Vehicle-mounted camera field of view deflection control method, vehicle-mounted camera, intelligent automobile and storage medium

Abstract

This application discloses a method for controlling the field of view deflection of an in-vehicle camera, an in-vehicle camera, an intelligent vehicle, and a storage medium, relating to the field of assisted driving technology. The method includes the following steps: acquiring the current vehicle's geographical location information, vehicle status information, and vehicle perception information; determining the actual driving scenario of the current vehicle based on the geographical location information, vehicle status information, and vehicle perception information; and controlling the field of view deflection structure to adjust the field of view deflection angle of the in-vehicle camera accordingly based on the actual driving scenario. By fusing multiple information such as the vehicle's geographical location, vehicle status, and vehicle perception to identify the current driving scenario, and actively driving the camera's field of view deflection structure to deflect the field of view based on the scenario, the vehicle can obtain a specific perception area for a specific driving scenario, improving the safety of assisted driving.

Description

Technical Field

[0001] This application relates to the field of driver assistance technology, and in particular to a method for controlling the field of view deflection of an in-vehicle camera, an in-vehicle camera, an intelligent vehicle, and a storage medium. Background Technology

[0002] Vehicle-mounted front-view cameras are typically fixed to the windshield or roof of a vehicle, and their field of view is fixed and cannot be dynamically adjusted according to the actual driving environment.

[0003] In real-world scenarios, various special situations exist, such as overtaking and traffic congestion. In these special scenarios, because the fixed field of view cannot be shifted to the side of the road in advance, the vehicle cannot achieve adaptive matching between the field of view and the driving scenario. This limits the perception capability in different scenarios and affects the safety and reliability of the driver assistance system. Summary of the Invention

[0004] The main objective of this application is to provide a method for controlling the field of view deflection of an in-vehicle camera, an in-vehicle camera, an intelligent vehicle, and a storage medium, aiming to solve the technical problem of how to improve the perception capabilities of vehicles in different scenarios.

[0005] To achieve the above objectives, this application provides a method for controlling the field of view deflection of an in-vehicle camera, applied to an in-vehicle camera equipped with a field of view deflection structure. The method includes the following steps:

[0006] Obtain the current vehicle's geographical location information, vehicle status information, and vehicle perception information; Based on geographic location information, vehicle status information, and vehicle perception information, determine the actual driving scenario of the current vehicle; Based on the actual driving scenario, the field of view deflection structure is controlled to adjust the field of view deflection angle of the vehicle camera accordingly.

[0007] In one embodiment, the step of determining the actual driving scenario of the current vehicle based on geographical location information, vehicle status information, and vehicle perception information includes: Determine the vehicle's current driving area based on geographical location information; By using vehicle status information, the steering wheel angle and / or turn signal status are obtained, and the vehicle's intention to change lanes is determined based on the steering wheel angle and / or turn signal status. Based on vehicle perception information, determine whether there are risk targets in the vehicle's real-time perception area; When the driving area is a high-speed area, the vehicle intends to change lanes, and there are risky targets in the vehicle's real-time perception area, the actual driving scenario of the vehicle is determined to be the first driving scenario. When the driving area is a high-speed area, the vehicle does not intend to change lanes, and there are no risk targets in the vehicle's real-time perception area, the actual driving scenario of the vehicle is determined to be the second driving scenario. When the driving area is a low-speed area and there are risky targets in the real-time perception area, the actual driving scenario of the vehicle is determined to be the third driving scenario.

[0008] In one embodiment, the step of adjusting the field-of-view deflection angle of the vehicle-mounted camera according to the field-of-view deflection structure based on the actual driving scenario includes: When the actual driving scenario is determined to be the first driving scenario, the vehicle's current real-time speed and steering wheel angle are obtained through vehicle status information. The target field of view deflection angle is determined based on the steering wheel angle, real-time vehicle speed, and a first preset basic deflection angle. The field-of-view deflection control structure adjusts the field-of-view deflection angle of the vehicle-mounted camera to the target field-of-view angle.

[0009] In one embodiment, after the step of controlling the field-of-view deflection structure to adjust the field-of-view deflection angle of the vehicle-mounted camera to the target field-of-view angle, the method further includes: The first relative distance between the vehicle and the risk target is obtained through vehicle perception information; When the first relative distance is greater than the first preset distance, the field of view deflection structure is controlled to correct the field of view deflection angle of the vehicle camera at a first preset rate.

[0010] In one embodiment, the step of adjusting the field-of-view deflection angle of the vehicle-mounted camera according to the field-of-view deflection structure based on the actual driving scenario includes: When the actual driving scenario is determined to be the second driving scenario, navigation information is obtained; Based on navigation information, obtain the second relative distance between the vehicle and the next traffic sign; Based on the second relative distance and the second preset basic deflection angle, the target field of view deflection angle is determined; The field-of-view deflection control structure adjusts the field-of-view deflection angle of the vehicle-mounted camera to the target field-of-view angle.

[0011] In one embodiment, the step of adjusting the field-of-view deflection angle of the vehicle-mounted camera according to the field-of-view deflection structure based on the actual driving scenario includes: When the actual driving scenario is determined to be a third driving scenario, the third relative distance between each risk target and the vehicle in the real-time perception area is obtained through vehicle perception information. The risk target corresponding to the minimum value among the third relative distances is taken as the staring target; The two-dimensional offset between the gaze target and the vehicle is obtained through vehicle perception information; The target field of view deflection angle is determined based on the two-dimensional offset. The field-of-view deflection control structure adjusts the field-of-view deflection angle of the vehicle-mounted camera to the target field-of-view angle.

[0012] In one embodiment, the step of obtaining the third relative distances between each risk target and the vehicle within the real-time perception area using vehicle perception information includes: Obtain the vehicle's current real-time speed by using vehicle status information; The real-time sensing area is adjusted based on the real-time vehicle speed to determine the warning area; The third relative distance between each risk target and the vehicle within the warning area is obtained by using vehicle perception information.

[0013] Furthermore, this application also proposes a vehicle-mounted camera, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the vehicle-mounted camera field-of-view deflection control method described above.

[0014] Furthermore, this application also proposes an intelligent vehicle that employs an in-vehicle camera as described above.

[0015] Furthermore, this application also proposes a storage medium, which is a computer-readable storage medium, storing a computer program. When the computer program is executed by a processor, it implements the steps of the above-described vehicle camera field-of-view deflection control method.

[0016] This application provides a method for controlling the field of view deflection of an in-vehicle camera, an in-vehicle camera, a smart car, and a storage medium. The method includes the following steps: acquiring the current vehicle's geographical location information, vehicle status information, and vehicle perception information; determining the actual driving scenario of the current vehicle based on the geographical location information, vehicle status information, and vehicle perception information; and controlling the field of view deflection structure to adjust the field of view deflection angle of the in-vehicle camera accordingly based on the actual driving scenario. By fusing multiple information such as the vehicle's geographical location, vehicle status, and vehicle perception to identify the current driving scenario, and actively driving the camera's field of view deflection structure to deflect the field of view based on the scenario, the vehicle can obtain a specific perception area for a specific driving scenario, thereby improving the safety of assisted driving. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an embodiment of the vehicle-mounted camera field-of-view deflection control method of this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the vehicle-mounted camera field-of-view deflection control method of this application; Figure 3 This is a schematic diagram of the first process for the third embodiment of the vehicle-mounted camera field-of-view deflection control method of this application; Figure 4 This is a second flowchart illustrating the third embodiment of the vehicle-mounted camera field-of-view deflection control method of this application; Figure 5 This is a third flowchart illustrating the third embodiment of the vehicle-mounted camera field-of-view deflection control method of this application.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] This application presents a first embodiment of a vehicle-mounted camera field-of-view deflection control method, applied to a vehicle-mounted camera. The vehicle-mounted camera is equipped with a field-of-view deflection structure. Please refer to... Figure 1 The steps of the method include: Step S10: Obtain the current vehicle's geographical location information, vehicle status information, and vehicle perception information; Step S20: Determine the actual driving scenario of the current vehicle based on geographical location information, vehicle status information, and vehicle perception information; It should be understood that in this embodiment, the executing entity is an in-vehicle camera, specifically an in-vehicle front camera with a field-of-view deflection structure configured in its optical path. The field-of-view deflection structure is a controllable optical structure that can change the angle of light transmission. The in-vehicle camera is also equipped with optical elements, a photosensitive device, and a controller. The controller can communicate with the vehicle to obtain geographical location information, vehicle status information, and vehicle perception information transmitted by the vehicle. Furthermore, the controller can also directly acquire images perceived by the in-vehicle camera through the photosensitive device, thereby obtaining some vehicle perception information. Finally, the controller adjusts the field-of-view deflection structure based on the above information, thereby adjusting the field-of-view deflection angle of the in-vehicle camera to change the perception range of the vehicle camera.

[0024] It should be noted that, in this embodiment, the geographical location information can be information related to the vehicle's current location obtained through satellite navigation systems or high-precision maps, including but not limited to the type of road (such as highways, urban roads, and ramps), mainly used to determine the driving area where the vehicle is currently located; the vehicle status information can be the real-time operating status of the vehicle obtained through the vehicle's CAN communication bus, including vehicle speed, steering wheel angle, turn signal status, acceleration, etc., mainly used to determine the driver's current driving intention and vehicle behavior; the vehicle perception information can be environmental perception data obtained through onboard sensors (such as cameras, millimeter-wave radar, lidar, etc.), including target type, target distance, relative speed, target confidence, predicted collision time, etc., mainly used to identify risky targets and dynamic environments.

[0025] It is worth noting that the image information acquired by the vehicle-mounted camera in this embodiment should also be understood as one of the aforementioned vehicle perception information.

[0026] It should be understood that, in this embodiment, the actual driving scenario refers to the current driving environment type identified by the fusion of the above-mentioned multi-source information (geographical location information, vehicle status information, and vehicle perception information), such as overtaking scenario, traffic sign recognition scenario, risk target staring scenario, etc.

[0027] It is easy to understand that in this embodiment, the acquired geographic location information reflects the vehicle's driving area, the acquired vehicle status information reflects the driver's real-time control intentions, and the acquired vehicle perception information reflects the distribution and risk level of surrounding dynamic targets. The fusion of these three provides multi-dimensional input for subsequent scene recognition, enabling the system to comprehensively perceive the current driving situation and thus accurately determine the actual driving scenario in which the vehicle is currently located.

[0028] Step S30: Adjust the field of view deflection angle of the vehicle camera according to the actual driving scenario by controlling the field of view deflection structure.

[0029] It should be understood that vehicles have different perception requirements in different scenarios. For example, overtaking scenarios require enhanced lateral perception, while high-speed scenarios require enhanced long-distance directional perception.

[0030] As is readily understood, in this embodiment, after identifying the actual driving scenario in which the vehicle is currently located, a field-of-view deflection control strategy pre-configured for the corresponding actual driving scenario can be invoked to drive the field-of-view deflection structure to adjust the field-of-view deflection direction of the vehicle camera, thereby changing the perception range of the vehicle camera. Through scenario-driven field-of-view adjustment, the perception capability of the vehicle camera is matched with the current driving task, improving perception capability and safety.

[0031] This application provides a method for controlling the field of view deflection of an in-vehicle camera. The method includes the following steps: acquiring the current vehicle's geographical location information, vehicle status information, and vehicle perception information; determining the actual driving scenario of the current vehicle based on the geographical location information, vehicle status information, and vehicle perception information; and controlling the field of view deflection structure to adjust the field of view deflection angle of the in-vehicle camera accordingly based on the actual driving scenario. By fusing multiple information such as the vehicle's geographical location, vehicle status, and vehicle perception to identify the current driving scenario, and actively driving the camera's field of view deflection structure to deflect the field of view based on the scenario, the vehicle can obtain a specific perception area for a specific driving scenario, thereby improving the safety of assisted driving.

[0032] Based on the first embodiment of the vehicle-mounted camera field-of-view deflection control method of this application, in the second embodiment of the vehicle-mounted camera field-of-view deflection control method of this application, the content that is the same as or similar to that in the first embodiment can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 In this embodiment, the steps for determining the actual driving scenario of the current vehicle based on geographical location information, vehicle status information, and vehicle perception information include: Step S21: Determine the vehicle's current driving area based on the geographical location information; It should be noted that the driving area refers to the type of vehicle driving environment classified according to geographical location. The corresponding driving areas mainly include high-speed areas (such as highways and urban expressways) and low-speed areas (such as urban roads, rural roads, and school zones). Different areas correspond to different speed ranges, traffic rules, and risk sources. In this embodiment, the current geographical location of the vehicle can be obtained through geographical location information, thereby determining whether the vehicle's driving area is in a high-speed or low-speed area.

[0033] Step S22: Obtain the steering wheel angle and / or turn signal status through vehicle status information, and determine whether the vehicle intends to change lanes based on the steering wheel angle and / or turn signal status. It should be noted that the steering wheel angle refers to the angle of steering wheel rotation, measured in degrees. Generally, the angle value corresponding to turning the steering wheel to the left is negative, and the angle value corresponding to turning the steering wheel to the right is positive, reflecting the actual steering action of the vehicle. The turn signal status refers to the on / off state of the left or right turn signal, reflecting the driver's theoretical steering intention. In this embodiment, since the vehicle usually turns on the turn signal in advance when preparing to change lanes or overtake, accompanied by a certain steering wheel angle input, the presence of a lane change intention can be accurately identified by comparing the currently acquired data with a reasonable threshold (such as steering wheel angle ≥15°, steering wheel angle ≤-15°, or left / right turn signal on).

[0034] Step S23: Based on the vehicle perception information, determine whether there are risk targets in the vehicle's real-time perception area; It should be noted that, in this embodiment, the real-time perception area refers to the area around the vehicle that the on-board sensor can currently cover, which usually includes areas such as the front and side front, and its range is limited by the detection angle and detection distance of the on-board sensor; risk targets refer to targets that pose a potential threat to the driving safety of the vehicle, including but not limited to pedestrians, motor vehicles, non-motor vehicles, stationary obstacles, etc.

[0035] It is easy to understand that in this embodiment, the vehicle perception information that can be acquired can be used to identify and assess the risk of objects perceived in the real-time perception area. The confidence level, distance, relative speed and predicted collision time (distance / relative speed) of each target are calculated. When a target meets the preset risk judgment conditions (e.g., target confidence level ≥ 95%, target distance is 10-200m, predicted collision time ≤ 3s, etc.), the object is marked as a risk target. Step S24: When the driving area is a high-speed area, the vehicle intends to change lanes, and there is a risky target in the vehicle's real-time perception area, the actual driving scenario of the vehicle is determined to be the first driving scenario. Step S25: When the driving area is a high-speed area, the vehicle does not intend to change lanes, and there are no risk targets in the vehicle's real-time perception area, the actual driving scenario of the vehicle is determined to be the second driving scenario. Step S26: When the driving area is a low-speed area and there are risky targets in the real-time perception area, the actual driving scenario of the vehicle is determined to be the third driving scenario.

[0036] It should be noted that in this embodiment, the first driving scenario corresponds to the overtaking or lane-changing scenario, that is, the vehicle is preparing to overtake or change lanes while driving at high speed, and there are risk targets (such as vehicles or obstacles in adjacent lanes) that need to be monitored; the second driving scenario corresponds to the traffic sign recognition scenario, that is, the vehicle is driving at high speed, has no intention to change lanes and has no risk targets, at which time the system can prioritize the traffic sign recognition task; the third driving scenario corresponds to the risk target staring scenario, that is, the vehicle is driving at low speed and there are high-risk targets in the surrounding area that need to be continuously tracked and monitored.

[0037] It is easy to understand that in this embodiment, if the following three conditions are met simultaneously: the current driving area is a high-speed area, the vehicle intends to change lanes, and there are risk targets in the area surrounding the vehicle (the real-time perception area, which is mainly the area on the side where the lane change is intended), it can be determined that the vehicle is currently in the first driving scenario, namely a high-speed overtaking or lane-changing scenario. At this time, it is necessary to enhance the perception capability of long-distance risk targets in adjacent lanes.

[0038] If all three conditions are met simultaneously—the current driving area is a highway, the vehicle does not intend to change lanes, and there are no risky targets in the area surrounding the vehicle (real-time perception area)—it can be determined that the vehicle is currently in the second driving scenario, namely the traffic sign recognition scenario. In this case, there are no particularly important perception requirements, and perception resources can be fully utilized to shift the field of view to the side of the road in advance to capture traffic signs ahead, thus improving the recognition success rate.

[0039] If both conditions are met—that the current driving area is a low-speed area and that there are risk targets in the area surrounding the vehicle (real-time perception area)—it can be determined that the vehicle is currently in a third driving scenario, namely a risk target staring scenario under low-speed complex road conditions. In this case, risk targets such as pedestrians and non-motorized vehicles are densely packed, and their behavior is uncertain. It is necessary to lock the field of view and track the nearest risk target to improve the accuracy of target recognition and the reliability and timeliness of risk assessment.

[0040] Based on the first and / or second embodiments of the vehicle-mounted camera field-of-view deflection control method of this application, in the third embodiment of the vehicle-mounted camera field-of-view deflection control method of this application, the content that is the same as or similar to the first and / or second embodiments described above can be referred to the above description and will not be repeated hereafter. Based on this, please refer to... Figure 3 , Figure 4 as well as Figure 5 In this embodiment, the step of adjusting the field-of-view deflection angle of the vehicle camera based on the actual driving scenario includes: Step S311: When the actual driving scenario is determined to be the first driving scenario, the vehicle's current real-time speed and steering wheel angle are obtained through vehicle status information. It should be noted that, please refer to Figure 3 In this embodiment, after determining that the vehicle is currently in the first driving scenario (high-speed overtaking or lane-changing scenario), the vehicle's current real-time speed and steering wheel angle can be extracted from the vehicle status information. The real-time vehicle speed is related to the required field of view during overtaking or lane-changing; the higher the speed, the wider the distant area that needs to be observed during overtaking or lane-changing. The steering wheel angle is used to characterize the overtaking or lane-changing direction to ensure the direction of the field of view deflection.

[0041] Step S312: Determine the target field of view deflection angle based on the steering wheel angle, real-time vehicle speed, and the first preset basic deflection angle; Step S313: Control the field of view deflection structure to adjust the field of view deflection angle of the vehicle camera to the target field of view angle.

[0042] It should be noted that, in this embodiment, the first preset basic deflection angle refers to the basic deflection amount in overtaking or lane changing scenarios, which is mainly used to provide minimum lateral field of view coverage and provide the most basic guarantee for overtaking or lane changing processes.

[0043] It is easy to understand that the target field-of-view deflection angle refers to the theoretically optimal deflection angle that enables the vehicle-mounted camera to perceive risky targets to the maximum extent. In this embodiment, under the first driving scenario, the formula for calculating the target field-of-view deflection angle of the vehicle-mounted camera can be as follows: ; in, The target field of view deflection angle, The first preset basic deflection angle (can be a fixed angle of 5-10°). For real-time vehicle speed, The final symbol is consistent with the symbol for the steering wheel angle.

[0044] After calculating the target field of view angle, the field of view deflection structure can be controlled to adjust the field of view deflection angle of the vehicle camera, so that the vehicle camera can acquire images of the lane on the side where it wants to overtake or change lanes, and capture real-time images of risk targets in the corresponding lane.

[0045] Furthermore, in this embodiment, after the step of controlling the field-of-view deflection structure to adjust the field-of-view deflection angle of the vehicle-mounted camera to the target field-of-view angle, the method further includes: Step S314: Obtain the first relative distance between the vehicle and the risk target through vehicle perception information; Step S315: When the first relative distance is greater than the first preset distance, control the field of view deflection structure to correct the field of view deflection angle of the vehicle camera at the first preset rate.

[0046] It should be noted that, in this embodiment, the first relative distance refers to the longitudinal distance between the current vehicle and the target vehicle or risk target being overtaken, which can be obtained by vehicle-mounted sensors such as millimeter-wave radar or visual ranging; the first preset distance is used to characterize the safe distance between the vehicle and the risk target, and for the overtaking process, the first preset distance can be set to 20m; the first preset rate refers to a preset rate of change of angle of the field of view deflection structure of the vehicle-mounted camera, which can be set to 0.2° / ms.

[0047] For easy understanding, please refer to Figure 3 In this embodiment, during the latter half of the overtaking or lane-changing process (when the vehicle passes the risk target), the distance between the risk target and the front of the vehicle in the current lane changes from near to far. At this time, the progress of the overtaking or lane-changing can be judged based on the change in distance between the risk target and the current vehicle. If the first relative distance between the current vehicle and the risk target has exceeded the first preset distance, it can be determined that the current overtaking or lane-changing process has safely ended. At the same time, the field-of-view deflection structure can be controlled to perform an angle correction operation at a first preset rate, so that the field-of-view deflection angle of the vehicle camera smoothly returns to 0°.

[0048] Furthermore, in this embodiment, the step of adjusting the field-of-view deflection angle of the vehicle camera based on the actual driving scenario includes: Step S321: When the actual driving scenario is determined to be the second driving scenario, obtain navigation information; Step S322: Based on navigation information, obtain the second relative distance between the vehicle and the next traffic sign; It should be noted that, in this embodiment, navigation information refers to route planning information obtained from the vehicle navigation system or mobile phone mapping navigation, including the location, type (speed limit, ramp, toll station, etc.), and distance of traffic signs ahead.

[0049] It is worth noting that, please refer to Figure 4 In this embodiment, the vehicle navigation system typically presets the locations of traffic signs along the road. The navigation information can predict in advance the location of the traffic signs that need to be identified ahead and the distance between the traffic signs and the vehicle, i.e., the second relative distance mentioned above.

[0050] Step S323: Determine the target field of view deflection angle based on the second relative distance and the second preset basic deflection angle; Step S324: Control the field of view deflection structure to adjust the field of view deflection angle of the vehicle camera to the target field of view angle.

[0051] It should be noted that, please refer to Figure 4The second relative distance between the vehicle and the next traffic sign is related to the required field-of-view deflection angle of the vehicle camera. The closer the second relative distance, the larger the deflection angle is required to ensure that the traffic sign occupies enough pixels in the image and improves the recognition rate.

[0052] It is easy to understand that the second preset base deflection angle refers to the base deflection amount used to identify traffic signs. In this embodiment, in the second driving scenario, the calculation formula for the target field-of-view deflection angle is as follows: ; in, The target field of view deflection angle, The second preset base deflection angle (can be a fixed angle of 5-10°) is set. The effective sensing range of the vehicle camera (a fixed value, which can be set to 500). The second relative distance, The final symbol is usually positive (traffic signs are generally placed on the right side of highway lanes).

[0053] It is easy to understand that in this embodiment, the target deflection angle required by the vehicle-mounted camera in the second driving scenario (traffic sign recognition scenario) can be dynamically calculated based on the second relative distance. The field-of-view deflection structure of the vehicle-mounted camera is then controlled based on the target field-of-view angle. By controlling the field-of-view deflection of the vehicle-mounted camera in advance, the image of the traffic sign can be moved to the center area of ​​the image captured by the vehicle-mounted camera at a suitable distance, improving image quality and recognition confidence. Specifically, when the second relative distance is relatively far (e.g., 500m), the field-of-view deflection angle of the vehicle-mounted camera is small, avoiding premature deflection that could affect normal driving perception. As the second relative distance gradually decreases, the field-of-view deflection angle of the vehicle-mounted camera increases linearly, ensuring that the traffic sign is placed in the center area of ​​the vehicle-mounted camera's field of view within the optimal recognition distance.

[0054] Furthermore, in this embodiment, the step of adjusting the field-of-view deflection angle of the vehicle camera based on the actual driving scenario includes: Step S331: When the actual driving scenario is determined to be the third driving scenario, the third relative distance between each risk target and the vehicle in the real-time perception area is obtained through vehicle perception information. Step S332: Take the risk target corresponding to the minimum value among the third relative distances as the staring target; It should be noted that in this embodiment, the third relative distance refers to the longitudinal distance between each risk target and the vehicle; the staring target refers to the risk target selected as the continuous tracking object, and the closest target usually has the highest risk.

[0055] For easy understanding, please refer to Figure 5 In this embodiment, when it is determined that the vehicle is currently in a third driving scenario (low-speed driving scenario), there may be multiple risk targets (such as multiple pedestrians and non-motorized vehicles) on the road around the vehicle. At this time, multiple on-board sensors are needed to collect relevant data on the surrounding environment of the vehicle in order to assess the risk level of each target around the vehicle. Among them, the effective data collection range of the on-board sensors is the real-time perception area.

[0056] It should be noted that in this embodiment, each third relative distance corresponds to a risk target. After obtaining the third relative distances between each risk target and the vehicle in the real-time perception area, the third relative distances can be compared, the smallest third relative distance can be selected, and the risk target corresponding to the smallest third relative distance can be used as the staring target to be tracked.

[0057] Step S333: Obtain the two-dimensional offset between the gaze target and the vehicle through vehicle perception information; Step S334: Determine the target field of view deflection angle based on the two-dimensional offset; It should be noted that in this embodiment, the two-dimensional offset refers to the positional offset of the gaze target relative to the vehicle coordinate system, that is, the aforementioned two-dimensional offset, which mainly includes the lateral offset (the lateral distance between the target center and the vehicle centerline) and the longitudinal distance.

[0058] Specifically, data can be collected via vision or radar. The collected data is then transformed to obtain the lateral and longitudinal offsets of the gaze target relative to the vehicle. These offsets are then calculated using trigonometric functions to determine the required target field-of-view deflection angle. In the third driving scenario, the formula for calculating the target field-of-view deflection angle is: ; in, The target field of view deflection angle, This is the lateral offset. This represents the vertical offset.

[0059] Step S335: Control the field of view deflection structure to adjust the field of view deflection angle of the vehicle camera to the target field of view angle.

[0060] It is easy to understand that, in this embodiment, the field-of-view deflection structure of the vehicle camera can be adjusted in real time according to the acquired target field-of-view angle, so that the vehicle camera is always aimed at the staring target, thereby achieving real-time tracking of high-risk targets.

[0061] Based on the above-mentioned active gaze mechanism, high-quality images of the gaze target can be continuously acquired, improving the accuracy of behavior prediction and risk assessment of the gaze target.

[0062] Furthermore, in this embodiment, the step of obtaining the third relative distances between each risk target and the vehicle within the real-time perception area using vehicle perception information includes: Step S3311: Obtain the vehicle's current real-time speed through vehicle status information; Step S3312: Adjust the real-time sensing area according to the real-time vehicle speed to determine the warning area; Step S3313: Obtain the third relative distance between each risk target and the vehicle within the warning area using vehicle perception information.

[0063] It should be understood that vehicle speed determines braking distance and reaction time; the higher the speed, the wider the area that needs to be monitored.

[0064] It should be noted that, in this embodiment, the warning area refers to the key focus area after the real-time perception area is dynamically adjusted according to the vehicle's real-time speed. The higher the current real-time speed, the larger the corresponding warning area should be, to ensure that any potentially high-risk targets are promptly included in the gaze range.

[0065] For easy understanding, please refer to Figure 5 In this embodiment, the real-time perception area can be adjusted based on the current real-time vehicle speed, and then evaluated based on the third relative distances of each risk target in the adjusted warning area relative to the vehicle. This reduces invalid calculations for distant, irrelevant targets in low-speed areas with complex road conditions, improving the efficiency and effectiveness of risk target screening.

[0066] Furthermore, this application embodiment also provides a vehicle-mounted camera, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the vehicle-mounted camera field-of-view deflection control method described above.

[0067] The vehicle-mounted camera provided in this application, employing the vehicle-mounted camera field-of-view deflection control method described in the above embodiments, can solve the technical problem of how to improve the perception capability of vehicles in different scenarios. Compared with the prior art, the beneficial effects of the vehicle-mounted camera provided in this application are the same as those of the vehicle-mounted camera field-of-view deflection control method described in the above embodiments, and other technical features of this vehicle-mounted camera are the same as those of the vehicle-mounted camera field-of-view deflection control method described in the above embodiments, and will not be elaborated here.

[0068] Furthermore, this application also proposes an intelligent vehicle that employs an in-vehicle camera as described above.

[0069] The intelligent vehicle provided in this application, employing the vehicle-mounted camera in the above embodiments, can solve the technical problem of how to improve the vehicle's perception capabilities in different scenarios. Compared with the prior art, the beneficial effects of the intelligent vehicle provided in this application are the same as those of the vehicle-mounted camera provided in the above embodiments, and other technical features of the intelligent vehicle are the same as those of the vehicle-mounted camera provided in the above embodiments, and will not be elaborated here.

[0070] Furthermore, this application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the vehicle-mounted camera field-of-view deflection control method in the above embodiments.

[0071] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described vehicle-mounted camera field-of-view deflection control method, which can solve the technical problem of how to improve the perception capability of vehicles in different scenarios. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the vehicle-mounted camera field-of-view deflection control method provided in the above embodiments, and will not be repeated here.

[0072] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent scope of this application.

Claims

1. A method for controlling the field of view deflection of a vehicle-mounted camera, characterized in that, Applied to a vehicle-mounted camera, the vehicle-mounted camera being configured with a field-of-view deflection structure, the method includes the following steps: Obtain the current vehicle's geographical location information, vehicle status information, and vehicle perception information; The actual driving scenario of the current vehicle is determined based on the geographical location information, the vehicle status information, and the vehicle perception information. Based on the actual driving scenario, the field of view deflection structure is controlled to adjust the field of view deflection angle of the vehicle camera accordingly.

2. The method for controlling the field of view deflection of a vehicle-mounted camera as described in claim 1, characterized in that, The step of determining the actual driving scenario of the current vehicle based on the geographical location information, the vehicle status information, and the vehicle perception information includes: Based on the geographical location information, determine the vehicle's current driving area; The vehicle status information is used to obtain the steering wheel angle and / or turn signal status, and the vehicle's intention to change lanes is determined based on the steering wheel angle and / or turn signal status. Based on the vehicle perception information, determine whether there are risk targets in the vehicle's real-time perception area; When the driving area is a high-speed area, the vehicle intends to change lanes, and there is a risky target in the vehicle's real-time perception area, the actual driving scenario of the vehicle is determined to be the first driving scenario. When the driving area is a high-speed area, the vehicle does not intend to change lanes, and there are no risk targets in the vehicle's real-time perception area, the actual driving scenario of the vehicle is determined to be the second driving scenario. When the driving area is a low-speed area and there are risky targets in the real-time perception area, the actual driving scenario of the vehicle is determined to be the third driving scenario.

3. The method for controlling the field of view deflection of a vehicle-mounted camera as described in claim 2, characterized in that, The step of controlling the field-of-view deflection structure to adjust the field-of-view deflection angle of the vehicle camera based on the actual driving scenario includes: When the actual driving scenario is determined to be the first driving scenario, the vehicle's current real-time speed and steering wheel angle are obtained through the vehicle status information. Based on the steering wheel angle, the real-time vehicle speed, and the first preset basic deflection angle, the target field of view deflection angle is determined. The field-of-view deflection structure is controlled to adjust the field-of-view deflection angle of the vehicle-mounted camera to the target field-of-view angle.

4. The vehicle-mounted camera field-of-view deflection control method as described in claim 3, characterized in that, After the step of controlling the field-of-view deflection structure to adjust the field-of-view deflection angle of the vehicle-mounted camera to the target field-of-view angle, the method further includes: The first relative distance between the vehicle and the risk target is obtained through the vehicle perception information; When the first relative distance is greater than the first preset distance, the field of view deflection structure is controlled to correct the field of view deflection angle of the vehicle camera at a first preset rate.

5. The method for controlling the field of view deflection of a vehicle-mounted camera as described in claim 2, characterized in that, The step of controlling the field-of-view deflection structure to adjust the field-of-view deflection angle of the vehicle camera based on the actual driving scenario includes: When the actual driving scenario is determined to be the second driving scenario, navigation information is obtained; Based on navigation information, obtain the second relative distance between the vehicle and the next traffic sign; Based on the second relative distance and the second preset basic deflection angle, the target field of view deflection angle is determined; The field-of-view deflection structure is controlled to adjust the field-of-view deflection angle of the vehicle-mounted camera to the target field-of-view angle.

6. The method for controlling the field of view deflection of a vehicle-mounted camera as described in claim 2, characterized in that, The step of controlling the field-of-view deflection structure to adjust the field-of-view deflection angle of the vehicle camera based on the actual driving scenario includes: When the actual driving scenario is determined to be the third driving scenario, the third relative distance between each risk target and the vehicle in the real-time perception area is obtained through the vehicle perception information. The risk target corresponding to the minimum value among the aforementioned third relative distances is taken as the staring target; The two-dimensional offset between the gaze target and the vehicle is obtained through the vehicle perception information. Based on the two-dimensional offset, the target field of view deflection angle is determined; The field-of-view deflection structure is controlled to adjust the field-of-view deflection angle of the vehicle-mounted camera to the target field-of-view angle.

7. The vehicle-mounted camera field-of-view deflection control method as described in claim 6, characterized in that, The step of obtaining the third relative distances between each risk target and the vehicle within the real-time perception area using the vehicle perception information includes: The vehicle's current real-time speed is obtained through the vehicle status information; The real-time sensing area is adjusted based on the real-time vehicle speed to determine the warning area; The vehicle perception information is used to obtain the third relative distance between each risk target and the vehicle within the warning area.

8. A vehicle-mounted camera, characterized in that, The vehicle-mounted camera includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle-mounted camera field-of-view deflection control method as described in any one of claims 1 to 7.

9. A smart car, characterized in that, The intelligent vehicle uses the vehicle-mounted camera as described in claim 8.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the vehicle-mounted camera field-of-view deflection control method as described in any one of claims 1 to 7.

Images