Obstacle early warning method and device, electronic equipment, storage medium and vehicle

Abstract

The invention provides an obstacle early warning method and device, electronic equipment, a storage medium and a vehicle, and relates to the technical field of vehicles. The method comprises the following steps: in a vehicle driving process, determining whether a vehicle is in an uphill scene, and when it is determined that the vehicle is in the uphill scene, determining a target sensing area of early warning detection according to a first sensing area of a fisheye camera and a second sensing area of an ultrasonic radar, the target sensing area comprises an overlapping area of the first sensing area and the second sensing area, and an area, located below the overlapping area, in the first sensing area. And finally, carrying out obstacle detection and early warning on the target sensing area. By means of the method, the sensing capacity of the vehicle on the obstacles in the uphill scene, especially on the obstacles in the blind area close to the front lower portion of the vehicle, is effectively improved, and the reliability of obstacle early warning of the vehicle in the uphill scene is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to an obstacle warning method and device, an electronic device, a storage medium and a vehicle. BACKGROUND

[0002] With the continuous popularization of assisted driving technology, the obstacle warning function in driving scenarios has become an important configuration to improve driving safety.

[0003] The existing obstacle warning in driving scenarios usually adopts fixed perception areas and alarm logic, that is, by fusing the perception data of ultrasonic radar and fisheye camera on the front bumper, the distance and risk of the obstacle in front of the vehicle are determined, and the driver is warned through the human-machine interface (HMI) when a collision is likely to occur. However, in the actual driving environment, especially when the vehicle is on an uphill or hilltop position, due to the lifting of the vehicle head, the vertical field of view of the sensor is limited, resulting in a blind area in the lower front area of the vehicle, thereby increasing the risk of collision with low obstacles.

[0004] In summary, the existing obstacle warning method based on fixed perception areas is difficult to achieve accurate and reliable collision warning when the vehicle is in an uphill scenario. SUMMARY

[0005] The present application provides an obstacle warning method, device, electronic device, storage medium and vehicle to improve the reliability of obstacle warning of the vehicle in an uphill scenario.

[0006] In a first aspect, the embodiments of the present application provide an obstacle warning method, comprising:

[0007] During the driving of the vehicle, it is determined whether the vehicle is in an uphill scenario;

[0008] If it is determined that the vehicle is in an uphill scenario, a target perception area for warning detection is determined according to a first perception area of a fisheye camera and a second perception area of an ultrasonic radar, the target perception area including an overlapping area of the first perception area and the second perception area and an area in the first perception area below the overlapping area;

[0009] Obstacle detection and warning are performed on the target perception area.

[0010] In a possible implementation, the determination of whether the vehicle is in an uphill scenario includes:

[0011] According to the position information and / or slope information of the vehicle, it is determined whether the driving scenario of the vehicle is an uphill scenario.

[0012] In a possible implementation, the determining whether the driving scenario of the vehicle is an uphill scenario according to the position information and / or the slope information of the vehicle comprises:

[0013] obtaining the position information of the vehicle, and determining whether the vehicle is currently in an uphill scenario according to the position information and a map navigation system;

[0014] or,

[0015] determining whether the vehicle is currently in an uphill scenario based on a slope of a current position of the vehicle detected by a slope sensor;

[0016] or,

[0017] determining whether the vehicle is currently in an uphill scenario based on a slope of a current position of the vehicle detected by a slope sensor and the position information of the vehicle in combination with map navigation information.

[0018] In a possible implementation, the obstacle detection and early warning for the target sensing area comprises:

[0019] if it is detected that the line-of-sight direction of the driver of the vehicle does not focus on the front of the vehicle, performing obstacle detection and early warning for the target sensing area.

[0020] In a possible implementation, the obstacle detection and early warning for the target sensing area comprises:

[0021] if it is detected that the line-of-sight direction of the driver of the vehicle does not focus on the front of the vehicle, and the vehicle speed of the vehicle is less than or equal to a preset vehicle speed, performing obstacle detection and early warning for the target sensing area.

[0022] In a possible implementation, the obstacle detection and early warning for the target sensing area comprises:

[0023] performing obstacle detection for the target sensing area based on an image processing algorithm;

[0024] when it is detected that there is an obstacle in the target sensing area, pushing an early warning prompt information.

[0025] In a possible implementation, the pushing of the early warning prompt information comprises:

[0026] pushing the early warning prompt information through an acousto-optic prompting mode and / or a steering wheel vibration mode.

[0027] In a second aspect, an embodiment of the present application provides an obstacle early warning device, comprising:

[0028] The first processing module is configured to determine whether the vehicle is in an uphill scene during vehicle driving.

[0029] The second processing module is configured to determine a target sensing area for early warning detection according to a first sensing area of the fisheye camera and a second sensing area of the ultrasonic radar if it is determined that the vehicle is in the uphill scene, wherein the target sensing area includes an overlapping area of the first sensing area and the second sensing area and an area below the overlapping area in the first sensing area.

[0030] The third processing module is configured to perform obstacle detection and early warning on the target sensing area.

[0031] In a third aspect, an electronic device is provided, including a memory and a processor.

[0032] The memory stores computer-executable instructions.

[0033] The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to the first aspect and / or various possible implementation manners of the first aspect.

[0034] In a fourth aspect, a vehicle is provided, including a vehicle body and a controller, wherein the controller is configured to perform the method according to the first aspect and / or various possible implementation manners of the first aspect.

[0035] In a fifth aspect, a computer-readable storage medium is provided, which stores computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method according to the first aspect and / or various possible implementation manners of the first aspect.

[0036] The obstacle early warning method, device, electronic device, storage medium and vehicle provided by the present application can effectively improve the sensing ability of the vehicle to obstacles, especially to obstacles near the blind area below the front of the vehicle, and improve the reliability of obstacle early warning of the vehicle in the uphill scene. BRIEF DESCRIPTION OF DRAWINGS

[0037] The accompanying drawings, which are incorporated herein and form part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the application.

[0038] Figure 1 A schematic diagram of the perception area in a driving scenario (flat road) provided in this application;

[0039] Figure 2 A schematic diagram of the perception area of ​​a vehicle in an uphill scenario provided in this application;

[0040] Figure 3 A flowchart illustrating an obstacle warning method provided in this application. Figure 1 ;

[0041] Figure 4 A flowchart illustrating an obstacle warning method provided in this application. Figure 2 ;

[0042] Figure 5 A flowchart illustrating an obstacle warning method provided in this application. Figure 3 ;

[0043] Figure 6 This is a schematic diagram of the structure of an obstacle warning device provided in this application;

[0044] Figure 7 A schematic diagram of the structure of the electronic device provided in this application.

[0045] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0046] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0047] The application background of this application is explained as follows:

[0048] With the popularization of intelligent driving and assisted driving technologies, obstacle warning function has become one of the key technologies to improve driving safety. The core objective of this function is to detect obstacles in the vehicle's surrounding environment (such as pedestrians, children, small animals or fixed obstacles) and promptly issue an alarm to the driver through the HMI interface when the vehicle is too close to the obstacle or there is a risk of collision, so as to reduce the incidence of collision accidents.

[0049] Figure 1 This application provides a schematic diagram of the perception area in a prior art driving scenario (flat road), as shown below. Figure 1 As shown, existing obstacle warning systems in driving scenarios typically employ fixed perception areas and alarm logic. This involves combining perception data from ultrasonic radar and fisheye cameras to locate and assess the risk of obstacles ahead. Specifically, a fisheye camera installed under the windshield acquires image data of the area in front of the vehicle using a wide-angle lens; its vertical field of view (FOV) is the first perception area. An ultrasonic radar installed on the front bumper emits ultrasonic waves and receives the echoes to measure the vertical distance between the obstacle and the vehicle; its vertical field of view (FOV) is the second perception area. If an obstacle exists within the overlapping perception area (Area A) of the ultrasonic radar and fisheye camera's vertical field of view, and the obstacle is too close or poses a collision risk, a visual or auditory warning signal is issued to the driver through the HMI interface. Area A can cover most normal, flat road driving conditions.

[0050] Figure 2 This application provides a schematic diagram of the perception area for a vehicle in an uphill scenario, as shown in the prior art. Figure 2 As shown, in real-world usage scenarios, especially when the vehicle is going uphill, the front of the car faces upwards due to the change in slope, significantly increasing the blind spot below and in front of the front. In this situation, if an obstacle (such as a child or small animal) suddenly enters the blind spot, such as... Figure 2 The perception area shown cannot cover obstacles within the blind spot. If the driver is looking left and right at the road conditions but does not pay attention to the environment ahead in time, it is difficult to achieve accurate and reliable collision warning through the existing obstacle warning methods in driving scenarios.

[0051] In summary, existing obstacle warning methods based on fixed sensing areas are difficult to achieve accurate and reliable collision warnings when the vehicle is on an uphill slope.

[0052] Based on the aforementioned technical problems, the inventors, in the process of researching obstacle warning methods for uphill scenarios, discovered that by determining that the vehicle is in an uphill scenario based on the vehicle's map positioning information or slope sensor data, the sensing area of ​​the ultrasonic radar installed on the vehicle's front bumper and the sensing area of ​​the fisheye camera installed under the vehicle's windshield are overlapped. The overlapping sensing area of ​​the two, as well as the area of ​​the fisheye camera's sensing area located below the overlapping sensing area, is defined as the target sensing area for warning detection. This expands the coverage of the sensing area under uphill conditions, effectively capturing obstacles that enter the blind spot below the front of the vehicle in uphill scenarios, thereby improving the accuracy and reliability of obstacle warnings in uphill scenarios and ensuring driving safety. Based on this, this application provides an obstacle warning method, device, electronic device, storage medium, and vehicle.

[0053] The obstacle warning method provided in this application is applicable to complex driving scenarios where vehicles are going uphill and drivers are distracted, such as uphill ramps exiting underground parking lots and steep slope passages in residential areas. It can specifically solve the problem of blind spots caused by the vehicle's nose tilting up in such conditions, and the problem that drivers are distracted and cannot detect sudden obstacles below the front of the vehicle in time, thus providing reliable protection for driving safety in complex uphill scenarios.

[0054] The technical solution of this application and how it solves the above-mentioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0055] Figure 3 A flowchart illustrating an obstacle warning method provided in this application. Figure 1 ,like Figure 3 As shown, the method includes:

[0056] S301: Determine whether the vehicle is in an uphill scenario while it is in motion.

[0057] Understandably, when a vehicle is going uphill, the front of the car tilts upwards with the slope. The detection angle of the onboard sensing equipment (cameras, ultrasonic radar, etc.) that was originally facing directly forward also shifts upwards, and their sensing range rises accordingly. This causes the area below and in front of the vehicle, close to the ground, to fall outside the detection range of the onboard sensing equipment. Simultaneously, this area is a blind spot for the driver. This blind spot is precisely a high-risk area where low obstacles such as children and small animals can easily wander in.

[0058] In one possible implementation, the vehicle's driving scenario can be determined as an uphill scenario based on the vehicle's location information and / or slope information.

[0059] Optionally, the vehicle's driving scenario can be determined as an uphill scenario based on the vehicle's location information and / or slope information.

[0060] The vehicle's location information includes real-time latitude, longitude, and heading geographic coordinates obtained from the vehicle's onboard satellite navigation system. Based on this location information and the map navigation system, the slope information of the road the vehicle is currently on can be determined. Slope information includes the inclination angle (slope angle) or longitudinal slope data of the road the vehicle is currently on. The longitudinal slope data refers to the quantified value of the road's longitudinal slope (the direction of vehicle travel). Understandably, determining whether the vehicle is on an uphill slope is a prerequisite for triggering subsequent obstacle warnings.

[0061] S302: If it is determined that the vehicle is in an uphill scenario, the target perception area for warning detection is determined based on the first perception area of ​​the fisheye camera and the second perception area of ​​the ultrasonic radar. The target perception area includes the overlapping area of ​​the first perception area and the second perception area, as well as the area in the first perception area located below the overlapping area.

[0062] In this step, a fisheye camera is an imaging device equipped with an ultra-wide-angle lens, whose lens angle of view typically reaches... even The above-mentioned device can be installed under the windshield of a vehicle. Its sensing area (first sensing area) presents a wide-angle fan-shaped field of view with the camera installation position as the apex. It can cover the near-ground area below the front of the vehicle that ordinary vehicle cameras cannot capture due to the limitation of the viewing angle, providing key near-ground field of view support for the delineation of the target sensing area.

[0063] Ultrasonic radar is a sensing device that uses the principle of ultrasonic wave emission and reflection to detect distance. It emits ultrasonic signals of a specific frequency in the detection direction; when the signal contacts an obstacle, it produces a reflected echo. By utilizing the time difference between the emitted and received echoes, combined with the speed of ultrasonic waves in the air, the distance between the vehicle and the obstacle can be determined. Ultrasonic radar is typically mounted on the front bumper of a vehicle. Its sensing area (second sensing area) presents a cone-shaped detection field of view with the ultrasonic radar probe as the apex. Its detection range is generally 0.1 to 5 meters, which perfectly matches the close-range monitoring needs of the blind spot below the front of the vehicle when going uphill. It complements the first sensing area, improving the reliability of obstacle recognition in low-speed uphill scenarios and reducing the probability of missed or false detections.

[0064] Understandably, the overlapping area of ​​the first and second sensing areas can combine the image recognition advantages of the fisheye camera with the precise ranging capability of the ultrasonic radar to achieve cross-verification of obstacle information. The part of the first sensing area located below the overlapping area can cover the near-ground blind zone outside the radar detection range. The overlapping area and the area below it together constitute a target sensing area adapted to uphill scenarios, providing a complete and reliable monitoring range for subsequent accurate early warning.

[0065] S303: Perform obstacle detection and early warning in the target perception area.

[0066] By detecting obstacles within the target perception area, the system identifies the types of obstacles present and issues warnings. For example, when obstacles such as children or small animals that are mobile and affect the smooth passage of the vehicle are detected within the target perception area, a warning message is pushed to the driver through the HMI interface, helping the driver to take timely evasive action and reduce the driving risks caused by sudden obstacles.

[0067] This application provides an obstacle warning method that determines whether a vehicle is in an uphill state based on its location and / or slope information during vehicle operation. When it is confirmed that the vehicle is in an uphill scenario, a target perception area covering the blind spot below the front of the vehicle is determined based on the wide-angle visual perception area (first perception area) of the fisheye camera and the near-field detection area (second perception area) of the ultrasonic radar. This target perception area includes the overlapping area of ​​the first and second perception areas, as well as the area below the overlapping area in the first perception area. Finally, obstacle detection and warning are performed on the target perception area. This method solves the problem of missed or misjudged obstacles caused by the specific near-ground blind spot due to the vehicle's elevation angle when the vehicle is in an uphill scenario. It significantly improves the perception and warning capabilities for low obstacles such as children and small animals in uphill scenarios, effectively reducing the resulting driving safety risks.

[0068] Based on the above embodiments, in S301: It is determined whether the vehicle's driving scenario is an uphill scenario based on the vehicle's location information and / or slope information, specifically including the following situations:

[0069] (1) Obtain the vehicle's location information and determine whether the vehicle is currently in an uphill scenario based on the location information and the map navigation system.

[0070] The high-precision electronic maps built into the map navigation system (such as commercial or high-precision versions of Baidu Maps and Gaode Maps) pre-store detailed geographic attribute data covering road slope, elevation changes, and road surface types. For example, the real-time latitude and longitude coordinates of the vehicle can be obtained by relying on the vehicle's in-vehicle Global Positioning System (GPS) or Beidou satellite navigation system. Combined with the map navigation system, the road slope corresponding to the vehicle's location in the high-precision electronic map can be obtained, and it can be directly determined whether the vehicle is currently in an uphill scenario.

[0071] Specifically, road slope can be quantified by longitudinal slope value, which is the quantified value of the slope in the longitudinal direction (vehicle travel direction). This longitudinal slope value is calculated by the ratio of the elevation difference between two points in the longitudinal direction of the road to the horizontal projection distance. The specific calculation method is as follows: Where A represents the longitudinal slope; S1 represents the endpoint elevation; S2 represents the starting elevation; and S represents the horizontal distance between the endpoint and the starting point. Road slope can also be quantified using slope angles, that is, in degrees. The slope angle can be calculated using the arctangent function. .

[0072] Understandably, taking the vehicle's current direction of travel as a reference, a positive road gradient indicates the vehicle is uphill, with the value directly reflecting the steepness of the uphill slope; a larger value indicates a steeper slope. Conversely, a negative road gradient indicates the vehicle is downhill, with a larger absolute value indicating a steeper downhill slope. A zero road gradient indicates the vehicle is traveling on a flat road.

[0073] (2) Based on the slope detected by the slope sensor, determine whether the vehicle is currently in an uphill scenario.

[0074] A slope sensor is an onboard sensing device that directly collects the inclination angle or slope value of the road surface on which a vehicle is traveling. It is typically mounted on the vehicle's chassis frame and senses changes in the angle between the direction of gravity and the sensor's mounting plane. It converts the physical angle signal into an electrical or digital signal that can be recognized by the vehicle's control system, thereby accurately obtaining the road slope data at the vehicle's current location. When the slope value detected by the slope sensor is within a preset positive range, the vehicle control system can determine that the vehicle is currently on an uphill slope. For example, when the slope value detected by the slope sensor is greater than... At that time, it was determined that the vehicle was currently in an uphill scenario.

[0075] (3) Based on the slope detected by the slope sensor and the vehicle's current location, and combined with the vehicle's location information and map navigation information, determine whether the vehicle is currently in an uphill scenario.

[0076] In one exemplary scenario, when a vehicle travels to a temporary construction ramp where map data has not been updated in a timely manner, or when the high-precision electronic map does not store the slope data for that temporary ramp, relying solely on location information combined with the map navigation system may not accurately determine whether the vehicle is currently in an uphill scenario. In this case, the slope values ​​collected in real time by the slope sensor can serve as the core basis for judgment, ensuring the effectiveness of the uphill scenario determination. In another exemplary scenario, when the slope sensor malfunctions, is affected by external signal interference, or its detection accuracy decreases, and it cannot output accurate slope detection data, relying solely on the slope sensor cannot effectively determine the uphill scenario. In this case, based on the vehicle's location information and the road slope corresponding to the vehicle's location in the high-precision electronic map obtained by the map navigation system, it can be directly determined whether the vehicle is currently in an uphill scenario.

[0077] By combining slope sensor data, vehicle location information, and map navigation information, a composite judgment method can effectively avoid the judgment risk caused by the failure of a single detection method, and ultimately improve the reliability and stability of vehicle uphill scene judgment.

[0078] Figure 4 A flowchart illustrating an obstacle warning method provided in this application. Figure 2 ,like Figure 4 As shown, based on the above embodiment, in S303: obstacle detection and warning are performed on the target perception area, specifically including:

[0079] S401: Obtain the driver's in-loop status.

[0080] In this step, being effectively in the loop requires the driver to be in a state where they can take over the vehicle or make driving decisions in a timely manner based on real-time road conditions. It emphasizes that the driver must be in an effective participation state where their attention is online and they can access the system at any time.

[0081] Specifically, in-vehicle sensors such as infrared cameras and high-definition vision cameras installed in front of the steering wheel, above the dashboard, or in the rearview mirror can collect real-time facial image sequences of the driver. These in-vehicle sensors can clearly capture the driver's eye features under different lighting conditions, such as daytime and nighttime, including key information such as pupil position, eyeball rotation angle, and eyelid opening and closing status. The Driver Monitoring System (DMS) analyzes the data and outputs the driver's on-loop status.

[0082] By combining in-vehicle visual sensing devices with the DMS system to obtain the driver's on-loop status, it is possible to accurately determine whether the driver is attentive and in an effective state where they can take over the vehicle at any time. This provides a key decision-making basis for triggering subsequent obstacle detection and warning functions, effectively avoiding safety hazards caused by the driver's lack of concentration.

[0083] S402: Determine whether the driver's gaze is focused on the front of the vehicle.

[0084] If not, execute S403; if yes, execute S404.

[0085] The driver's line of sight is one of the bases for determining whether the driver is in an effective state of responsiveness. It refers to the direction in which the driver's eyes are pointing, specifically the angle and direction of the driver's line of sight relative to the vehicle's coordinate system or the road's coordinate system. It is a key quantitative indicator for judging whether the driver is paying attention to the road conditions ahead. The direction of the line of sight directly reflects the driver's level of attention to the road conditions ahead, and continuous attention to the road conditions ahead is a prerequisite for the driver to respond promptly to emergencies and take over the vehicle at any time.

[0086] S403: Perform obstacle detection and early warning in the target perception area.

[0087] In other words, if it is detected that the driver's line of sight is not focused on the front of the vehicle, obstacle detection and warning will be performed in the target perception area.

[0088] Understandably, when a driver's gaze is not focused on the vehicle ahead, their ability to perceive sudden obstacles and changes in road conditions is significantly reduced, making it difficult to take evasive action in a timely manner. This delayed reaction greatly increases the risk of a collision. Since this off-track state of driver attention poses a significant safety hazard, proactive obstacle detection and warnings within the target perception area can compensate for the driver's blind spots and ensure driving safety.

[0089] In another possible implementation, if it is detected that the driver's gaze is not focused on the front of the vehicle and the vehicle speed is less than or equal to a preset speed, then obstacle detection and warning are performed on the target perception area.

[0090] This scenario is based on the characteristics of low-speed driving, often occurring in congested areas, parking lot entrances / exits, residential roads, and uphill starts. These low-speed uphill scenarios not only involve relatively narrow passageways and high frequency of pedestrian and non-motorized vehicle traffic, but also present additional risks such as vehicle start-up jerking and close following distances from vehicles approaching from behind. For example, the preset speed could be 20 km / h. If the driver's gaze is not focused on the road ahead, and the vehicle speed is less than or equal to 20 km / h, obstacle detection and warnings are issued for the target perception area. This accurately matches the safety requirements of low-speed uphill scenarios, providing effective support for drivers to avoid risks in a timely manner.

[0091] S404: Maintain the standard detection area and do not send warning messages.

[0092] In other words, if the system detects that the driver's gaze is focused on the front of the vehicle, it will maintain the standard detection area and will not send any warning messages.

[0093] Understandably, when a driver's gaze is focused on the front of the vehicle, it indicates that the driver is in a state of focused attention and can effectively monitor the driving environment. The driver can promptly detect potential risks such as pedestrians and obstacles in the target perception area ahead through their own observation, and autonomously take evasive actions such as braking and avoidance based on the actual road conditions. At this time, there is no need to detect obstacles and issue warnings in the target perception area. Maintaining a standard detection area is sufficient to meet driving safety requirements. At the same time, it can also avoid distracting the driver's attention due to frequent push notifications of unnecessary warning information, and prevent interference with normal driving operations.

[0094] The obstacle warning method provided in this application embodiment acquires the driver's on-loop status through an in-vehicle vision sensing device combined with a DMS system, and determines whether the driver's gaze is focused on the area in front of the vehicle. When it is determined that the driver's gaze is not focused on the area in front, obstacle detection and warning are actively performed on the target perception area; if the driver's gaze is focused on the area in front, the standard detection area is maintained, and no warning prompt is pushed. Through the above method, obstacle detection and warning for the blind spot below the front of the vehicle are only activated when the driver's attention may be distracted (such as when the gaze deviates). This provides effective safety redundancy to compensate for blind spots when the driver's attention is insufficient, and avoids unnecessary warning interference when the driver is focused on driving. Thus, it significantly improves uphill driving safety, optimizes the human-machine co-driving experience, and reduces the interference of system false alarms on driving operations.

[0095] Figure 5 A flowchart illustrating an obstacle warning method provided in this application. Figure 3 ,like Figure 5As shown, based on the above embodiment, in S403: obstacle detection and warning are performed on the target perception area, specifically including:

[0096] S501: Obstacle detection in the target perception area based on image processing algorithms.

[0097] By collecting environmental data within the vehicle's target perception area using in-vehicle sensing devices such as cameras and ultrasonic radar, and analyzing the collected environmental data through image processing algorithms, the types of obstacles within the target perception area can be identified, and it can be determined whether there are mobile obstacles such as children or small animals that may affect driving safety, thereby reducing the driving risks caused by sudden obstacles.

[0098] For example, the image processing algorithm can be the YOLO series real-time target detection algorithm, the SSD (Single Shot MultiBox Detector) single-stage detection algorithm, or the Faster R-CNN two-stage detection algorithm, etc., to quickly extract features and identify targets from environmental data in the target perception area, providing data support for subsequent early warning decisions.

[0099] S502: Determine whether there are obstacles within the target perception area.

[0100] If yes, then execute S503; otherwise, execute S504.

[0101] S503: Pushes early warning notification messages.

[0102] In other words, when an obstacle is detected within the target's perception area, a warning message is sent.

[0103] As mentioned in S302, the target perception area includes the overlapping area of ​​the first perception area of ​​the fisheye camera and the second perception area of ​​the ultrasonic radar, as well as the area in the first perception area located below the overlapping area. That is, the target perception area includes the area in front of the vehicle and the near-ground blind spot formed due to the tilt of the vehicle's front.

[0104] If there is an obstacle in the target perception area, a warning message will be pushed to the driver through sound and light prompts and / or steering wheel vibration. That is, the warning message will be pushed through sound alarms, dashboard pop-ups or steering wheel vibration, etc., to promptly remind the driver to take braking or evasive measures and effectively eliminate the safety hazards caused by blind spots.

[0105] S504: Do not push warning messages.

[0106] In other words, if there are no obstacles within the target's perception area, no warning message will be sent.

[0107] Understandably, the absence of obstacles within the target perception area indicates that there are no factors affecting driving safety in the vehicle's current driving path. In this case, even if the driver is in a low-speed uphill or other conditions with limited visibility, there is no need for additional warning prompts to interfere with normal driving operations. This can avoid meaningless warning information from distracting the driver's attention, improve the user experience, and reduce the computing power consumption of the vehicle system.

[0108] The obstacle warning method provided in this application further refines the specific execution process of obstacle detection and warning in the target perception area of ​​an uphill scene when the driver's eyes are not focused on the road ahead. Specifically, it includes: real-time obstacle detection and identification of the target perception area using image processing algorithms (such as YOLO, SSD, Faster R-CNN, etc.), and determining whether an obstacle exists within the area based on the detection results. If an obstacle exists within the target perception area, a warning message is pushed to the driver through audio-visual cues or steering wheel vibration; if no obstacle exists within the target perception area, no warning is issued. This method achieves accurate identification and proactive warning of obstacles in the blind spot in front of and below the vehicle in uphill scenes, effectively compensating for the perception gap when the driver's attention is distracted, improving driving safety in complex scenarios while also considering the system's practicality and user experience.

[0109] In one possible implementation, the obstacle warning method provided in this application can also be implemented by adding a sensor to the vehicle chassis, typically fixed to the front side of the chassis or the sides near the tires. This ensures that during vehicle uphill driving, the sensor's detection surface faces the slope and bottom area in the direction of vehicle travel, thereby enabling obstacle detection and warning. However, this method not only increases hardware procurement and assembly labor costs but is also prone to triggering false alarms due to the uneven terrain features of the slope, interfering with the driver's normal operation.

[0110] Figure 6 This is a schematic diagram of the structure of an obstacle warning device provided in this application, as shown below. Figure 6 As shown, the obstacle warning device 60 provided in this embodiment includes:

[0111] The first processing module 601 is used to determine whether the vehicle is in an uphill scenario during the vehicle's movement.

[0112] The second processing module 602 is used to determine the target perception area for early warning detection based on the first perception area of ​​the fisheye camera and the second perception area of ​​the ultrasonic radar if it is determined that the vehicle is in an uphill scene. The target perception area includes the overlapping area of ​​the first perception area and the second perception area, as well as the area in the first perception area located below the overlapping area.

[0113] The third processing module 603 is used for obstacle detection and early warning in the target perception area.

[0114] In one possible implementation, the first processing module 601 is specifically used for:

[0115] Based on the vehicle's location information and / or slope information, determine whether the vehicle's driving scenario is an uphill scenario.

[0116] In one possible implementation, the first processing module 601 is further configured to:

[0117] Obtain the vehicle's location information and determine whether the vehicle is currently in an uphill scenario based on the location information and the map navigation system;

[0118] or,

[0119] Based on the slope detected by the slope sensor at the vehicle's current location, determine whether the vehicle is currently in an uphill scenario;

[0120] or,

[0121] Based on the slope detected by the slope sensor at the vehicle's current location, and combined with the vehicle's location information and map navigation information, it is determined whether the vehicle is currently in an uphill scenario.

[0122] In one possible implementation, the third processing module 603 is specifically used for:

[0123] If it is detected that the driver's gaze is not focused on the front of the vehicle, obstacle detection and warning will be performed in the target perception area.

[0124] In one possible implementation, the third processing module 603 is further used for:

[0125] If it is detected that the driver's gaze is not focused on the front of the vehicle, and the vehicle speed is less than or equal to a preset speed, then obstacle detection and warning will be performed on the target perception area.

[0126] In one possible implementation, the third processing module 603 is further used for:

[0127] Obstacle detection in the target perception area is performed based on image processing algorithms;

[0128] When an obstacle is detected within the target's perception area, a warning message is sent.

[0129] In one possible implementation, the third processing module 603 is further used for:

[0130] Warning messages will be pushed out via sound and light alerts and / or steering wheel vibration.

[0131] The obstacle warning device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described again in this embodiment.

[0132] Figure 7 A schematic diagram of the structure of the electronic device provided in this application, such as... Figure 7 As shown, the electronic device 70 provided in this embodiment includes at least one processor 701 and a memory 702. Optionally, the electronic device 70 further includes a communication component 703. The processor 701, memory 702, and communication component 703 are connected via a bus 704.

[0133] In a specific implementation, at least one processor 701 executes computer execution instructions stored in memory 702, causing at least one processor 701 to perform the above-described method.

[0134] The specific implementation process of processor 701 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0135] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0136] The memory may include random access memory (RAM) in high-speed memory, and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0137] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0138] This application also provides a vehicle, including a vehicle body and a controller, which is used to execute the above-described method. For the specific implementation process, please refer to the above-described method embodiments. The implementation principle and technical effect are similar, and will not be repeated here.

[0139] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0140] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0141] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside within an ASIC. Alternatively, the processor and the readable storage medium can exist as discrete components in a device.

[0142] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0143] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0144] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0145] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0146] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0147] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. An obstacle warning method, characterized in that, include: During the vehicle's movement, determine whether the vehicle is in an uphill scenario; If it is determined that the vehicle is in an uphill scenario, then the target perception area for warning detection is determined based on the first perception area of ​​the fisheye camera and the second perception area of ​​the ultrasonic radar. The target perception area includes the overlapping area of ​​the first perception area and the second perception area, as well as the area of ​​the first perception area located below the overlapping area. Obstacle detection and early warning are performed on the target perception area.

2. The method according to claim 1, characterized in that, Determining whether the vehicle is in an uphill scenario includes: Based on the vehicle's location information and / or slope information, determine whether the vehicle's driving scenario is an uphill scenario.

3. The method according to claim 2, characterized in that, Determining whether the vehicle's driving scenario is an uphill scenario based on the vehicle's location information and / or slope information includes: The location information of the vehicle is obtained, and the location information and the map navigation system are used to determine whether the vehicle is currently in an uphill scenario. or, Based on the slope detected by the slope sensor at the current location of the vehicle, it is determined whether the vehicle is currently in an uphill scenario; or, Based on the slope detected by the slope sensor at the current location of the vehicle, and the vehicle's location information combined with map navigation information, it is determined whether the vehicle is currently in an uphill scenario.

4. The method according to any one of claims 1 to 3, characterized in that, The obstacle detection and warning for the target perception area includes: If it is detected that the driver's line of sight is not focused on the front of the vehicle, then obstacle detection and warning are performed on the target perception area.

5. The method according to any one of claims 1 to 3, characterized in that, The obstacle detection and warning for the target perception area includes: If it is detected that the driver of the vehicle is not looking in front of the vehicle and the vehicle speed is less than or equal to a preset speed, then obstacle detection and warning will be performed on the target perception area.

6. The method according to any one of claims 1 to 3, characterized in that, The obstacle detection and warning for the target perception area includes: Obstacle detection is performed on the target perception area based on image processing algorithms; When an obstacle is detected within the target perception area, a warning message is pushed out.

7. The method according to claim 6, characterized in that, The push notification information includes: The warning message is pushed out via sound and light alerts and / or steering wheel vibration.

8. An obstacle warning device, characterized in that, include: The first processing module is used to determine whether the vehicle is in an uphill scenario during the vehicle's operation. The second processing module is used to determine the target perception area for early warning detection based on the first perception area of ​​the fisheye camera and the second perception area of ​​the ultrasonic radar if it is determined that the vehicle is in an uphill scene. The target perception area includes the overlapping area of ​​the first perception area and the second perception area, as well as the area of ​​the first perception area located below the overlapping area. The third processing module is used to perform obstacle detection and early warning for the target perception area.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1 to 7.

10. A vehicle, characterized in that, It includes a vehicle body and a controller, the controller being used to perform the method as described in any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 7.

Images