Apparatus and method for monitoring weighing violation of vehicle

Abstract

The present invention relates to an apparatus for monitoring a weighing violation of a vehicle and an operating method thereof and, more specifically, the apparatus comprises: a vehicle; a weighbridge for measuring the weight of the vehicle; one or more cameras for photographing the vehicle and the weighbridge; a detection device for detecting, by using artificial intelligence, whether the weight of the vehicle is normal on the basis of an image captured by the camera; and an alarm unit for notifying a driver of the vehicle of a weighing violation, and thus, the weighing violation may be automatically detected without manpower and notified to the driver.

Description

Vehicle weighing violation monitoring device and method

[0001] The present invention relates to a weighing violation monitoring device and method, and specifically to a device and method that detects weighing violations by analyzing images captured by a camera based on artificial intelligence.

[0002] In its dictionary definition, "gyegeun" refers to "measuring the weight of an object," and generally, it can mean measuring the weight of cargo inside a vehicle responsible for freight transport, such as a truck.

[0003] Generally, when cargo is brought in or taken out using cargo vehicles, the weight of the cargo is weighed, and costs or transportation fees based on that weight are calculated and managed accordingly.

[0004] Conventional weighing management involves placing a cargo vehicle onto a cargo vehicle scaler (a weight detection device that detects the weight of a cargo vehicle; hereinafter abbreviated as "weighing platform") to detect the weight of the cargo vehicle, detecting the weight when empty and when full, calculating the difference between the weight when empty and when full to obtain the actual weight of the cargo, and issuing a weighing certificate based on the actual weight.

[0005] In other words, in a conventional weighing system, when a cargo vehicle arrives at the cargo entry and exit point, the manager must recognize this, guide the vehicle to the weighing table to verify that the vehicle is in the correct position, and after verifying the position, enter the control room to perform weighing, issue a certificate, and then proceed to the vehicle to notify the driver, and only after the notification can the vehicle depart.

[0006] Furthermore, for this weighing process, not only must managers manually input and manage the type of vehicle by vehicle and company, but if the distance between the weighing station and the control room is long, unnecessary time is spent on the manager's travel, resulting in a problem of wasted manpower.

[0007] Meanwhile, although an attempt was made to perform weighing management using a vision system to solve the above-mentioned problems, this also only reaches the level of photographing trucks using cameras, and there are practical limitations because the manager must still perform the same task of checking the camera images and correcting the positions.

[0008] In addition, conventional weighing automation methods generally require additional devices because they perform operations based on tags such as RFID, and there is a limitation in that vision systems cannot be used for vehicles without tags, such as new vehicles.

[0009] (Patent Document 1) Korean Published Patent Application No. 10-2008-0041779 (Published May 14, 2008)

[0010] (Patent Document 2) Korean Registered Patent Publication No. 10-2425437 (Registered July 21, 2022)

[0011] The present invention aims to solve the problems regarding the above technical problem by providing a device and method of operation that use artificial intelligence to automatically recognize the location of a vehicle entering a weighbridge without wasting manpower and monitor weighing violations.

[0012] A vehicle weighing violation monitoring device according to an embodiment of the present invention for solving the above technical problem may include a vehicle, a weighing platform for measuring the weight of the vehicle, one or more cameras for photographing the vehicle and the weighing platform, a detection device that detects whether the vehicle is weighed normally based on an image captured by the camera using artificial intelligence, and an alarm unit that notifies the driver of the vehicle of whether there is a weighing violation.

[0013] Additionally, the detection device may include an image input unit into which an image captured by the camera is input, an object recognition unit that recognizes an object within the image, a determination unit that determines whether the object is the vehicle, a license plate recognition unit that recognizes the license plate of the vehicle, a position estimation unit that estimates the positions of the front, side, rear, front wheel, and rear wheel of the vehicle, an entry / exit recognition unit that recognizes the entry and exit of the vehicle to the weighing scale based on the positions, and a violation detection unit that determines whether the weighing is normal based on the positions.

[0014] In addition, the entry / exit recognition unit can recognize that a vehicle has entered if the center point of the front is within the coordinate range of the starting line of the weighing platform and the wheel position coincides with the starting line.

[0015] In addition, the violation detection unit can divide the weighing platform into multiple areas and detect whether weighing has occurred by comparing the position of the wheel with the position of the weighing platform for each of the multiple areas.

[0016] In addition, the alarm unit may notify the driver of the vehicle of whether there is a weighing violation by using one or more of sound and light.

[0017] In addition, it may further include a server connected to the above-mentioned detection device via wired or wireless communication, and storing and managing one or more of the following: whether the vehicle has violated weighing regulations, an image of the vehicle in case of a weighing violation, and the vehicle's entry and exit records.

[0018] In another aspect, a method for monitoring a weighing violation of a vehicle located on a weighing scale using a detection device according to an embodiment of the present invention for solving the above technical problem may include the steps of acquiring an image of the weighing scale taken using a camera, monitoring the entry of the vehicle and whether a weighing violation has occurred based on the image using artificial intelligence in the detection device, and an alarm unit notifying whether a weighing violation has occurred.

[0019] Additionally, the monitoring step may include the step of inputting the image into an image input unit, the step of recognizing an object within the image in an object recognition unit, the step of determining whether the object is the vehicle in a determination unit, the step of recognizing the license plate of the vehicle in a license plate recognition unit, the step of estimating the positions of the front, side, rear, front wheel, and rear wheel of the vehicle in a position estimation unit, the step of recognizing the entry of the vehicle into the weighing scale based on the position in an entry / exit recognition unit, and the step of determining whether the weighing is normal based on the position in a violation detection unit.

[0020] In addition, the step of recognizing entry can recognize that a vehicle has entered if the center point of the front is within the coordinate range of the starting line of the weighing platform and the wheel position coincides with the starting line.

[0021] In addition, the step of determining whether the weighing is normal may divide the weighing platform into multiple areas and detect whether the weighing is normal by comparing the position of the wheel and the position of the weighing platform for each of the multiple areas.

[0022] In addition, the step of notifying whether there is a weighing violation may notify the driver of the vehicle of the weighing violation using one or more of sound and light.

[0023] In addition, the method may further include a step of being connected to the detection device via wired or wireless communication and storing and managing one or more of the following on a server: whether the vehicle has violated weighing regulations, an image of the vehicle in case of a weighing violation, and the vehicle's entry and exit records.

[0024] A weighing violation monitoring device and method according to one embodiment of the present invention described above can automatically detect weighing violations and notify the driver without requiring manpower.

[0025] In addition, weighing violations can be automatically managed and classified on the server based on various criteria, such as by vehicle, time, and model, to obtain statistics.

[0026] FIG. 1 is a diagram showing the configuration of a weighing violation monitoring device according to one embodiment of the present invention.

[0027] FIG. 2 is a drawing specifically illustrating the structure of a detection device of a weighing violation monitoring device according to one embodiment of the present invention.

[0028] FIG. 3 is a diagram illustrating a method for recognizing the entry and exit of a vehicle in a weighing violation monitoring device according to an embodiment of the present invention.

[0029] FIG. 4 is a diagram illustrating a method for detecting the degree of entry of a vehicle in a weighing violation monitoring device according to an embodiment of the present invention.

[0030] FIG. 5 is a diagram illustrating a method for monitoring whether a weighing violation has occurred in a weighing violation monitoring device according to an embodiment of the present invention.

[0031] FIG. 6 is a flowchart illustrating a method for monitoring whether a weighing violation has occurred in a weighing violation monitoring device according to one embodiment of the present invention.

[0032] The present invention is capable of various modifications and may have various embodiments, and specific embodiments are illustrated in the drawings and described in detail.

[0033] However, this is not intended to limit the invention to specific embodiments, and it should be understood that it includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the invention.

[0034] The terms used in this application are used merely to describe specific embodiments and are not intended to limit the invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "having" are intended to specify the presence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0035] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0036] Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the attached drawings. In order to facilitate an overall understanding of the present invention, the same reference numerals are used for identical components in the drawings, and redundant descriptions of identical components are omitted.

[0037] FIG. 1 is a diagram showing the configuration of a weighing violation monitoring device according to one embodiment of the present invention.

[0038] A weighing violation monitoring device according to one embodiment of the present invention may include a vehicle (100), a weighing platform (200), a camera (300), a detection device (400), an alarm unit (500), and a server (600).

[0039] The vehicle (100) may include all types of means of transport capable of carrying cargo, excluding the driver and passengers, such as passenger cars, cargo trucks, pickup trucks, and trailers. Specifically, it may include all devices that transport cargo by driving on a road with the cargo loaded by rotating wheels (tires) using electric, hydrogen, fuel cells, internal combustion engines, fossil fuels, etc.

[0040] The weighing scale (200) is a device for measuring the weight of a vehicle (100) and may include all general weighing scales. It may refer to a device that detects the weight of a vehicle (100) by detecting the weight at one or more sensors located below the supporting plate when the vehicle (100) is placed on a supporting plate such as a steel plate, and calculates the detected weight based on a preset program.

[0041] The support plate can be formed as an underground or above-ground type. The underground type is formed at the same height as the ground and the sensor, etc. is located on the ground, while the above-ground type is formed at a position slightly higher than the ground and the sensor is located at a height similar to the ground. The underground and above-ground types each have their advantages and disadvantages.

[0042] The weighing platform (200) of the present invention can perform operations regardless of whether it is above ground or underground, and is not limited as long as it can perform weighing of a vehicle (100).

[0043] The camera (300) may be one or more imaging devices that capture the vehicle (100) and the weighing scale (200) to generate images, and may generate video and / or still images in a time series format.

[0044] A single camera (300) may be positioned at the upper center of the weighing platform (200) to photograph entry, exit, and location of the weighing platform (200), or may be positioned at the front and rear of the weighing platform (200), or may have one camera positioned at each corner of the weighing platform (200) to perform photography from four directions, and may be used without limitation on the number, shape, and location as long as it can photograph the entry, exit, and location of the vehicle (100).

[0045] In addition, the camera (300) in one embodiment of the present invention is exemplified as a general digital camera, but is not limited thereto and may include any shooting equipment capable of performing shooting, such as an infrared camera, an ultraviolet camera, or a black and white camera, and sensors such as radar, a laser sensor, a depth camera, a stereo camera, or LiDAR may also be additionally utilized as needed or optionally.

[0046] The detection device (400) can perform weighing of the vehicle (100) based on information collected from a sensor included in the weighing platform (200), detect the entry and exit of the vehicle (100) based on an image captured by a camera (300), recognize the license plate of the vehicle, and determine whether there is a weighing violation by recognizing the location of the vehicle.

[0047] A weighing violation means including abnormal behavior that is not normal during the process of measuring the weight of a vehicle (100), such as the vehicle (100) not being positioned in the correct location within the weighing platform (200) or the number of passengers in the vehicle changing before and after the weighing operation.

[0048] The detection device (400) can determine whether there is an entry, exit, and weighing violation of the vehicle (100) using a detection model including one or more artificial intelligences, and a detailed explanation is provided in Fig. 2 below.

[0049] When a weighing violation is detected by the detection device (400), the alarm unit (500) can convey the weighing violation to the driver of the vehicle (100) using one or more of sound or light, and can convey the violation to the manager in various forms such as sound, light, vibration, and pop-up by sending a message to the display (not shown) of the detection device (400) or to an electronic device (not shown) connected to the detection device (400).

[0050] The alarm unit (500) may include a speaker and may transmit a pre-set recorded message or the voice of a manager to the detection device (400). Additionally, the alarm unit (500) may be configured in the form of a display such as an LED to output a pre-set message, or configured in the form of a fluorescent light to briefly convey violation and normal status according to color, and the form is not limited as long as it can convey weighing violation details to the driver of the vehicle (100).

[0051] The server (600) can store one or more of the vehicle (100) type, model, entry time, weighing time, exit time, weighing violation details, weighing violation location, image at the time of weighing violation, and weighing result, and can classify and store and manage based on the vehicle's license plate.

[0052] The server (600) may perform operations in conjunction with one or more detection devices (400), may be located within the same electronic device as the detection device (400) within a closed network where no separate external communication is connected, and may be located without restriction as long as it can perform the operations of the server (600).

[0053] Additionally, for integrated management, the detection device (400) may be constructed as a centralized system. Specifically, when an electronic device performing a weighing operation of the weighing scale (200) acquires an image from the camera (300), the acquired image is transmitted to an external server (not shown) via wired or wireless communication, and a detection operation is performed by the detection device (400) included in the external server (not shown), and this is transmitted back to the electronic device to control the operation of the alarm unit (500).

[0054] FIG. 2 is a drawing specifically illustrating the structure of a detection device (400) of a weighing violation monitoring device according to one embodiment of the present invention.

[0055] A detection device (400) of a weighing violation monitoring device according to one embodiment of the present invention may include an image input unit (410), an object recognition unit (420), a discrimination unit (430), a license plate recognition unit (440), a location estimation unit (450), an entry / exit recognition unit (460), a violation detection unit (470), and a communication unit (480).

[0056] The image input unit (410) receives an image captured by the camera (300) and can change the format to enable smooth operation of the detection device (400).

[0057] For example, depending on the shape and type of the camera (300), video can be input in various formats and extensions, and in particular, video and still images may be captured and transmitted in different formats, and even if multiple cameras (300) are different models, they may be captured and transmitted in different formats, or depending on the settings, one camera (300) may capture video and another camera (300) may capture still images, so that the video can also be stored and transmitted in different formats.

[0058] In such cases, the operation of converting the video into a still image can be performed, or the video can be converted into a preset format to enable smooth operation in the detection device (400) and stored and managed.

[0059] In the following description, 'image' may refer to an image converted into a format that has been pre-set in the image input unit (410), and in the case of a video, may refer to a frame image divided into a time series.

[0060] The object recognition unit (420) detects objects within the image based on the image input unit (410) and can set a rectangular area of ​​interest for the detected objects.

[0061] The discrimination unit (430) can determine the type of objects recognized by the object recognition unit (420), and the types of objects can be broadly classified into people and vehicles. In the case of vehicles, the types can be classified based on size or cargo load, such as passenger cars, SUVs, small trucks, medium trucks, large trucks, trailers, and containers, but the operation can also be performed by simply distinguishing only between people and vehicles due to reasons such as operation speed.

[0062] The reason for distinguishing the types of vehicles will be explained again below, but the weighing violation monitoring device in one embodiment of the present invention can perform operations based on the position of the center of the vehicle and the tires, and since the position of the center of the vehicle and the tires is provided by each manufacturer, the position of the center of the vehicle and the tires can be recognized, thereby improving the operation speed of the detection device (400).

[0063] Power consumption of the detection device (400) can be saved by terminating the operation and switching to a standby state when the object detected as a result of the determination in the determination unit (430) is a person, and performing the following operation only when the detected object is a vehicle.

[0064] The license plate recognition unit (440) can recognize the license plate of a vehicle (100) when the determination unit (430) determines that an object within the area of ​​interest is a vehicle. Since the license plate of the vehicle (100) corresponds to the unique number of each vehicle, it can be used as a standard for storing weighing violation details for each vehicle in the server (600), or it can be used as a standard for calling up past weighing violation data in the server (600).

[0065] The license plate of the vehicle (100) may be configured by borrowing a license plate recognition system, such as one currently in use in a parking lot, and a detailed explanation will be omitted.

[0066] The position estimation unit (450) can be composed of a PIDNet capable of performing real-time semantic segmentation, and can predict the positions of the side, front, rear, front wheels, and rear wheels of the vehicle based on an image input from the image input unit (410), and in particular, can recognize the center point of the front to track the movement of the vehicle (100).

[0067] In addition, the coordinates of the lowest part of the wheel (min(y)) can be recognized as the contact surface between the wheel and the ground, and the wheel closest to the front part in the X-ray can be recognized as the front wheel.

[0068] The entry / exit recognition unit (460) can recognize when a vehicle (100) enters and exits the weighbridge (200).

[0069] FIG. 3 is a diagram illustrating a method for recognizing the entry and exit of a vehicle in an entry / exit recognition unit (460). As shown in FIG. 3 (a), if the vehicle (100) is within the x-coordinate range of the starting line (dotted line) of the weighing platform (200) and the contact surface of the front wheel coincides with the starting line, it can be recognized that the vehicle (100) is entering the weighing platform (200). As shown in FIG. 3 (b), if the vehicle (100) is within the x-coordinate range of the starting line (dotted line) based on the direction of travel of the weighing platform (200) and the contact surface of the front wheel coincides with the starting line, it can be recognized that the vehicle (100) has exited the weighing platform (200).

[0070] Additionally, when the entry / exit recognition unit (460) recognizes that the vehicle (100) is entering the weighing platform (200), it can send a notification to the manager that the vehicle (100) has entered and will perform weighing.

[0071] The following description describes the case where the vehicle (100) enters the weighing scale in the entry / exit recognition unit (460), but since exiting is the reverse order of entry and performs substantially the same operation, a detailed description regarding exiting is omitted and the description is intended to be given only in the case where entry is recognized.

[0072] FIG. 4 is a diagram illustrating a method for detecting the degree of entry of a vehicle in a weighing violation monitoring device. The entry / exit recognition unit (460) can divide the range from the start line to the end line of the weighing platform (200) into 0 to 100, divide the range into multiple areas by dividing it into preset ranges, and can recognize the entry of the vehicle (100) by recognizing contact with the contact surface of the vehicle (100) based on the start line of each area.

[0073] For example, it can be divided into five areas: 0~20, 21~40, 41~60, 61~80, and 81~100. A virtual line is drawn for each divided area, and the drawn line is recognized as the first to fifth starting line. When the center of the front of the vehicle and the contact surface of the wheel pass through the starting line, it can be recognized that the vehicle (100) has completed entering each area of ​​the weighing platform (200).

[0074] Additionally, the entry / exit recognition unit (460) can estimate the speed of the vehicle (100) using a Byte Tracker, and specifically, it can track the movement of the vehicle (100) by using a Byte Tracker together with an image of PIDNet, and estimate the speed of the vehicle based on the distance the vehicle (100) has moved based on the frame.

[0075] Additionally, the entry / exit recognition unit (460) can determine that the entry of the vehicle (100) is completed and weighing has started when the driver's hand is detected while the vehicle (100) is positioned on the weighing platform (200) using SimCLR (simple Contrastive Learning Representations), and can temporarily stop the operation of the entry / exit recognition unit (460) when it is determined that weighing has started.

[0076] FIG. 5 is a diagram illustrating a method for monitoring whether there is a weighing violation, where the left side of FIG. 5 illustrates a normal weighing state and the right side of FIG. 5 illustrates a weighing violation state.

[0077] Referring to FIG. 5, the violation detection unit (470) can perform operations simultaneously or sequentially with the entry / exit recognition unit (460), and when the entry / exit recognition unit (460) recognizes that the vehicle (100) is entering the weighing platform (200), the violation detection unit (470) can detect a weighing violation by comparing the position of the vehicle's wheels with the boundary line of the weighing platform (200).

[0078] Specifically, the violation detection unit (470) recognizes the boundary lines in the four directions (front, back, left, and right) of the weighing platform (200), compares the recognized boundary lines with the positions of the front and rear wheels of the vehicle (100), and if the wheels are all located within the boundary lines as a result of the comparison, it can be determined that the weighing is normal. Alternatively, if it detects that the wheels are in contact with the boundary lines of the weighing platform (200) or that the wheels are located outside the boundary lines, it can be determined that the weighing is a violation.

[0079] When the violation detection unit (470) determines that there is a weighing violation, it notifies the alarm unit (500) of the occurrence of the weighing violation and the location of the occurrence, so that the alarm unit (500) can notify the driver (100) of the weighing violation and also send the same message to the manager.

[0080] The violation detection unit (470) can terminate operation together with the entry / exit recognition unit (460) when it is determined that the exit of the vehicle (100) is completed.

[0081] In the above description, the entry / exit recognition unit (460) and the violation detection unit (470) were described separately for convenience of explanation; however, in actual operation, the entry / exit recognition unit (460) and the violation detection unit (470) generally operate simultaneously as a single component and are interconnected.

[0082] The communication unit (480) can perform communication with the detection device (400) and an external device, and the external device may include a weighing scale (200), a camera (300), an alarm unit (400), and a server (600), and additionally, although not disclosed in the drawing, it may perform communication with an electronic device (not shown) capable of controlling or monitoring the monitoring device (400) from the outside.

[0083] The communication unit (480) may be connected to an external device via a wired connection to perform operations, or may communicate with an external device using any wireless communication method such as Bluetooth, Wi-Fi, NFC, 3G, LTE, CDMA, NR, etc.

[0084] FIG. 6 is a flowchart illustrating a method for monitoring whether a weighing violation has occurred in a weighing violation monitoring device according to one embodiment of the present invention.

[0085] When an image captured by one or more cameras (300) capturing the weighing platform (200) is applied to the object recognition unit (420) through the image input unit (410), the object recognition unit (420) can recognize whether an object exists within the input image (S1100).

[0086] The above object may include all moving objects such as people and vehicles, and the object recognition unit (420) may set the detected object as a region of interest when the object is detected.

[0087] The determination unit (430) can determine the type of object recognized by the object recognition unit (420) (S1200).

[0088] If the type of object recognized in step S1200 is not a vehicle ('No' in step S1200), the operation of the detection device (400) can be stopped again, and the device can wait with only the operation of the image input unit (410) and the object recognition unit (420) activated.

[0089] If the type of object recognized in step S1200 is a vehicle ('yes' in step S1200), the position estimation unit (450) can estimate the positions of the front, side, rear and wheels—front wheels, rear wheels—of the vehicle (100) (S1300).

[0090] The position estimation unit (450) can be composed of a PIDNet capable of performing real-time semantic segmentation, and can predict the positions of the side, front, rear, front wheels, and rear wheels of the vehicle based on an image input from the image input unit (410), and in particular, can recognize the center point of the front to track the movement of the vehicle (100).

[0091] In addition, the coordinates of the lowest part of the wheel (min(y)) can be recognized as the contact surface between the wheel and the ground, and the wheel closest to the front part in the X-ray can be recognized as the front wheel.

[0092] The entry / exit recognition unit (460) can detect whether the vehicle (100) has entered the weighing platform (200) based on the position estimation result of the position estimation unit (450) (S1400).

[0093] In the above S1400 step, the method of detecting entry is such that if the center point of the front part is within the x-coordinate range of the starting line based on the starting line of the weighing platform (200) and the joint surface coincides with the starting line, it can be determined that the vehicle (100) has entered the weighing platform (200).

[0094] The entry / exit recognition unit (460) can notify the manager of the vehicle (100) entering the weighing platform (200) when the vehicle (100) enters the weighing platform (200) (S1500).

[0095] As a method of notifying the manager, a speaker (not shown) included in the detection device (400) can be used, or a method such as sound, light, vibration, or pop-up can be used to notify an electronic device (not shown) connected to the detection device (400) via wired or wireless communication, and any method can be utilized as long as it conveys information to the manager that the vehicle (100) has entered the weighing platform (200).

[0096] The entry / exit recognition unit (460) tracks the movement of the vehicle (100) entering the weighing platform (200) (S1600), and the violation detection unit (470) can determine whether the vehicle (100) is entering the weighing platform (200) normally (S1700).

[0097] In the above S1600 step, the range from the start line to the end line of the weighing platform (200) can be divided into 0 to 100, and divided into multiple areas based on the preset range, and the entry of the vehicle (100) can be recognized by recognizing contact with the contact surface of the vehicle (100) based on the start line of each area.

[0098] Additionally, the entry / exit recognition unit (460) can estimate the speed of the vehicle (100) using a Byte Tracker, and specifically, it can track the movement of the vehicle (100) by using a Byte Tracker together with an image of PIDNet, and estimate the speed of the vehicle based on the distance the vehicle (100) has moved based on the frame.

[0099] In the above S1700 step, the violation detection unit (470) recognizes the boundary lines in the four directions (front, back, left, and right) of the weighing platform (200), compares the recognized boundary lines with the positions of the front and rear wheels of the vehicle (100), and if the comparison result shows that all wheels are located within the boundary lines, it can be determined that it is a normal weighing. Alternatively, if it detects that the wheels are in contact with the boundary lines of the weighing platform (200) or that the wheels are located outside the boundary lines, it can be determined that it is a weighing violation.

[0100] When the violation detection unit (470) determines that there is a weighing violation (S1700’s ‘No’), it notifies the alarm unit (500) of the occurrence of the weighing violation and the location of the occurrence, so that the alarm unit (500) can notify the driver (100) of the weighing violation and also send the same message to the manager (S1800).

[0101] When the violation detection unit (470) does not detect a weighing violation, the entry / exit recognition unit (460) can use SimCLR (simple Contrastive Learning Representations) to determine that the entry of the vehicle (100) is complete and weighing has started when the driver's hand is recognized while the vehicle (100) is positioned on the weighing platform (200), and can perform the weighing operation (S1900).

[0102] When the weighing operation is completed, the departure of the vehicle (100) is detected in the reverse order of steps S1500 and S1600, and the completion of the vehicle (100) exit can be detected (S2000).

[0103] When the evacuation of the vehicle (100) is completed, it can be determined that the operation of the weighing scale (200) has been finished, and the relevant information can be stored in the server (600) (S2100).

[0104] The above-mentioned related information may include all information related to weighing operations, such as the vehicle number, type, entry time, exit time, whether there is a weighing violation, time of weighing violation, and an image of the weighing violation, and may be classified, stored, and managed by vehicle within the server (600).

[0105] As described above, the weighing violation monitoring device and method according to one embodiment of the present invention can automatically detect weighing violations and notify the driver without requiring manpower.

[0106] In addition, weighing violations can be automatically managed and classified on the server based on various criteria, such as by vehicle, time, and model, to obtain statistics.

[0107] The features, structures, effects, etc. described in the above-described embodiments are included in at least one embodiment of the present invention and are not necessarily limited to only one embodiment. Furthermore, the features, structures, effects, etc. exemplified in each embodiment may be combined or modified and implemented in other embodiments by a person skilled in the art to which the embodiments belong.

[0108] Therefore, details regarding such combinations and variations should be interpreted as being included within the scope of the present invention. Furthermore, although the above description has focused on embodiments, this is merely illustrative and does not limit the present invention. Those skilled in the art will understand that various modifications and applications not exemplified above are possible within the scope of the essential characteristics of the embodiments. For example, each component specifically shown in the embodiments may be modified and implemented. Differences related to such modifications and applications should be interpreted as being included within the scope of the present invention as defined in the appended claims.

[0109] By accurately detecting and notifying vehicle weighing violations in real time, it is possible to induce normal weighing operations without consuming additional manpower, and to manage vehicles performing weighing through the storage and management of the entire weighing process.

[0110] 100: Vehicle

[0111] 200: Weighing scale

[0112] 300: Camera

[0113] 400: Detector

[0114] 410: Image input section

[0115] 420: Object Recognition Unit

[0116] 430: Discriminant

[0117] 440: License plate recognition unit

[0118] 450: Position Estimation Unit

[0119] 460: Entry / Exit Recognition Unit

[0120] 470: Violation detection unit

[0121] 480: Communications Department

[0122] 500: Alarm section

[0123] 600: Server

Claims

1. Vehicle; A weighbridge for measuring the weight of the above vehicle; One or more cameras for photographing the above vehicle and the above weighbridge; A detection device that detects whether the vehicle is weighed normally based on an image captured by the camera using artificial intelligence; and An alarm unit notifying the driver of the above vehicle of whether there is a weighing violation; A vehicle weighing violation monitoring device including 2. In Paragraph 1, The above-mentioned sensing device is, An image input unit into which an image captured by the above camera is input; An object recognition unit that recognizes objects within the above image; A determination unit that determines whether the above object is the above vehicle; A license plate recognition unit that recognizes the license plate of the above vehicle; A position estimation unit for estimating the positions of the front, side, rear, front wheels, and rear wheels of the above vehicle; An entry / exit recognition unit that recognizes the entry and exit of the vehicle to the weighing scale based on the above location; and A violation detection unit that determines whether the weighing is normal based on the above location; A vehicle weighing violation monitoring device characterized by further including 3. In Paragraph 2, The above entry / exit recognition unit is, A vehicle weighing violation monitoring device characterized by recognizing that a vehicle has entered when the center point of the front is within the coordinate range of the starting line of the weighing platform and the wheel position coincides with the starting line.

4. In Paragraph 2, The above violation detection unit is, A vehicle weighing violation monitoring device characterized by dividing the weighing platform into multiple regions and detecting whether weighing has occurred by comparing the position of the wheel and the position of the weighing platform for each of the multiple regions.

5. In Paragraph 1, The above alarm unit is, A vehicle weighing violation monitoring device characterized by notifying the driver of the vehicle of whether there is a weighing violation using one or more of sound and light.

6. In Paragraph 1, It is connected to the above-mentioned detection device via wired or wireless communication, and A vehicle weighing violation monitoring device characterized by further including a server that stores and manages one or more of the following: whether the vehicle has a weighing violation, an image at the time of the weighing violation, and the entry / exit records of the vehicle.

7. A method for monitoring weighing violations of a vehicle located on a weighing platform using a detection device, A step of generating an image of the above-mentioned weighing scale captured by a camera; A step of monitoring whether the vehicle's entry and weighing violations are in violation based on the image using artificial intelligence in the above detection device; and A step of notifying the alarm unit of whether there is a weighing violation of the above vehicle; A method for monitoring vehicle weighing violations including 8. In Paragraph 7, The above monitoring step is, A step in which the above image is input into an image input unit; A step of recognizing an object within the image in the object recognition unit; A step of determining whether the object is the vehicle in the determination unit; A step of recognizing the license plate of the vehicle in a license plate recognition unit; A step of estimating the positions of the front, side, rear, front wheels, and rear wheels of the vehicle in the position estimation unit; A step of recognizing the entry of the vehicle into the weighbridge based on the above location in the entry / exit recognition unit; and A step of determining whether the weighing is normal based on the above location in the violation detection unit; A method for monitoring vehicle weighing violations characterized by further including 9. In Paragraph 8, The step of recognizing the above entry is, A method for monitoring vehicle weighing violations, characterized by recognizing that a vehicle has entered when the center point of the front is within the coordinate range of the starting line of the weighing platform and the wheel position coincides with the starting line.

10. In Paragraph 8, The step of determining whether the above-mentioned normal weighing is valid is, A method for monitoring weighing violations of a vehicle, characterized by dividing the weighing platform into multiple regions and detecting whether weighing has occurred by comparing the position of the wheel and the position of the weighing platform for each of the multiple regions.

11. In Paragraph 1, The step of notifying whether the above-mentioned weighing violation occurred is, A method for monitoring weighing violations of a vehicle, characterized by notifying the driver of the vehicle of whether there is a weighing violation using one or more of sound and light.

12. In Paragraph 1, It is connected to the above-mentioned detection device via wired or wireless communication, and A method for monitoring a vehicle's weighing violation, characterized by further including the step of storing and managing one or more of the following on a server: whether the vehicle has a weighing violation, an image at the time of the weighing violation, and an entry / exit record of the vehicle.

Images