Method, device and equipment for monitoring oil tank of truck and medium

Abstract

The invention relates to the technical field of motor vehicles, and discloses a method, device and equipment for monitoring a truck fuel tank and a medium, and the method comprises the steps: obtaining an image of an area where the fuel tank is located; face recognition is carried out based on the image, and if a result obtained by face recognition is other people except the preset people, action feature extraction is carried out based on the image; if it is judged that the gasoline conveying action possibly exists through the extracted action characteristics, whether the truck is in the gasoline station or not is judged, and if not, an alarm is given. According to the invention, if the fact that other personnel except the preset personnel approach the oil tank is identified, a further feature extraction and judgment process is triggered, so that an illegal oil stealing behavior is effectively prevented, and alarms generated when the preset personnel approach the oil tank can be reduced; under the condition that the action of conveying the gasoline exists, if the truck is judged to be in the gasoline station, an alarm is not given, so that the high-frequency condition that workers in the gasoline station are helped to refueling can be eliminated, and the probability of false alarm is greatly reduced.

Description

Technical Field

[0001] The present invention relates to the field of motor vehicle technology, and in particular to a method, a device, a equipment and a medium for monitoring a truck fuel tank. Background Art

[0002] It is a common and serious problem for truck drivers to encounter "fuel thieves" during their trips. "Fuel thieves" are oil thieves. Since the fuel tanks of large trucks are very large, if you encounter oil thieves, the stolen oil may cause a loss of thousands of yuan. Some oil thieves may also steal oil by destroying the fuel tank, and the maintenance of the fuel tank will also incur certain costs.

[0003] There are many methods or devices for preventing oil thieves from stealing oil in the related art, such as using infrared sensing, vibration sensing or radar sensing to generate sensing alarms, but there is a high false alarm rate. Summary of the invention

[0004] In view of this, the present invention provides a method, device, equipment and medium for monitoring truck fuel tanks to solve the problem of high false alarm rate when prompting the driver of fuel theft through induction alarm.

[0005] In a first aspect, the present invention provides a method for monitoring a truck fuel tank, the method comprising: acquiring an image of an area where the fuel tank is located; performing face recognition based on the image, and if the result of the face recognition is a person other than a preset person, performing motion feature extraction based on the image; if it is determined through the extracted motion features that there may be a gasoline delivery action, determining whether the truck is at a gas station, and if not, issuing an alarm.

[0006] In an optional embodiment, if it is determined through the extracted features that there may be an action of gasoline delivery, determining whether the truck is at a gas station includes: after determining that there may be an action of gasoline delivery, acquiring monitoring images within a preset time range after the action occurs; if multiple frames of the monitoring images indicate that there may be an action of gasoline delivery, determining whether the truck is at a gas station.

[0007] In an optional embodiment, feature extraction is performed based on the image; if it is determined through the extracted features that there may be an action of gasoline delivery, it also includes: hand feature extraction based on the image, the extracted hand features include one or more of the following: hand shape, hand contour and hand movement trajectory; comparing the predefined gasoline delivery action with the extracted hand features, if the matching degree of the comparison result is higher than a preset threshold, it is determined that there may be an action of gasoline delivery.

[0008] In an optional embodiment, the method further includes: performing object detection based on the image; if the detected object determines that there is a tubular object or an electric drill, determining whether the truck is at a gas station, and if not, issuing an alarm.

[0009] In an optional embodiment, the determining whether the truck is at a gas station includes: determining whether the location of the truck is within a preset range of the gas station based on a global positioning system of the truck; or detecting whether the truck is at the gas station through a camera.

[0010] In an optional embodiment, the method further includes, when the alarm is issued, performing one or more of the following actions: obtaining video information of the area where the fuel tank is located; uploading the video information to the cloud; transmitting the video information to a terminal held by the preset personnel.

[0011] In an optional implementation, the method further includes: when the truck is in an engine-off state or a parking gear state, if fuel tank vibration data is obtained, obtaining an image of the area where the fuel tank is located.

[0012] In a second aspect, the present invention provides a device for monitoring a truck fuel tank, the device comprising: an image acquisition module, for acquiring an image of the area where the fuel tank is located; a first judgment module, for performing face recognition based on the image, and if the result of the face recognition is a person other than a preset person, performing feature extraction based on the image; a second judgment module, for determining whether the truck is at a gas station if it is determined through the extracted features that there is an action of gasoline delivery, and if not, issuing an alarm.

[0013] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the method for monitoring a truck fuel tank according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for monitoring a truck fuel tank according to the first aspect or any corresponding embodiment thereof.

[0015] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the method for monitoring a truck fuel tank according to the first aspect or any corresponding embodiment thereof.

[0016] If other persons besides the preset persons are identified approaching the fuel tank, further feature extraction and judgment processes will be triggered. This can effectively prevent illegal oil theft while reducing the alarms generated by the preset persons approaching the fuel tank. When it is determined that there is gasoline delivery, if it is determined that the truck is at a gas station, no alarm will be issued. This can eliminate the high-frequency situation where gas station staff help with refueling, greatly reducing the probability of false alarms. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the related technologies, the drawings required for use in the specific embodiments or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A schematic flow chart of a method for monitoring a truck fuel tank according to an embodiment of the present invention is shown;

[0019] Figure 2 A schematic flow chart of another method for monitoring a truck fuel tank according to an embodiment of the present invention is shown;

[0020] Figure 3 A schematic structural diagram of a device for monitoring a truck fuel tank according to an embodiment of the present invention is shown;

[0021] Figure 4 Another schematic diagram showing the structure of the device for monitoring a truck fuel tank according to an embodiment of the present invention;

[0022] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0024] At present, some truck drivers use traditional methods to deal with oil thieves, such as guarding the tank by hand, raising dogs, locking the fuel tank cap, sealing the tank, or wrapping the tank with steel, etc. However, for the traditional anti-oil theft methods adopted by drivers, oil thieves may use methods such as drilling to steal oil, which makes it difficult for truck drivers to prevent.

[0025] There are also methods of using electronic products to prevent oil theft in related technologies. For example, infrared sensing type, which detects moving objects through infrared sensing and triggers oil theft alarm; vibration sensing type, which detects vibration and triggers oil theft alarm; radar sensing type, which detects moving objects through radar and triggers oil theft alarm when moving objects are detected and the oil tank vibrates.

[0026] The aforementioned method of preventing oil theft through electronic products can deter oil thieves to a certain extent, but there are also obvious disadvantages. First, through infrared sensing, vibration sensing or radar sensing, it is not possible to judge exactly what the people around the oil tank are doing. It only judges whether there is oil theft through live detection or vibration sensing, which will lead to a high false alarm rate. In addition, the aforementioned method of preventing oil theft through electronic products cannot obtain the biological characteristics of the oil thieves, and cannot directly obtain the criminal evidence of the oil thieves, and can only have a small deterrent effect on the oil thieves.

[0027] According to an embodiment of the present invention, a method embodiment for monitoring a truck fuel tank is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] In this embodiment, a method for monitoring a truck fuel tank is provided, which can be used in a terminal such as a mobile phone, a tablet computer, a vehicle smart cockpit or a server, etc. Figure 1 A schematic diagram of a method for monitoring a truck fuel tank according to an embodiment of the present invention is shown. Figure 1 As shown, the process includes the following steps:

[0029] Step S101, obtaining an image of the area where the fuel tank is located.

[0030] In this step, an image of the area where the fuel tank is located can be obtained by using a fuel tank camera or other suitable camera equipment. The fuel tank camera can be set on the side of the truck's cockpit, or at other locations where gasoline extraction from the fuel tank can be captured, and the angle of the fuel tank camera can be adjusted to ensure that the face, hands, and fuel tank of the person extracting gasoline can be clearly captured.

[0031] The image of the area where the oil tank is located can be preprocessed, and the image preprocessing includes but is not limited to one or more of the following: grayscale, denoising, and size adjustment, etc. This can facilitate subsequent face recognition and feature extraction.

[0032] Step S102, performing face recognition based on the image, if the face recognition result is a person other than the preset person, performing action feature extraction based on the image.

[0033] In this step, face detection is performed on the image of the area where the fuel tank is located to determine whether there is a face in the image and to determine the position and size of the face. Facial features are extracted based on the detected face. The extracted facial features include one or a combination of the following: facial contour, position and shape of eyes, nose, mouth and other parts, as well as facial texture and skin color information. Key areas can be extracted from the preprocessed image, such as the hands or facial areas of a person.

[0034] The extracted facial features are compared with the features of the preset person. If the comparison result shows that the extracted features do not match the preset person, it means that a person other than the preset person is identified. Based on the image of the area where the fuel tank is located, the action features are extracted. The action features include at least one of the following: the action of the hand approaching the fuel tank cap, the hand rotating, pulling the fuel tank cap, or the hand holding a tubular object.

[0035] The preset personnel may be persons who have actual management and control authority over the truck, such as the owner or the driver of the vehicle. The preset personnel may register their faces in advance, and the face registration information may be stored locally on the terminal running the method for truck fuel tank monitoring, for use in comparing face information during face recognition.

[0036] Step S103, if it is determined through the extracted action features that there is an action of gasoline delivery, it is determined whether the truck is at a gas station, and if not, an alarm is issued.

[0037] In this step, the extracted action features are matched with the gasoline delivery action model to determine whether there is an intention or action to deliver gasoline. If it is determined that there is an intention or action to deliver gasoline, then it is determined whether the truck is at the gas station. The location information of the truck can be obtained using the global positioning system or other positioning technology. The truck location is compared with the known gas station location data.

[0038] There may be an action of delivering gasoline, which may be the action of a gas station worker filling gasoline, or the action of stealing gasoline by other personnel, such as inserting a tubular object into the fuel tank.

[0039] If it is determined that there may be gasoline delivery action and the truck is not in the gas station, the alarm condition is triggered and alarm information is generated, including the location of the truck, timestamp, action characteristics of suspected gasoline delivery, etc., and sent to relevant personnel or the monitoring center.

[0040] If it is determined that there may be gasoline delivery action, or it is inside the gas station, no alarm will be triggered. The high-frequency scenes of gas station staff refueling can be filtered out to reduce the false alarm rate.

[0041] The method for monitoring the fuel tank of a truck provided in this embodiment, if it is identified that other persons except the preset persons are approaching the fuel tank, further feature extraction and judgment processes are triggered, which can effectively prevent illegal oil theft and reduce the alarm generated by the preset persons approaching the fuel tank; when it is determined that there is an action of gasoline delivery, if it is determined that the truck is at a gas station, no alarm is issued, which can exclude the high-frequency situation that the gas station staff helps to refuel, greatly reducing the probability of false alarms.

[0042] In some optional embodiments, if the extracted features determine that there may be an action of gasoline delivery, determining whether the truck is at a gas station includes: after determining that there may be an action of gasoline delivery, acquiring monitoring images within a preset time range after the action occurs; if multiple frames of monitoring images indicate that there may be an action of gasoline delivery, determining whether the truck is at a gas station.

[0043] In this embodiment, after initially determining that there may be a gasoline delivery action, continuous monitoring images within a preset time range after the action occurs are obtained, and the preset time range can be from a few seconds to a few minutes. The acquired monitoring images are analyzed frame by frame or in batches to detect whether there are continuous and consistent gasoline delivery action features. This can be oil pipe connection, oil pipe insertion into the oil tank, etc. In the case of determining that there is a gasoline delivery action, it is then determined whether the truck is at a gas station.

[0044] If multiple consecutive frames of images show the presence of refueling or oil theft, it can be determined that oil theft or refueling is in progress, that is, there is a gasoline delivery action. The detection of gasoline delivery action includes: image acquisition, image preprocessing, feature extraction, gasoline delivery action recognition and time series analysis.

[0045] In this way, analyzing the image sequence over a period of time to determine whether there is a continuous oil theft action can improve the accuracy of oil tank theft monitoring.

[0046] In some optional embodiments, feature extraction is performed based on the image; if it is determined that there may be an action of gasoline delivery through the extracted features, it also includes: hand feature extraction based on the image, the extracted hand features include one or more of the following: hand shape, hand contour and hand movement trajectory; comparing the predefined gasoline delivery action with the extracted hand features, if the matching degree of the comparison result is higher than a preset threshold, it is determined that there may be an action of gasoline delivery.

[0047] In this embodiment, the hand features can be extracted by image segmentation and edge detection. The hand shape features are further refined to extract the precise outline of the hand. This can be achieved through a contour detection algorithm, such as a Canny edge detector. The geometric shape information of the hand can be obtained by identifying and processing the hand contour. The movement trajectory of the hand is analyzed and extracted by the change in the hand position between consecutive image frames. This can be achieved through image registration and optical flow calculation. Features can also be extracted from preprocessed images, for example, using a convolutional neural network (CNN) in deep learning to extract hand or facial features. Pre-trained network models, such as a residual network (Residual Network, abbreviated as ResNet) or a deep convolutional neural network (VGG), can also be used, and fine-tuned as needed to adapt to the specific task of gasoline delivery action behavior detection.

[0048] The predefined gasoline delivery action is a hand action feature related to gasoline delivery, which can be obtained based on expert knowledge, historical data or actual observation. Specifically, it can be an action of the hand approaching the fuel tank cap, such as the hand moving toward the fuel tank cap, or an action of the hand rotating, such as trying to rotate the fuel tank cap, or an action of pulling the fuel tank cap, such as opening the fuel tank cap, or an action of the hand holding a tubular object, such as holding a fuel suction pipe or a fuel gun.

[0049] The extracted hand features are compared with the predefined gasoline delivery action, and algorithms such as template matching or feature vector similarity calculation can be used to calculate the matching degree between the extracted hand features and the predefined gasoline delivery action features. The matching degree can be set to a value between 0 and 1, and the preset threshold can be set to 0.6. The specific setting of the preset threshold can be determined according to the actual application scenario.

[0050] By extracting and analyzing features such as the shape, contour, and motion trajectory of the hand, specific actions related to gasoline delivery can be more accurately identified. These hand features play a key role in distinguishing gasoline delivery actions from other similar actions, such as picking up other objects, thereby significantly improving the accuracy of recognition. At the same time, it not only relies on a single image feature, but also combines multiple hand features for comprehensive judgment. This multi-feature fusion strategy enables the system to maintain high recognition performance in complex situations such as different lighting conditions, background changes, or hand occlusion, thereby enhancing the robustness of the system.

[0051] In some optional embodiments, the aforementioned method for monitoring truck fuel tanks further includes performing object detection based on images. If the detected objects determine that there are tubular objects or electric drills, it is determined whether the truck is at a gas station. If not, an alarm is issued.

[0052] In this embodiment, an image of the area where the oil tank is located is obtained; face recognition is performed based on the image, and if the result of face recognition is a person other than the preset person, action features are extracted based on the image; based on the extracted action features, it is determined whether there is an action of drilling the oil tank or punching a hole, and it can be detected whether the hand holds an electric drill or turns on the electric drill, or, through object detection, it is determined whether there is a tubular object or an electric drill in the image. This can be achieved through target detection algorithms such as YOLO or SSD.

[0053] In this way, once a tubular object (such as an oil pipeline) or a tool such as an electric drill that may be related to illegal oil extraction is detected, it can immediately determine whether the truck is in a gas station. If the truck is not at the gas station but these objects are found, an alarm will be triggered, thus promptly reminding relevant personnel to deal with it, which can effectively prevent fuel theft or illegal use.

[0054] In some optional embodiments, determining whether the truck is at the gas station includes: determining whether the location of the truck is within a preset range of the gas station based on the global positioning system of the truck; or detecting whether the truck is at the gas station by a camera.

[0055] In this embodiment, the Global Positioning System (GPS) can be used to determine whether the vehicle is within a preset range of a gas station, wherein the preset range of a gas station can be set to within 25 meters of a gas station. A 360° panoramic camera set in the vehicle can also be used to detect whether there are gas stations or gas pumps around the vehicle.

[0056] In the case of an alarm, the recording function of the 360° panoramic camera and the fuel tank camera can be turned on. The recording time can be determined according to actual needs. For example, it can be set to 30 minutes. If it is detected that the gasoline delivery action has not stopped, it can be recorded in a loop without overwriting the already recorded video. At the same time, the video can be saved to the local album of the car and uploaded to the cloud at the same time.

[0057] In this way, combined with GPS positioning, it is possible to accurately determine whether the vehicle is in a gas station, eliminate the high-frequency gasoline delivery scenario of trucks refueling in gas stations, and greatly reduce the probability of false alarms for oil theft.

[0058] In some optional embodiments, the aforementioned method for monitoring truck fuel tanks also includes, in the event of an alarm, performing one or more of the following actions: obtaining video information of the area where the fuel tank is located; uploading the video information to the cloud; transmitting the video information to a terminal held by a preset person.

[0059] In this embodiment, the video information is acquired through the camera, and the video can be stored locally through the vehicle computer, or uploaded to the cloud through the vehicle computer, and the video can be transmitted to the mobile terminal of the owner or the driver who has the management and control authority of the vehicle through the cloud, and a message notification can be made, and at the same time, the police can be called. The video uploaded to the cloud can have an oil theft tag. When the cloud detects the video with this tag, it will transmit the video to the owner's mobile phone application and send a text message reminder; at the same time, the Internet of Vehicles of some car companies can realize direct alarm and speed up the dispatch of police by connecting with the police platform.

[0060] To issue an alarm, a message can be shouted through the external speaker of the vehicle, for example, "Please stop damaging the fuel tank, your behavior has been recorded", which can be played in a loop until no gasoline delivery action is detected.

[0061] In this way, while detecting the oil theft, evidence can also be obtained to report to the police, further increasing the deterrent effect on criminal behavior.

[0062] In some optional embodiments, the aforementioned method for monitoring a truck fuel tank further includes, when the truck is in an ignition-off state or a parking gear state, if fuel tank vibration data is obtained, obtaining an image of the area where the fuel tank is located.

[0063] In this embodiment, Figure 2 FIG. 2 is a flow chart showing another method for monitoring a truck fuel tank according to an embodiment of the present invention. Figure 2 Another method for monitoring a truck fuel tank is shown, comprising:

[0064] Step S201, when the vehicle is in an ignition-off state or a parking gear state, if the fuel tank vibration data is obtained;

[0065] Step S202, turning on a camera installed on the vehicle, acquiring an image of the area where the fuel tank is located, and performing face recognition based on the image;

[0066] Step S203, determining whether the result of face recognition is a preset person, if yes, proceeding to step S204, if no, proceeding to step S205;

[0067] Step S204, turning off the camera installed in the vehicle;

[0068] Step S205, extracting action features based on the image, and judging whether there may be an action of gasoline delivery based on the extracted action features, if so, proceeding to step S206, if not, proceeding to step S204;

[0069] Step S206, if it is determined through the extracted action features that there may be a gasoline delivery action, determine whether the truck is at the gas station, if so, go to step S204, if not, go to step S207;

[0070] Step S207, in the case of an alarm, perform one or more of the following actions: obtain video information of the area where the fuel tank is located; upload the video information to the cloud; transmit the video information to a terminal held by a preset person.

[0071] In this way, through face recognition, behavior recognition and GPS technology, the probability of false alarms can be greatly reduced. And because the OTA technology of the smart cockpit is mature, during the application process, it is also possible to increase judgment conditions according to specific scenarios, continuously optimize, and further reduce the probability of false alarms.

[0072] In this embodiment, a device for monitoring a truck fuel tank is also provided, and the device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made are not repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0073] This embodiment provides a device for monitoring a truck fuel tank. Figure 3 FIG. 1 is a schematic diagram showing a structure of a device for monitoring a truck fuel tank according to an embodiment of the present invention. Figure 3 As shown, including:

[0074] The image acquisition module 301 is used to acquire an image of the area where the fuel tank is located.

[0075] The first judgment module 302 is used to perform face recognition based on the image. If the result of face recognition is other than the preset person, feature extraction is performed based on the image.

[0076] The second judgment module 303 is used to judge whether the truck is at a gas station if it is determined through the extracted features that there is a gasoline delivery action, and to issue an alarm if the truck is not at a gas station.

[0077] In some optional implementations, the second determination module 303 includes:

[0078] The first unit of the second judgment module is used to obtain monitoring images within a preset time range after the action of gasoline delivery occurs after it is determined that there may be an action of gasoline delivery; if multiple frames of monitoring images indicate that there may be an action of gasoline delivery, it is determined whether the truck is at a gas station.

[0079] In some optional implementations, the second determining module 303 further includes:

[0080] The second unit of the second judgment module is used to extract hand features based on the image, and the extracted hand features include one or more of the following: hand shape, hand contour and hand movement trajectory; compare the predefined gasoline delivery action with the extracted hand features, if the matching degree of the comparison result is higher than a preset threshold, it is determined that there may be a gasoline delivery action.

[0081] In some optional embodiments, the aforementioned device for monitoring truck fuel tanks also includes a third judgment module, which is used to perform object detection based on images; if the detected objects determine that there are tubular objects or electric drills, it is determined whether the truck is at a gas station, and if not, an alarm is issued.

[0082] In some optional implementations, the second determining module 303 further includes:

[0083] The third unit of the second judgment module is used to judge whether the location of the truck is within a preset range of the gas station based on the global positioning system of the truck; or to detect whether the truck is at the gas station through a camera.

[0084] In some optional embodiments, the aforementioned device for monitoring truck fuel tanks also includes a storage module, which is used to perform one or more of the following actions when an alarm is issued: obtaining video information of the area where the fuel tank is located; uploading the video information to the cloud; transmitting the video information to a terminal held by a preset person.

[0085] In some optional embodiments, the aforementioned device for monitoring a truck fuel tank further includes a trigger module for acquiring an image of the area where the fuel tank is located if fuel tank vibration data is acquired when the truck is in an ignition-off state or a parking gear state.

[0086] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0087] The device for monitoring the truck fuel tank in this embodiment is presented in the form of a functional unit, where the unit refers to an application specific integrated circuit (ASIC) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0088] Figure 4 Another schematic diagram showing the structure of the device for monitoring the fuel tank of a truck according to an embodiment of the present invention. Figure 4As shown, the structure of the device for monitoring the fuel tank of a truck includes a system on chip (SOC) 401; a deserializer 402 (DES), a low-power Bluetooth 403 (BLE), a class D power amplifier 404 (class D), a storage device 405, a 4G module 406 and a global navigation satellite system 407 (GNSS) connected to the system on chip 401; wherein a fuel tank camera 408 and a 360° panoramic camera 409 are connected to the deserializer 402, a fuel tank vibration sensor 410 is connected to the low-power Bluetooth 403, an external speaker 411 is connected to the class D power amplifier 404, a 4G antenna 412 and a digital SIM card 414 (eSIM) are connected to the 4G module 406, and a GPS antenna 413 is connected to the global navigation satellite system 407.

[0089] In this way, through the linkage between the vehicle cockpit operating system and the on-board camera, the face recognition and behavior recognition technology installed in the smart cockpit is used, combined with GPS positioning, and the judgment condition is not limited to liveness detection, but is changed to the accurate recognition of the behavior around the fuel tank. The false alarm rate of oil theft is greatly reduced.

[0090] The embodiment of the present invention also provides a computer device having the above Figure 3 The device shown is used for truck tank monitoring.

[0091] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display graphical information of a graphical user interface on an external input / output device (such as a display device coupled to an interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0092] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0093] The aforementioned memory 20 stores instructions executable by at least one processor 10, so that the aforementioned at least one processor 10 executes the method shown in the above embodiment.

[0094] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0095] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0096] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0097] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (such as a light emitting diode) and a tactile feedback device (such as a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0098] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0099] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0100] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for monitoring a truck fuel tank, characterized in that: The method comprises: Get an image of the area where the fuel tank is located; Performing face recognition based on the image, and if a result of the face recognition is a person other than the preset person, performing action feature extraction based on the image; If the extracted action features determine that there may be gasoline delivery action, determine whether the truck is at the gas station. If not, issue an alarm.

2. The method according to claim 1, characterized in that If it is determined through the extracted features that there may be an action of gasoline delivery, determining whether the truck is at a gas station includes: After determining that there may be an action of gasoline delivery, acquiring monitoring images within a preset time range after the action occurs; If multiple frames of the monitoring images indicate that there may be an action of gasoline delivery, a determination is made as to whether the truck is at a gas station.

3. The method according to claim 1 or 2, characterized in that: The feature extraction is performed based on the image; if it is determined through the extracted features that there may be an action of gasoline delivery, it also includes: Extracting hand features based on the image, the extracted hand features including one or more of the following: hand shape, hand contour and hand motion trajectory; The predefined gasoline delivery action is compared with the extracted hand features, and if the matching degree of the comparison result is higher than a preset threshold, it is determined that there may be a gasoline delivery action.

4. The method according to claim 3, characterized in that The method further comprises: performing object detection based on the image; If it is determined through the detected objects that there is a tubular object or an electric drill, it is determined whether the truck is at a gas station. If not, an alarm is issued.

5. The method according to claim 1, characterized in that The step of determining whether the truck is at a gas station includes: Based on the global positioning system of the truck, determining whether the location of the truck is within a preset range of the gas station; or, Whether the truck is at a gas station is detected by a camera.

6. The method according to claim 1, characterized in that The method further includes, when the alarm is issued, performing one or more of the following actions: Obtaining video information of the area where the fuel tank is located; Uploading the video information to the cloud; The video information is transmitted to a terminal held by the preset person.

7. The method according to claim 1, characterized in that The method further comprises: When the truck is in an engine-off state or a parking gear state, if the oil tank vibration data is obtained, an image of the area where the oil tank is located is obtained.

8. A device for monitoring a truck fuel tank, characterized in that: The device comprises: An image acquisition module, used for acquiring an image of the area where the fuel tank is located; A first judgment module is used to perform face recognition based on the image, and if the face recognition result is a person other than the preset person, perform feature extraction based on the image; The second judgment module is used to determine whether the truck is at a gas station if it is determined through the extracted features that there is a gasoline delivery action, and to issue an alarm if it is not at a gas station.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for monitoring a truck fuel tank as claimed in any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for monitoring a truck fuel tank according to any one of claims 1 to 7.

Images