Visual big data identification system for power control
By using a visual big data identification system to identify the contact state between the refueling nozzle and the refueling gun, the safety problem of refueling gun breakage during vehicle refueling is solved, and effective monitoring of refueling safety is achieved.
Patent Information
- Application Number
- CN202410625603.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-20
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-05-20
AI Technical Summary
In existing technologies, the failure to promptly detect whether the fuel nozzle is in contact with the vehicle's fuel tank opening during refueling can easily lead to safety accidents such as fuel nozzle breakage.
A visual big data identification system is used to determine the contact state between the fuel nozzle and the fuel pump by identifying the imaging area and depth value of the fuel nozzle in the image. When contact occurs, the vehicle's drive mechanism is disabled to prevent the fuel pump from breaking while driving.
It effectively identifies the contact status between the refueling nozzle and the refueling gun, avoiding accidents caused by the refueling gun breaking when the vehicle is not in contact, thus improving refueling safety.
Smart Images

Figure CN118550232B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of power control, and in particular to a visual big data identification system for power control. Background Art
[0002] Visual monitoring can be applied to key monitoring in various scenarios. For example, when browsing the news, you will often see news about people falling in a certain area and no one discovering them for a long time, or people breaking into a dangerous area and managers failing to persuade them to leave in time, leading to accidents. Due to limited human resources and manual inspection capabilities, it is impossible to detect people's behavior in time in many public areas, which leads to danger. In order to ensure the safety of people's behavior in public areas, an intelligent video monitoring system for people's behavior based on AI video technology can be used. The video monitoring system refers to installing cameras in public areas and connecting them to the video monitoring platform through the Internet, which can monitor the situation in public areas in real time and detect abnormal behavior and safety risks in time.
[0003] In the prior art, visual monitoring can also be applied to other specific sub-fields. For example, the following scenarios need to be monitored closely: when a vehicle user uses a gas gun to refuel the vehicle, there is a possibility that the user drives away from the refueling area without considering whether the muzzle of the gas gun is in contact with the vehicle's fuel tank opening. At this time, the gas gun body may be broken or the refueling pile may be directly pulled down, causing a fire accident due to friction between the facilities. Therefore, a high-precision detection mechanism is needed to perform on-site scene recognition and processing on whether the muzzle of the gas gun is in contact with the vehicle's fuel tank opening. Summary of the invention
[0004] In order to solve the technical problems in the prior art, the present invention provides a visual big data identification system for power control, which can identify the imaging area occupied by the fuel filler in the received content mapping image as a reference imaging area, obtain the geometric shape of the edge of the reference imaging area, and when the acquired geometric shape is missing relative to the geometric shape of the reference outline pattern corresponding to the fuel filler, obtain the depth of field value of the fuel filler in the content mapping image and the depth of field value of the fuel gun in the content mapping image, when the difference between the depth of field value of the fuel filler in the content mapping image and the depth of field value of the fuel gun in the content mapping image is less than or equal to the set depth of field limit, it is determined that the fuel filler is connected to the fuel gun, otherwise, it is determined that the fuel filler is not connected to the fuel gun, thereby achieving effective resolution of the contact state between the fuel filler and the fuel gun, and disabling the driving mechanism of the vehicle when it is visually identified that the fuel filler is connected to the fuel gun, and enabling the driving mechanism of the vehicle when it is visually identified that the fuel filler is not connected to the fuel gun, thereby avoiding safety accidents caused by the fuel gun breaking when the vehicle is driven away with the fuel filler still connected to the fuel gun.
[0005] According to the present invention, a visual big data identification system for power control is provided, the system comprising:
[0006] A cover judging mechanism connected to the cover of the fuel tank filling port of the vehicle, used to send a first judging signal when judging that the cover is currently in an open state, and also used to send a second judging signal when judging that the cover is currently in a closed state;
[0007] a micro-photographing mechanism, disposed on the cover of the fuel tank filling port of the vehicle and connected to the cover judging mechanism, for performing photographing processing facing the refueling scene of the vehicle upon receiving the first judging signal, so as to obtain and output a corresponding refueling scene image;
[0008] A tilt correction device, disposed inside the vehicle and connected to the micro-photographing mechanism, for performing a tilt correction process on the received refueling scene image to obtain and output a corresponding tilt correction image;
[0009] A directional filtering device, connected to the tilt correction device, for performing directional filtering processing on the received tilt-corrected image to obtain and output a corresponding directional filtered image;
[0010] a content mapping device, connected to the directional filtering device, configured to perform Butterworth low-pass filtering on the received directional filtered image to obtain and output a corresponding content mapping image;
[0011] a separation identification device, arranged inside the vehicle and connected to the content mapping device, for identifying an imaging area occupied by the fuel filler port in the received content mapping image as a reference imaging area, obtaining a geometric shape of an edge of the reference imaging area, and obtaining a depth of field value of the fuel filler port in the content mapping image and a depth of field value of the fuel gun in the content mapping image when the obtained geometric shape is missing relative to the geometric shape of the reference outer shape pattern corresponding to the fuel filler port, so as to determine that the fuel filler port is connected to the fuel gun when the difference between the depth of field value of the fuel filler port in the content mapping image and the depth of field value of the fuel gun in the content mapping image is less than or equal to a set depth of field limit, otherwise, determine that the fuel filler port is not connected to the fuel gun;
[0012] a power control device, disposed inside the vehicle and connected to the disengagement identification device and the driving mechanism of the vehicle, respectively, for disabling the driving mechanism of the vehicle when the disengagement identification device determines that the fuel inlet is connected to the fuel gun, and for enabling the driving mechanism of the vehicle when the disengagement identification device determines that the fuel inlet is not connected to the fuel gun;
[0013] The micro-shooting mechanism is further used to suspend the shooting process of the refueling scene of the vehicle when receiving the second judgment signal.
[0014] Therefore, the present invention has the following three outstanding technical effects:
[0015] Technical effect 1: Identify the imaging area occupied by the fuel filler port in the received content mapping image as a reference imaging area, obtain the geometric shape of the edge of the reference imaging area, and when the obtained geometric shape is missing relative to the geometric shape of the reference outline pattern corresponding to the fuel filler port, obtain the depth of field value of the fuel filler port in the content mapping image and the depth of field value of the fuel gun in the content mapping image;
[0016] Technical effect 2: When the difference between the depth of field value of the fuel filler port in the content mapping image and the depth of field value of the fuel gun in the content mapping image is less than or equal to the set depth of field limit, it is determined that the fuel filler port and the fuel gun are connected; otherwise, it is determined that the fuel filler port and the fuel gun are not connected, thereby achieving effective discrimination of the contact state between the fuel filler port and the fuel gun;
[0017] Technical effect three: Introduce a power control device installed inside the vehicle, which is used to disable the vehicle's driving mechanism when it is visually identified that the fuel filler port and the fuel gun are connected, and to enable the vehicle's driving mechanism when it is visually identified that the fuel filler port and the fuel gun are not connected, thereby avoiding safety accidents caused by the fuel gun breaking when the vehicle is driven away with the fuel filler port still connected to the fuel gun.
[0018] The visual big data identification system for power control of the present invention is easy to operate and widely used. Since it can identify various visual data of the fuel filler port and the fuel gun in the optimized on-site image, it can determine that the fuel filler port is connected to the fuel gun, and when it is determined that the fuel filler port is connected to the fuel gun, the driving mechanism of the vehicle is disabled, thereby avoiding the safety accident of the fuel gun breaking due to the vehicle leaving the vehicle with the fuel filler port still connected to the fuel gun. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:
[0020] Figure 1 It is a structural block diagram of a visual big data identification system for power control according to the first embodiment of the present invention.
[0021] Figure 2 It is a structural block diagram of a visual big data identification system for power control according to the second embodiment of the present invention.
[0022] Figure 3 It is a structural block diagram of a visual big data identification system for power control according to the third embodiment of the present invention. DETAILED DESCRIPTION
[0023] The following will describe in detail an embodiment of a visual big data identification system for power control of the present invention with reference to the accompanying drawings.
[0024] Figure 1 The structure block diagram of a visual big data identification system for power control according to the first embodiment of the present invention is shown, and the system includes:
[0025] A cover judging mechanism connected to the cover of the fuel tank filling port of the vehicle, used to send a first judging signal when judging that the cover is currently in an open state, and also used to send a second judging signal when judging that the cover is currently in a closed state;
[0026] For example, the cover judgment mechanism is connected to the cover of the fuel tank filling port of the vehicle, and is used to send a first judgment signal when judging that the cover is currently in an open state, and is also used to send a second judgment signal when judging that the cover is currently in a closed state, including: selecting a programmable logic device to implement the cover judgment mechanism, connected to the cover of the fuel tank filling port of the vehicle, and is used to send a first judgment signal when judging that the cover is currently in an open state, and is also used to send a second judgment signal when judging that the cover is currently in a closed state;
[0027] a micro-photographing mechanism, disposed on the cover of the fuel tank filling port of the vehicle and connected to the cover judging mechanism, for performing photographing processing facing the refueling scene of the vehicle upon receiving the first judging signal, so as to obtain and output a corresponding refueling scene image;
[0028] A tilt correction device, disposed inside the vehicle and connected to the micro-photographing mechanism, for performing a tilt correction process on the received refueling scene image to obtain and output a corresponding tilt correction image;
[0029] A directional filtering device, connected to the tilt correction device, for performing directional filtering processing on the received tilt-corrected image to obtain and output a corresponding directional filtered image;
[0030] a content mapping device, connected to the directional filtering device, configured to perform Butterworth low-pass filtering on the received directional filtered image to obtain and output a corresponding content mapping image;
[0031] a separation identification device, arranged inside the vehicle and connected to the content mapping device, for identifying an imaging area occupied by the fuel filler port in the received content mapping image as a reference imaging area, obtaining a geometric shape of an edge of the reference imaging area, and obtaining a depth of field value of the fuel filler port in the content mapping image and a depth of field value of the fuel gun in the content mapping image when the obtained geometric shape is missing relative to the geometric shape of the reference outer shape pattern corresponding to the fuel filler port, so as to determine that the fuel filler port is connected to the fuel gun when the difference between the depth of field value of the fuel filler port in the content mapping image and the depth of field value of the fuel gun in the content mapping image is less than or equal to a set depth of field limit, otherwise, determine that the fuel filler port is not connected to the fuel gun;
[0032] a power control device, disposed inside the vehicle and connected to the disengagement identification device and the driving mechanism of the vehicle, respectively, for disabling the driving mechanism of the vehicle when the disengagement identification device determines that the fuel inlet is connected to the fuel gun, and for enabling the driving mechanism of the vehicle when the disengagement identification device determines that the fuel inlet is not connected to the fuel gun;
[0033] Wherein, the micro-shooting mechanism is further used to suspend the shooting process of the refueling scene of the vehicle when receiving the second judgment signal;
[0034] Wherein, identifying the imaging area occupied by the fuel filler port in the received content mapping image as the reference imaging area, acquiring the geometric shape of the edge of the reference imaging area, and acquiring the depth of field value of the fuel filler port in the content mapping image and the depth of field value of the fuel gun in the content mapping image when the acquired geometric shape is missing relative to the geometric shape of the reference outline pattern corresponding to the fuel filler port, comprises: identifying the imaging area occupied by the fuel filler port in the received content mapping image as the reference imaging area based on the distribution range of brightness values corresponding to the fuel filler port;
[0035] Figure 2 It is a structural block diagram of a visual big data identification system for power control according to the second embodiment of the present invention.
[0036] Compared to Figure 1 , Figure 2 The visual big data identification system for power control may also include:
[0037] a temperature detection device, disposed near the tilt correction device, the direction filtering device, the content mapping device, and the separation identification device and connected to the tilt correction device, the direction filtering device, the content mapping device, and the separation identification device, respectively;
[0038] Among them, the temperature detection device is arranged near the tilt correction device, the direction filtering device, the content mapping device and the detachment identification device and is respectively connected to the tilt correction device, the direction filtering device, the content mapping device and the detachment identification device, including: the temperature detection device is used to respectively realize on-site measurement of the current temperature of the tilt correction device, the direction filtering device, the content mapping device and the detachment identification device.
[0039] Figure 3 It is a structural block diagram of a visual big data identification system for power control according to the third embodiment of the present invention.
[0040] Compared to Figure 1 , Figure 3 The visual big data identification system for power control may also include:
[0041] a voltage detection device, arranged near the tilt correction device, the direction filtering device, the content mapping device and the separation identification device and connected to the tilt correction device, the direction filtering device, the content mapping device and the separation identification device respectively;
[0042] The voltage detection device is arranged near the tilt correction device, the direction filtering device, the content mapping device and the separation identification device and is respectively connected to the tilt correction device, the direction filtering device, the content mapping device and the separation identification device, and includes: the voltage detection device is used to respectively realize the on-site measurement of the current voltage of the tilt correction device, the direction filtering device, the content mapping device and the separation identification device;
[0043] Wherein, a SOC chip is used to perform image data processing on the output data of the tilt correction device, the direction filtering device, the content mapping device and the separation identification device to obtain the output processing data corresponding to the tilt correction device, the direction filtering device, the content mapping device and the separation identification device respectively;
[0044] Wherein, using the SOC chip to perform image data processing on the output data of the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device respectively comprises: performing nearest neighbor interpolation processing on the output data of the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device respectively;
[0045] Wherein, using the SOC chip to perform image data processing on the output data of the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device respectively comprises: performing bilinear interpolation processing on the output data of the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device respectively;
[0046] The method of using a SOC chip to perform image data processing on the output data of the tilt correction device, the directional filtering device, the content mapping device, and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device, and the detachment identification device includes: performing bicubic interpolation processing of a 16×16 pixel neighborhood on the output data of the tilt correction device, the directional filtering device, the content mapping device, and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device, and the detachment identification device;
[0047] Among them, the SOC chip is used to perform image data processing on the output data of the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device respectively, including: performing 4×4 pixel neighborhood Lnczos interpolation processing on the output data of the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device respectively.
[0048] In addition, in the visual big data identification system for power control, the power control device is respectively connected to the disengagement identification device and the vehicle's drive mechanism, and is used to disable the vehicle's drive mechanism when the disengagement identification device determines that the fuel port and the fuel gun are connected, and is also used to enable the vehicle's drive mechanism when the disengagement identification device determines that the fuel port and the fuel gun are not connected, including: the vehicle's drive mechanism is a gasoline engine or a gasoline-electric hybrid engine.
[0049] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A visual big data identification system for power control, characterized in that: The system comprises: A cover judging mechanism connected to the cover of the fuel tank filling port of the vehicle, used to send a first judging signal when judging that the cover is currently in an open state, and also used to send a second judging signal when judging that the cover is currently in a closed state; a micro-photographing mechanism, disposed on the cover of the fuel tank filling port of the vehicle and connected to the cover judging mechanism, for performing photographing processing facing the refueling scene of the vehicle upon receiving the first judging signal, so as to obtain and output a corresponding refueling scene image; A tilt correction device, disposed inside the vehicle and connected to the micro-photographing mechanism, for performing a tilt correction process on the received refueling scene image to obtain and output a corresponding tilt correction image; A directional filtering device, connected to the tilt correction device, for performing directional filtering processing on the received tilt-corrected image to obtain and output a corresponding directional filtered image; a content mapping device, connected to the directional filtering device, configured to perform Butterworth low-pass filtering on the received directional filtered image to obtain and output a corresponding content mapping image; a separation identification device, arranged inside the vehicle and connected to the content mapping device, for identifying an imaging area occupied by the fuel filler port in the received content mapping image as a reference imaging area, obtaining a geometric shape of an edge of the reference imaging area, and obtaining a depth of field value of the fuel filler port in the content mapping image and a depth of field value of the fuel gun in the content mapping image when the obtained geometric shape is missing relative to the geometric shape of the reference outer shape pattern corresponding to the fuel filler port, so as to determine that the fuel filler port is connected to the fuel gun when the difference between the depth of field value of the fuel filler port in the content mapping image and the depth of field value of the fuel gun in the content mapping image is less than or equal to a set depth of field limit, otherwise, determine that the fuel filler port is not connected to the fuel gun; a power control device, disposed inside the vehicle and connected to the disengagement identification device and the driving mechanism of the vehicle, respectively, for disabling the driving mechanism of the vehicle when the disengagement identification device determines that the fuel inlet is connected to the fuel gun, and for enabling the driving mechanism of the vehicle when the disengagement identification device determines that the fuel inlet is not connected to the fuel gun; The micro-shooting mechanism is further used to suspend the shooting process of the refueling scene of the vehicle when receiving the second judgment signal.
2. The visual big data identification system for power control according to claim 1, characterized in that: Identify the imaging area occupied by the fuel filler port in the received content mapping image as a reference imaging area, obtain the geometric shape of the edge of the reference imaging area, and when the obtained geometric shape is missing relative to the geometric shape of the reference outline pattern corresponding to the fuel filler port, obtain the depth of field value of the fuel filler port in the content mapping image and the depth of field value of the fuel gun in the content mapping image, including: based on the brightness value distribution range corresponding to the fuel filler port, identify the imaging area occupied by the fuel filler port in the received content mapping image as the reference imaging area.
3. The visual big data identification system for power control according to claim 2, characterized in that: The system further comprises: a temperature detection device, disposed near the tilt correction device, the direction filtering device, the content mapping device, and the separation identification device and connected to the tilt correction device, the direction filtering device, the content mapping device, and the separation identification device, respectively; Among them, the temperature detection device is arranged near the tilt correction device, the direction filtering device, the content mapping device and the detachment identification device and is respectively connected to the tilt correction device, the direction filtering device, the content mapping device and the detachment identification device, including: the temperature detection device is used to respectively realize on-site measurement of the current temperature of the tilt correction device, the direction filtering device, the content mapping device and the detachment identification device.
4. The visual big data identification system for power control according to claim 2, characterized in that: The system further comprises: a voltage detection device, arranged near the tilt correction device, the direction filtering device, the content mapping device and the separation identification device and connected to the tilt correction device, the direction filtering device, the content mapping device and the separation identification device respectively; Among them, the voltage detection device is arranged near the tilt correction device, the direction filtering device, the content mapping device and the detachment identification device and is respectively connected to the tilt correction device, the direction filtering device, the content mapping device and the detachment identification device, including: the voltage detection device is used to respectively realize on-site measurement of the current voltage of the tilt correction device, the direction filtering device, the content mapping device and the detachment identification device.
5. The visual big data identification system for power control according to any one of claims 2 to 4, characterized in that: A SOC chip is used to perform image data processing on the output data of the tilt correction device, the direction filtering device, the content mapping device and the detachment identification device to obtain output processing data corresponding to the tilt correction device, the direction filtering device, the content mapping device and the detachment identification device respectively.
6. The visual big data identification system for power control according to claim 5, characterized in that: Using a SOC chip to perform image data processing on the output data of the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device respectively includes: performing nearest neighbor interpolation processing on the output data of the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device respectively.
7. The visual big data identification system for power control according to claim 5, characterized in that: Using a SOC chip to perform image data processing on the output data of the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device respectively includes: performing bilinear interpolation processing on the output data of the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device respectively.
8. The visual big data identification system for power control according to claim 5, characterized in that: The SOC chip is used to perform image data processing on the output data of the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device respectively, including: performing bicubic interpolation processing of a 16×16 pixel neighborhood on the output data of the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device respectively.
9. The visual big data identification system for power control according to claim 5, characterized in that: The SOC chip is used to perform image data processing on the output data of the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device respectively, including: performing 4×4 pixel neighborhood Lnczos interpolation processing on the output data of the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device to obtain the output processing data corresponding to the tilt correction device, the directional filtering device, the content mapping device and the detachment identification device respectively.
