results.

[0011] Furthermore, the camera is an intrinsically safe image processing camera for use in mines.

[0012] Furthermore, the preset nodes include vehicle entrance and exit areas.

[0013] Further, the video analysis device includes an acquisition module, a vehicle identification module, a trajectory tracking module, a license plate recognition module, and a cargo status recognition module;

[0014] The acquisition module is used to acquire the images to be identified taken by each camera through the network transmission module;

[0015] The vehicle identification module is used to classify and identify the images to be identified acquired by the acquisition module based on the first machine learning model, so as to determine whether there is a vehicle in the images to be identified, and to extract the position and outline of the vehicle;

[0016] The trajectory tracking module is used to track the moving trajectory of the vehicle based on the tracking algorithm of the Kalman filter after the vehicle recognition module determines that there is a vehicle in the image to be recognized;

[0017] The license plate recognition module is used to further recognize the vehicle's license plate based on the image to be recognized at the position and outline of the vehicle extracted by the vehicle recognition module;

[0018] The cargo state recognition module is used to further classify and recognize the image to be recognized at the position and outline of the vehicle extracted by the vehicle recognition module based on the second machine learning model to determine whether the vehicle is empty or loaded.

[0019] Furthermore, the first machine learning model and the second machine learning model are convolutional neural network models respectively.

[0020] Furthermore, before the trajectory tracking module is used to track the moving trajectory of the vehicle based on the tracking algorithm of the Kalman filter after the vehicle identification module determines that there is a vehicle in the image to be identified, the trajectory tracking module is also used to perform histogram equalization processing on the image to be identified.

[0021] Furthermore, the license plate recognition module includes a license plate positioning module, a character segmentation module and a character recognition module;

[0022] The license plate positioning module is used to further extract the license plate area from the image to be identified at the position and outline of the vehicle extracted by the vehicle identification module;

[0023] The character segmentation module is used to segment the license plate area into individual characters;

[0024] The character recognition module is used to perform normalization processing and feature extraction on the segmented individual characters respectively, and to identify the characters by matching them with a preset character database template through a third machine learning model.

[0025] Furthermore, the license plate recognition module also includes a license plate correction module;

[0026] The license plate correction module is used to correct the license plate area after the license plate positioning module extracts the license plate area, so as to remove deformation and noise of the license plate area.

[0027] Furthermore, the third machine learning model is selected from one of a support vector machine model and a neural network model.

[0028] Furthermore, the monitoring terminal includes a monitoring module and a counting module;

[0029] The monitoring module is used to store and output the recognition results of vehicles in each image to be recognized uploaded by the video analysis device;

[0030] The counting module is used to count the underground vehicles according to the recognition result.

[0031] The beneficial effects of the present invention are as follows:

[0032] The present invention sets up cameras at important nodes in underground tunnels, such as entrance and exit areas. The images sent carry the location information of the cameras, so that the information of vehicles entering and exiting each area and the current number of vehicles and specific vehicle information in each area can be obtained in real time to understand the underground production capacity, make reasonable scheduling, and improve vehicle safety.

[0033] The present invention obtains the image to be identified through a video analysis device, and based on the identification of the vehicle, further identifies the vehicle's travel trajectory, license plate number, cargo status and other data to obtain the identification result of the vehicle in the image to be identified; the monitoring terminal automatically counts according to the identification result.

[0034] The present invention realizes real-time and automatic monitoring of vehicles by saving and monitoring the recognition results such as the vehicle's travel trajectory, license plate number and cargo status in the image to be recognized. It has high recognition efficiency, good recognition effect and high accuracy, which greatly improves the recognition effect of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The specific implementation modes of the present invention are further described in detail below in conjunction with the accompanying drawings.

[0036] Figure 1 A diagram showing an exemplary system architecture in which one embodiment of the present invention may be applied.

[0037] Figure 2The display content of the display terminal on the monitoring terminal provided by one embodiment of the present invention is shown. DETAILED DESCRIPTION

[0038] In order to explain the present invention more clearly, the present invention is further described below in conjunction with embodiments and drawings. Similar components in the drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content specifically described below is illustrative rather than restrictive, and the protection scope of the present invention should not be limited thereto.

[0039] like Figure 1 and Figure 2 As shown, an embodiment of the present disclosure provides a vehicle counting system for underground coal mines, comprising:

[0040] A network transmission module 2, a video analysis device 4, a monitoring terminal 3, and cameras 1 respectively arranged at a plurality of preset nodes in underground tunnels;

[0041] The camera 1 is configured with the location information of the preset node of the underground tunnel where the camera 1 is located, and is used to shoot and upload the image to be identified of the preset node of the underground tunnel where the camera 1 is located to the video analysis device 4 through the network transmission module 2; the image to be identified includes the location information of the preset node of the underground tunnel where the camera 1 is located;

[0042] The video analysis device 4 is used to obtain the images to be identified uploaded by each camera 1 through the network transmission module 2, and determine the preset node of the underground tunnel where the camera that uploaded the image to be identified is located according to the image to be identified; identify the vehicle in each image to be identified and identify the vehicle's travel trajectory, license plate number and cargo status, obtain the identification result of the vehicle in each image to be identified and upload it to the monitoring terminal 3;

[0043] The monitoring terminal 3 is used to store and output the recognition results of the vehicles in each image to be recognized uploaded by the video analysis device 4 and count the underground vehicles according to the recognition results.

[0044] The present invention sets up a camera 1 at important nodes in underground tunnels such as entrance and exit areas. The images sent carry the location information of the camera 1. The vehicle information entering and exiting each area and the current number of vehicles and specific vehicle information in each area can be obtained in real time to grasp the underground production capacity, make reasonable scheduling, and improve vehicle safety.

[0045] The present disclosure obtains the image to be identified through the video analysis device 4, and on the basis of identifying the vehicle, further identifies the vehicle's travel trajectory, license plate number, cargo status and other data to obtain the identification result of the vehicle in the image to be identified; the monitoring terminal 3 automatically counts according to the identification result.

[0046] In a specific implementation, the camera 1 is connected to the network transmission module 2 via a ring network.

[0047] In a possible implementation, the camera 1 is an intrinsically safe image processing camera 1 for use in mines.

[0048] The intrinsically safe image processing camera 1 for mining is specially designed for dangerous environments such as coal mines. It has explosion-proof characteristics to ensure safe use in flammable and explosive environments such as gas and coal dust. It has a compact structure, small size and light weight, and is suitable for use in narrow spaces such as underground coal mines; and the camera 1 has the characteristics of waterproof, dustproof, drop-proof, shockproof, scratch-proof, external force impact-proof, anti-static, etc., and can adapt to various harsh environments. And the imaging is clear and accurate. With its explosion-proof characteristics, environmental adaptability, high image quality, rich functions, excellent transmission performance, intelligent functions and ease of use, the intrinsically safe image processing camera 1 for mining plays an important role in dangerous environments such as coal mines, providing clear, reliable and stable video monitoring for coal mine safety production.

[0049] In one possible implementation, the preset node includes a vehicle entrance and exit area.

[0050] In a possible implementation, the network transmission module 2 is selected from one or more of a switch, a wireless bridge, and a wireless AP. Considering the complex environment underground, the present disclosure can use a combination of switches, wireless bridges, and wireless APs (Wireless Access Points) for communication. In the present disclosure, when there are 10 or more wireless APs, the present disclosure also provides a wireless AC (Wireless Access Point Controller) to manage each wireless AP.

[0051] In a possible implementation, the video analysis device 4 includes an acquisition module, a vehicle identification module, a trajectory tracking module, a license plate recognition module, and a cargo state recognition module;

[0052] The acquisition module is used to acquire the image to be identified taken by each camera 1 through the network transmission module 2;

[0053] The vehicle identification module is used to classify and identify the images to be identified acquired by the acquisition module based on the first machine learning model, so as to determine whether there is a vehicle in the images to be identified, and to extract the position and outline of the vehicle;

[0054] The trajectory tracking module is used to track the moving trajectory of the vehicle based on the tracking algorithm of the Kalman filter after the vehicle recognition module determines that there is a vehicle in the image to be recognized;

[0055] The license plate recognition module is used to further recognize the vehicle's license plate based on the image to be recognized at the position and outline of the vehicle extracted by the vehicle recognition module;

[0056] The cargo state recognition module is used to further classify and recognize the image to be recognized at the position and outline of the vehicle extracted by the vehicle recognition module based on the second machine learning model to determine whether the vehicle is empty or loaded.

[0057] In a specific implementation, the monitoring terminal 3 determines whether the vehicle is empty or loaded according to the cargo condition of the vehicle, and thereby determines whether the vehicle is entering or exiting, wherein the vehicle is empty when entering and loaded when exiting. Thus, the number of vehicles entering and the number of vehicles exiting can be further determined.

[0058] In one possible implementation, the first machine learning model and the second machine learning model are respectively convolutional neural network models.

[0059] In one possible implementation, before the trajectory tracking module is used to track the vehicle's trajectory based on a Kalman filter tracking algorithm after the vehicle identification module determines that there is a vehicle in the image to be identified, the trajectory tracking module is also used to perform histogram equalization processing on the image to be identified.

[0060] Since the histogram of an image in a dark environment is usually concentrated in a low-brightness area, the present disclosure can enhance the contrast of the image through histogram equalization, making the details in the image clearer, so as to further improve the effect of the trajectory tracking module on tracking the vehicle's moving trajectory based on the tracking algorithm of the Kalman filter.

[0061] In a specific embodiment, the area where vehicles enter or exit is a coal mine cleaning inclined lane; all vehicles need to enter each coal mine cleaning inclined lane through a preset node in the underground lane, and also need to exit each coal mine cleaning inclined lane through a preset node in the underground lane. When there are two or more vehicles, by tracking the vehicle's travel trajectory, the coal mine cleaning inclined lane that the corresponding vehicle enters or exits can be determined based on the different vehicle travel trajectories. Further, the monitoring module in the monitoring terminal 3 obtains the travel trajectory of the corresponding vehicle in the identification result, and compares it with the preset trajectory leading to each coal mine cleaning inclined lane, and obtains the preset trajectory leading to the coal mine cleaning inclined lane that is closest to the travel trajectory of the corresponding vehicle, so as to identify the coal mine cleaning inclined lane that the vehicle enters or exits.

[0062] In a possible implementation, the license plate recognition module includes a license plate positioning module, a character segmentation module and a character recognition module;

[0063] The license plate positioning module is used to further extract the license plate area from the image to be identified at the position and outline of the vehicle extracted by the vehicle identification module; in a specific implementation, the license plate area extraction method is usually based on the texture, color, shape and other features of the license plate, and generally uses projection analysis, connected domain analysis and machine learning algorithms for extraction.

[0064] The character segmentation module is used to segment the license plate area into individual characters; commonly used algorithms include connected domain analysis, projection analysis, character clustering and template matching, etc.;

[0065] The character recognition module is used to perform normalization processing and feature extraction on the segmented individual characters respectively, and to identify the characters by matching them with a preset character database template through a third machine learning model.

[0066] In one possible implementation, the license plate recognition module further includes a license plate correction module;

[0067] The license plate correction module is used to correct the license plate area after the license plate positioning module extracts the license plate area to remove deformation and noise in the license plate area. More specifically, after the license plate area is extracted, the license plate area is corrected to facilitate subsequent character recognition. Common correction methods include Hough Transform, rotation projection and principal component analysis.

[0068] In one possible implementation, the third machine learning model is selected from one of a support vector machine model and a neural network model.

[0069] In a possible implementation, the monitoring terminal 3 includes a monitoring module and a counting module;

[0070] The monitoring module is used to store and output the recognition results of the vehicles in each image to be recognized uploaded by the video analysis device 4;

[0071] The counting module is used to count the underground vehicles according to the recognition result.

[0072] The present invention realizes real-time and automatic monitoring of vehicles by saving and monitoring the recognition results such as the vehicle's travel trajectory, license plate number and cargo status in the image to be recognized. It has high recognition efficiency, good recognition effect and high accuracy, which greatly improves the recognition effect of the vehicle.

[0073] In the description of the present invention, it should be noted that the terms "upper", "lower", etc. indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific position, be constructed and operated in a specific position, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0074] It should also be noted that, in the description of the present invention, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0075] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the embodiments here. All obvious changes or modifications derived from the technical solution of the present invention are still within the protection scope of the present invention.

Claims

1. A vehicle statistics system for underground coal mines, characterized in that: include: A network transmission module, a video analysis device, a monitoring terminal, and cameras respectively arranged at a plurality of preset nodes in underground tunnels; The camera is configured with the location information of the preset node of the underground tunnel where the camera is located, and is used to shoot and upload the image to be identified of the preset node of the underground tunnel where the camera is located to the video analysis device through the network transmission module; the image to be identified includes the location information of the preset node of the underground tunnel where the camera is located; The video analysis device is used to obtain the images to be identified uploaded by each camera through the network transmission module, and determine the preset node of the underground tunnel where the camera that uploaded the image to be identified is located according to the image to be identified; identify the vehicle in each image to be identified and identify the vehicle's travel trajectory, license plate number and cargo status, obtain the identification result of the vehicle in each image to be identified and upload it to the monitoring terminal; The monitoring terminal is used to store and output the recognition results of the vehicles in each image to be recognized uploaded by the video analysis device and count the underground vehicles according to the recognition results.

2. The underground vehicle counting system of coal mine according to claim 1, characterized in that: The camera is an intrinsically safe image processing camera for use in mines.

3. The underground vehicle counting system of coal mine according to claim 1, characterized in that: The preset nodes include vehicle entrance and exit areas.

4. The underground vehicle counting system of coal mine according to claim 1, characterized in that: The video analysis device includes an acquisition module, a vehicle identification module, a trajectory tracking module, a license plate recognition module, and a cargo status recognition module; The acquisition module is used to acquire the image to be identified uploaded by each camera through the network transmission module; The vehicle identification module is used to classify and identify the images to be identified acquired by the acquisition module based on the first machine learning model, so as to determine whether there is a vehicle in the images to be identified, and to extract the position and outline of the vehicle; The trajectory tracking module is used to track the moving trajectory of the vehicle based on the tracking algorithm of the Kalman filter after the vehicle recognition module determines that there is a vehicle in the image to be recognized; The license plate recognition module is used to further recognize the vehicle's license plate based on the image to be recognized at the position and outline of the vehicle extracted by the vehicle recognition module; The cargo state recognition module is used to further classify and recognize the image to be recognized at the position and outline of the vehicle extracted by the vehicle recognition module based on the second machine learning model to determine whether the vehicle is empty or loaded.

5. The underground vehicle counting system of coal mine according to claim 4, characterized in that: The first machine learning model and the second machine learning model are convolutional neural network models respectively.

6. The underground vehicle counting system of coal mine according to claim 4, characterized in that: The trajectory tracking module is used to track the moving trajectory of the vehicle based on the tracking algorithm of the Kalman filter after the vehicle identification module determines that there is a vehicle in the image to be identified, and the trajectory tracking module is also used to perform histogram equalization processing on the image to be identified.

7. The underground vehicle counting system of coal mine according to claim 4, characterized in that: The license plate recognition module includes a license plate positioning module, a character segmentation module and a character recognition module; The license plate positioning module is used to further extract the license plate area from the image to be identified at the position and outline of the vehicle extracted by the vehicle identification module; The character segmentation module is used to segment the license plate area into individual characters; The character recognition module is used to perform normalization processing and feature extraction on the segmented individual characters respectively, and to identify the characters by matching them with a preset character database template through a third machine learning model.

8. The underground vehicle counting system of coal mine according to claim 7, characterized in that: The license plate recognition module also includes a license plate correction module; The license plate correction module is used to correct the license plate area after the license plate positioning module extracts the license plate area, so as to remove deformation and noise of the license plate area.

9. The underground vehicle counting system of coal mine according to claim 7, characterized in that: The third machine learning model is selected from a support vector machine model and a neural network model.

10. The underground vehicle counting system of coal mine according to claim 1, characterized in that: The monitoring terminal includes a monitoring module and a counting module; The monitoring module is used to store and output the recognition results of vehicles in each image to be recognized uploaded by the video analysis device; The counting module is used to count the underground vehicles according to the recognition result.

Images