Intrinsic safety type mining auxiliary driving system and method

Abstract

The invention discloses an intrinsic safety type mining auxiliary driving system and method, and relates to the field of mining auxiliary driving, the intrinsic safety type mining auxiliary driving system mainly comprises an auxiliary driving controller, an all-round camera, an ultrasonic radar, a driver monitoring camera, a forward millimeter wave radar, a forward camera, a driver control display screen and a power supply circuit; wherein the auxiliary driving controller comprises a vehicle 360-degree looking-around module, a driver monitoring module, a personnel approaching prevention module and a front obstacle early warning module. By means of the intrinsic safety type mining auxiliary driving system and method, the vehicle driving safety can be improved.

Description

Technical Field

[0001] The present invention relates to the field of mining assisted driving, and more specifically, to an intrinsically safe mining assisted driving system and method. Background Art

[0002] The mining transportation field has multiple unfavorable working environment characteristics such as insufficient lighting, a large amount of dust in the environment, small underground space, narrow passages, etc. Therefore, the probability and severity of safety accidents in the mining transportation field are much higher than those in the general road traffic field. At the same time, the geological environment in the mining field is complex and may contain flammable and explosive gases such as methane and carbon monoxide, as well as corrosive gases such as hydrogen sulfide. These gases may cause explosions under certain conditions, so equipment in the mining field needs to have explosion-proof properties. How to provide an assisted driving system that meets the requirements of intrinsically safe equipment is an urgent problem to be solved. Summary of the invention

[0003] The object of the present invention is to provide an intrinsically safe mining auxiliary driving system and method, which can improve vehicle driving safety.

[0004] The present invention provides an intrinsically safe mining assisted driving system, comprising an assisted driving controller, a surround-view camera, an ultrasonic radar, a driver monitoring camera, a forward millimeter-wave radar, a forward camera, a driver control display screen and a power supply circuit; the assisted driving controller is electrically connected to the surround-view camera, the ultrasonic radar, the driver monitoring camera, the forward millimeter-wave radar, the forward camera, the driver control display screen and the power supply circuit, respectively.

[0005] Furthermore, the above-mentioned assisted driving controller includes a vehicle 360° surround view module, a driver monitoring module, a personnel anti-approach module and a front obstacle warning module; the vehicle 360° surround view module is used to obtain an eagle-eye perspective image; the driver monitoring module is used to obtain driver fatigue alarm information and inattention alarm information; the personnel anti-approach module is used to obtain personnel approach warning information; the front obstacle warning module is used to obtain obstacle type and alarm information.

[0006] Furthermore, the above-mentioned vehicle 360° surround view module is configured as follows: using the surround view camera to dynamically collect fisheye images around the vehicle; using pixel point coordinate conversion and image pixel interpolation algorithm to correct the distortion of the fisheye images around the vehicle to obtain a standard visual image; using a pixel matrix coordinate conversion algorithm to convert the field of view of the standard visual image from front view to top view to obtain a top view image; based on the top view image, according to the 360° model around the vehicle, using a fast corner detection algorithm to perform image stitching and fusion, to obtain an eagle-eye perspective image.

[0007] Furthermore, the above-mentioned driver monitoring module is configured as follows: using the driver monitoring camera to collect the driver's facial image information, identifying and analyzing the driver's facial image information to obtain the eye aspect ratio and the mouth aspect ratio, and obtaining the eye closing time and the yawning time according to the driver's facial image information, the eye aspect ratio and the mouth aspect ratio; when the eye closing time is greater than a preset eye closing time threshold, or the yawning time is greater than a preset yawning time threshold, a fatigue alarm information is obtained.

[0008] Furthermore, the above-mentioned driver monitoring module is also configured to: use the driver monitoring camera to collect the driver's facial image information, identify and analyze the driver's facial image information, and obtain the head lowering time and the head tilting time; when the head lowering time is greater than the preset head lowering time threshold, or when the head tilting time is greater than the preset head tilting time threshold, an inattention alarm information is obtained.

[0009] Furthermore, the above-mentioned personnel anti-approach module is configured as follows: using the ultrasonic radar to obtain information about neighboring obstacles, using the surround-view camera to obtain a standard visual image, performing image recognition on the standard visual image to obtain information about surrounding personnel, and obtaining personnel approach warning information based on the surrounding personnel information and the neighboring obstacle information.

[0010] Furthermore, the above-mentioned forward obstacle warning module is configured as follows: using the forward millimeter-wave radar to detect obstacles ahead of the vehicle to obtain millimeter-wave radar detection information; using the forward camera to perform image acquisition to obtain a forward image; performing pre-dust and fog removal processing on the forward image to obtain a dust-removed fog image; performing image recognition on the dust-removed fog image to obtain recognized image information; and combining the millimeter-wave radar detection information to judge the recognized image information to obtain the obstacle type and alarm information.

[0011] Furthermore, the forward image is pre-dust-removed to obtain a dust-removed image, as shown in the formula: , , in, To remove dust and fog images, is the dust and fog image to be removed, i.e. the forward image. is the atmospheric light component value, is the transmittance, is the minimum revision value of the white field, Keep constant for dust and fog, In pixels A dust removal window in the center, Represents the three channels of the image R / G / B, Represents each channel value of a color image, A per-channel value representing the atmospheric light component.

[0012] Furthermore, the above-mentioned power supply circuit includes a power supply board and an input-output interface protection device, the power supply board includes low-energy release components and a protection circuit; the protection circuit is used to limit the voltage and current to reduce the generation of electric sparks and thermal effects; the input-output interface protection device is used to cut off the power supply in time and limit the scope of the fault when a fault occurs in the intrinsically safe mining auxiliary driving system or the load connected to the interface; the input-output interface protection device includes a fuse, a circuit breaker, a voltage limiting diode and an overcurrent protector; the intrinsically safe mining auxiliary driving system also includes a heat dissipation device, a high-temperature resistant and flame-retardant isolated independent cabin shell and an external wiring harness.

[0013] The present invention also provides an assisted driving method, comprising: using the above-mentioned intrinsically safe mining assisted driving system to obtain an eagle-eye perspective image, driver fatigue alarm information, inattention alarm information, personnel approach warning information, obstacle type and warning information; controlling a controlled vehicle according to the eagle-eye perspective image, the personnel approach warning information, the obstacle type and warning information; and alarming the driver of the controlled vehicle according to the driver fatigue alarm information and the inattention alarm information.

[0014] The implementation of the intrinsically safe mining auxiliary driving system and method provided by the present invention has the following beneficial effects: The present invention provides an assisted driving system that meets the requirements of intrinsically safe equipment for special working conditions in the mining field; the system provides a complete assisted driving solution for the driver by realizing functions such as 360° surround view of the vehicle, driver monitoring system (DMS), personnel anti-approach system, and vehicle front obstacle warning; the system fundamentally eliminates or reduces potential explosion hazards and risks by optimizing the product hardware circuit design, ensuring that no explosion hazards will be caused to personnel, environment or equipment under normal use and fault conditions, and the product complies with the intrinsic safety design requirements of GB3836.4-2021; when the vehicle is traveling forward, the system uses the vehicle front obstacle warning function to warn of obstacles in front with sound and light alarms; when the vehicle is turning, reversing, or starting, it detects and warns of obstacles around the vehicle, and prompts people approaching; the driver's fatigue and concentration are dynamically monitored, and warning information is issued according to the threshold setting. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which: Figure 1 It is a schematic diagram of the composition of the intrinsically safe mining auxiliary driving system provided by the present invention; Figure 2It is a power supply output circuit diagram with power component parameter restrictions provided by the present invention; Figure 3 The present invention provides a power supply input circuit diagram with surge suppression and current limitation; Figure 4 It is an image processing flow chart of the vehicle 360° surround view module provided by the present invention. DETAILED DESCRIPTION

[0016] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described in detail with reference to the accompanying drawings.

[0017] Figure 1 The composition diagram of the intrinsically safe mining assisted driving system of this embodiment is shown. In this embodiment, the intrinsically safe mining assisted driving system includes an assisted driving controller, a surround view camera, an ultrasonic radar, a driver monitoring camera, a forward millimeter-wave radar, a forward camera, a driver control display screen and a power supply circuit; the assisted driving controller is electrically connected to the surround view camera, the ultrasonic radar, the driver monitoring camera, the forward millimeter-wave radar, the forward camera, the driver control display screen and the power supply circuit respectively; For an exemplary embodiment, the auxiliary driving controller includes a vehicle 360° surround view module, a driver monitoring module, a personnel approach prevention module and a front obstacle warning module; the vehicle 360° surround view module is used to obtain an eagle-eye perspective image; the driver monitoring module is used to obtain driver fatigue warning information and inattention warning information; the personnel approach prevention module is used to obtain personnel approach warning information; the front obstacle warning module is used to obtain obstacle type and warning information; For an exemplary embodiment, the vehicle 360° surround view module is configured as follows: using the surround view camera to dynamically collect fisheye images around the vehicle; using pixel point coordinate conversion and image pixel interpolation algorithm to perform distortion correction on the fisheye images around the vehicle to obtain a standard visual image; using a pixel matrix coordinate conversion algorithm to convert the field of view of the standard visual image from front view to top view to obtain a top view image; based on the top view image, according to the 360° model around the vehicle, using a fast corner point detection algorithm to perform image stitching and fusion to obtain an eagle-eye perspective image; For an exemplary embodiment, the driver monitoring module is configured as follows: using the driver monitoring camera to collect driver facial image information, identifying and analyzing the driver facial image information to obtain eye aspect ratio and mouth aspect ratio, and obtaining eye closing time and yawning time according to the driver facial image information, eye aspect ratio and mouth aspect ratio; when the eye closing time is greater than a preset eye closing time threshold, or the yawning time is greater than a preset yawning time threshold, obtaining fatigue alarm information; For an exemplary embodiment, the preset eye closing time threshold is 0.5 seconds, and the preset yawning time threshold is 1 second; For an exemplary embodiment, the driver monitoring module is further configured to: collect driver facial image information using the driver monitoring camera, identify and analyze the driver facial image information, and obtain head-down time and head-tilt time; when the head-down time is greater than a preset head-down time threshold, or when the head-tilt time is greater than a preset head-tilt time threshold, obtain inattention alarm information; For an exemplary embodiment, the preset head-down time threshold is 0.5 seconds, and the preset head-tilt time threshold is 0.5 seconds; For an exemplary embodiment, the personnel anti-approach module is configured as follows: using the ultrasonic radar to obtain information about adjacent obstacles, using the surround-view camera to obtain a standard visual image, performing image recognition on the standard visual image to obtain information about surrounding personnel, and obtaining personnel approach warning information based on the surrounding personnel information and the adjacent obstacle information; For an exemplary embodiment, the front obstacle warning module is configured as follows: using the forward millimeter-wave radar to detect obstacles ahead of the vehicle to obtain millimeter-wave radar detection information; using the forward camera to perform image acquisition to obtain a forward image; performing pre-dust and fog removal processing on the forward image to obtain a dust and fog removal image; performing image recognition on the dust and fog removal image to obtain recognition image information; combining the millimeter-wave radar detection information, judging the recognition image information to obtain obstacle type and alarm information; For an exemplary embodiment, the forward image is pre-dust-removed to obtain a dust-removed image, as shown in the formula: , , in, To remove dust and fog images, is the dust and fog image to be removed. is the atmospheric light component value, is the transmittance, is the minimum revision value of the white field, Keep constant for dust and fog, In pixels A dust removal window in the center, Represents the three channels of the image R / G / B, Represents each channel value of a color image, Each channel value representing the atmospheric light component; For an exemplary embodiment, the driver control display screen is configured to display the eagle eye perspective image, the driver fatigue warning information, the inattention warning information, the person approaching warning information, the obstacle type and warning information; For an exemplary embodiment, the power circuit includes a power board and an input-output interface protection device, the power board includes low-energy release components and a protection circuit; the protection circuit is used to limit the voltage and current to reduce the generation of electric sparks and thermal effects; the input-output interface protection device is used to cut off the power supply and limit the fault range in time when the intrinsically safe mining auxiliary driving system or the load connected to the interface fails; the input-output interface protection device includes a fuse, a circuit breaker, a voltage limiting diode and an overcurrent protector; the intrinsically safe mining auxiliary driving system also includes a heat dissipation device, a high temperature resistant and flame retardant isolated independent cabin shell and an external wiring harness; This embodiment provides an assisted driving method, including: using the above-mentioned intrinsically safe mining assisted driving system to obtain eagle-eye perspective images, driver fatigue alarm information, inattention alarm information, personnel approach warning information, obstacle type and warning information; controlling a controlled vehicle according to the eagle-eye perspective images, the personnel approach warning information, the obstacle type and warning information; and alarming the driver of the controlled vehicle according to the driver fatigue alarm information and the inattention alarm information.

[0018] In some embodiments, the above-mentioned intrinsically safe mining assisted driving system can also be implemented in the following manner.

[0019] In this embodiment, the intrinsically safe mining auxiliary driving system includes an auxiliary driving controller, a surround view camera, an ultrasonic radar, a driver monitoring system (DMS) camera, a forward millimeter-wave radar, a forward camera, a driver control display screen and a power supply circuit; the auxiliary driving controller is electrically connected to the surround view camera, the ultrasonic radar, the driver monitoring camera, the forward millimeter-wave radar, the forward camera, the driver control display screen and the power supply circuit respectively; the auxiliary driving controller includes a vehicle 360° surround view module, a driver monitoring module, a personnel anti-approach module and a front obstacle warning module; The vehicle's 360° surround view module is configured as follows: 4 to 6 groups of wide-angle (fisheye) cameras distributed around the vehicle are used to dynamically collect images around the vehicle; fisheye images are distorted and converted into standard visual images through algorithms such as pixel point coordinate conversion and image pixel interpolation; the image field of view is converted from front view to top view through the pixel matrix coordinate conversion algorithm; the 4 to 6 groups of images collected and converted are stitched and fused according to the 360° model around the vehicle using the FAST (fast corner detection) algorithm, and finally a 360° visual image (eagle-eye perspective) of the vehicle's surroundings is formed from above the vehicle; Figure 4 The image processing flow chart of the vehicle's 360° surround view module is shown; The driver monitoring module is configured as follows: the driver's facial image information is collected through the in-car camera, and two types of analysis are performed using the Driver Monitoring System (DMS): one is fatigue warning: the driver's facial image information is identified and analyzed, the aspect ratio of the eyes and mouth (open or closed) is calculated, and the time thresholds for closing eyes and yawning under fatigue conditions are set. When the detected image exceeds the threshold at a continuous image frame rate, an audible and visual alarm is issued; the other is inattention warning: the driver's facial image information is identified and analyzed, and the time thresholds for lowering the head and tilting the head are set. When the driver's non-frontal image is detected at a continuous image frame rate and exceeds the threshold, an audible and visual alarm is issued; Among them, the personnel anti-approach module is configured as follows: 8 ultrasonic radars installed around the vehicle detect obstacles within a range of 3 meters to 5 meters. The detected obstacles include personnel, production tools, and mine passage walls. The obstacle reminder information detected by the above detection and induction is combined with 4 to 6 groups of images collected before 360° surround view image processing to perform image recognition of obstacles. When personnel information is detected within 3 meters to 5 meters around the vehicle, a personnel approach warning reminder is issued; Among them, the front obstacle warning module is configured as follows: the millimeter wave radar is used to detect obstacles in front of the vehicle, and the detection distance of the millimeter wave radar is 100 meters; the image dust removal and defogging algorithm based on the dark channel filter is used to pre-process the front obstacle warning (FCW) forward acquisition image; because there is a lot of dust in the mine environment and the air is humid and fog is easy to generate, it is necessary to remove dust and fog from the image collected by the FCW forward high-definition camera; in computer vision and computer graphics, the dust and fog image formation model described by the following equation is widely used:

[0020] in, I ( x ) is the existing image (the image to be dust-removed), J (x ) is the dust-free fog image to be restored, A is the atmospheric light component, t ( x ) is the transmittance; the known conditions are I ( x ), this embodiment uses dark channel theory to solve the unknowns, and finally obtains a dust-free image J ( x ); In most non-sky local areas (including the illuminated environment in the mine), some pixels always have at least one color channel with a very low value, that is, the minimum value of the light intensity in this area is a very small number; for any input image J, its dark channel can be expressed as follows:

[0021] (2) In the formula Represents each channel of a color image, represents a window centered on pixel X. When implementing the algorithm, the window radius is set in combination with the dust removal effect and the operating efficiency. In this embodiment, the actual setting value is 10, that is, the dust removal window is set to a 20×20 pixel matrix. Combining graphic theory and a large amount of actual data, the dark channel of the dust-free fog image has the following characteristics:

[0022] That is, in the local area other than the sky (including the illuminated environment in the mine), the dark channel of the dust-free fog image has the characteristic of approaching 0. Applying the above dark channel theory to resolve the unknowns, first transform equation (1) into the following equation:

[0023] The superscript C represents the three channels of the image R / G / B. In the atmospheric environment inside the mine, the transmittance inside the window is t ( x ) is a constant, defined as , the atmospheric component A is also a constant. By performing two minimum operations on both sides of equation (4), we get the following equation:

[0024] In the above formula, J is the dust-free image to be obtained. According to the aforementioned dark channel theory, we have:

[0025] It can be deduced that:

[0026] Substituting equation (7) into equation (5), we get:

[0027] Therefore, the transmittance in the atmospheric environment of the mine can be calculated by using the dust fog image to be removed. The estimated value of In practical applications, there are always some particles in the air, so when looking at distant objects, we can always feel the presence of dust and fog. At the same time, the presence of dust and fog also gives the image a sense of depth of field. Therefore, a certain degree of dust and fog needs to be retained. By introducing a factor between [0,1] in formula (8), formula (8) is corrected to:

[0028] This embodiment sets ω =0.95, and thus the transmittance in the atmospheric environment of the mine is calculated by using the dust fog image to be removed ; In this embodiment, the atmospheric light component A value is obtained from the dust fog image by means of the dark channel image. The specific steps are: taking the first 0.1% of pixels in the dark channel image according to the brightness; among these positions, finding the value of the corresponding point with the highest brightness in the original dust fog image I as the A value; Using the above calculation formula, the transmittance in the atmospheric environment can be calculated through the dust and fog image to be removed. And the atmospheric light component A value; the following image dust removal processing is performed: Applying formula (1), we can know that: J = (I - A) / t + A ; In practical applications, when the projection rate t value is very small, the value of J will be too large, so that the overall white field of the image is excessive. Therefore, a threshold T0 can be set. When the t value is less than T0, t=T0. In this embodiment, all effect diagrams are calculated based on T0=0.1. Therefore, the final image dust removal formula is as follows:

[0029] In this embodiment, combined with the particularity of the underground lighting environment, the dust removal fog window Based on the actual effect and the calculation efficiency, the pixel matrix of 20×20 is set to be ideal, the dust and fog retention constant is set to ω=0.95, and the minimum white field revision value is set to T0=0.1; The forward-facing high-definition camera collects images, and the system processor uses a learning model to perform image recognition on the forward-facing image. It then integrates the millimeter-wave radar detection information to judge the image information and identify the obstacle type; obstacle types include personnel, production tools, mine passage walls, and road obstacles; the forward obstacle recognition detection range is 100 meters, and the speed limit for vehicles in the mine is 30 km / h. Therefore, the driver is provided with forward obstacle warning information at least 12 seconds in advance, so that the driver can perform emergency braking, deceleration, and other avoidance driving operations; It should be noted that in this implementation, the intrinsically safe equipment solution adopted by the intrinsically safe mining auxiliary driving system is based on the GB3836.4-2021 intrinsically safe equipment standard. The hardware and structural design of the system adopts the following design: (1) Power board design: The system power design uses low-energy release components, that is, components that will not release a large amount of energy under fault conditions, and limit the selection of power circuit component parameters (capacitor capacitance, inductor value). By adding a protection circuit to the power circuit, the voltage and current are limited to reduce the generation of electric sparks and thermal effects; Figure 2 The figure shows a power supply output circuit diagram with power component parameter restrictions; optimize the power supply circuit loop design and limit the voltage and current in the circuit so that it does not exceed the safety limit set by the power supply system (24V) of this system specified in the GB3836.4-2021 standard in both normal operation and fault conditions; (2) Input and output interface protection: Install protection devices in the system's external input and output interface circuits, and select fuses, circuit breakers, voltage limiting diodes (TVS), overcurrent protection devices (PTC), etc. according to the electrical characteristics of the interface (voltage, circuit) to promptly cut off the power supply or limit the scope of the fault when a fault occurs in the system or the load connected to the interface; Figure 3 Shown is a power input circuit diagram with surge suppression and current limiting; (3) Circuit board (PCB) protection: Based on the safety limits of PCB line width and line spacing of the power supply system (24V) of this system specified in GB3836.4-2021, the layout and wiring of the circuit board (PCB) are optimized to ensure that the circuit board routing design meets the safety range of line width and line spacing settings; (4) Structural design: The system structural design is equipped with heat dissipation devices to ensure that the heat generating devices will not cause local overheating during the operation of the product. The heat generated during operation can be dissipated in time to avoid local overheating and causing danger. The system shell and external wiring harness are selected based on high temperature resistance and flame retardant properties. The internal structure of the system adopts an independent compartment isolation design for the system circuit board. When the system overheats or there is a risk of explosion outside, the heat source is isolated in time or prevented from spreading.

[0030] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. An intrinsically safe mining auxiliary driving system, characterized in that: The intrinsically safe mining auxiliary driving system includes an auxiliary driving controller, a surround view camera, an ultrasonic radar, a driver monitoring camera, a forward millimeter wave radar, a forward camera, a driver control display screen and a power supply circuit; The auxiliary driving controller is electrically connected to the surround view camera, the ultrasonic radar, the driver monitoring camera, the forward millimeter wave radar, the forward camera, the driver control display screen and the power supply circuit respectively.

2. The intrinsically safe mining auxiliary driving system according to claim 1 is characterized in that: The auxiliary driving controller includes a vehicle 360° surround view module, a driver monitoring module, a personnel approach prevention module and a front obstacle warning module; The vehicle 360° surround view module is used to obtain an eagle-eye perspective image; the driver monitoring module is used to obtain driver fatigue alarm information and inattention alarm information; The personnel approach prevention module is used to obtain personnel approach warning information; The front obstacle warning module is used to obtain obstacle type and warning information.

3. The intrinsically safe mining auxiliary driving system according to claim 2 is characterized in that: The vehicle's 360° surround view module is configured as follows: using the surround view camera to dynamically collect fisheye images around the vehicle; using pixel point coordinate conversion and image pixel interpolation algorithms to correct the distortion of the fisheye images around the vehicle to obtain a standard visual image; using a pixel matrix coordinate conversion algorithm to convert the field of view of the standard visual image from front view to top view to obtain a top view image; based on the top view image, according to the 360° model around the vehicle, using a fast corner point detection algorithm to perform image stitching and fusion, to obtain an eagle-eye perspective image.

4. The intrinsically safe mining auxiliary driving system according to claim 2 is characterized in that: The driver monitoring module is configured as follows: using the driver monitoring camera to collect driver facial image information, identifying and analyzing the driver facial image information to obtain eye aspect ratio and mouth aspect ratio, and obtaining eye closing time and yawning time according to the driver facial image information, eye aspect ratio and mouth aspect ratio; when the eye closing time is greater than a preset eye closing time threshold, or the yawning time is greater than a preset yawning time threshold, a fatigue alarm message is obtained.

5. The intrinsically safe mining auxiliary driving system according to claim 2 is characterized in that: The driver monitoring module is also configured to: use the driver monitoring camera to collect the driver's facial image information, identify and analyze the driver's facial image information, and obtain the head lowering time and the head tilting time; when the head lowering time is greater than the preset head lowering time threshold, or when the head tilting time is greater than the preset head tilting time threshold, obtain an inattention alarm message.

6. The intrinsically safe mining auxiliary driving system according to claim 2 is characterized in that: The personnel anti-approach module is configured as follows: using the ultrasonic radar to obtain information about neighboring obstacles, using the surround-view camera to obtain a standard visual image, performing image recognition on the standard visual image to obtain information about surrounding personnel, and obtaining personnel approach warning information based on the surrounding personnel information and the neighboring obstacle information.

7. The intrinsically safe mining auxiliary driving system according to claim 2 is characterized in that: The front obstacle warning module is configured as follows: Utilizing the forward millimeter-wave radar to detect obstacles ahead of the vehicle, and obtaining millimeter-wave radar detection information; Using the forward camera to acquire an image and obtain a forward image; Performing a pre-dust and fog removal process on the forward image to obtain a dust and fog removed image; Performing image recognition on the dust removal mist image to obtain recognition image information; The millimeter wave radar detection information and the recognition image information are combined to make a judgment to obtain the obstacle type and warning information.

8. The intrinsically safe mining auxiliary driving system according to claim 7, characterized in that: The forward image is pre-dust-removed to obtain a dust-removed image, as shown in the formula: ， ， in, To remove dust and fog images, is the dust and fog image to be removed, i.e. the forward image. is the atmospheric light component value, is the transmittance, is the minimum revision value of the white field, Keep constant for dust and fog, In pixels A dust removal window in the center, Represents the three channels of the image R / G / B, Represents each channel value of a color image, A per-channel value representing the atmospheric light component.

9. The intrinsically safe mining auxiliary driving system according to claim 1, characterized in that: The power circuit includes a power board and an input / output interface protection device, wherein the power board includes low-energy release components and a protection circuit; the protection circuit is used to limit voltage and current to reduce the generation of electric sparks and thermal effects; The input and output interface protection device is used to cut off the power supply in time and limit the scope of the fault when the intrinsically safe mining auxiliary driving system or the load connected to the interface fails; the input and output interface protection device includes a fuse, a circuit breaker, a voltage limiting diode and an overcurrent protector; The intrinsically safe mining auxiliary driving system also includes a heat dissipation device, a high temperature resistant and flame retardant isolated independent cabin shell and an external wiring harness.

10. A driving assistance method, characterized in that: include: By using the intrinsically safe mining auxiliary driving system as described in any one of claims 1 to 9, an eagle-eye perspective image, driver fatigue alarm information, inattention alarm information, personnel approach warning information, obstacle type and warning information are obtained; Controlling the controlled vehicle according to the eagle-eye perspective image, the personnel approach warning information, the obstacle type and the warning information; The driver of the controlled vehicle is warned according to the driver fatigue warning information and the inattention warning information.

Images