Intelligent driving safety auxiliary method and device, vehicle and storage medium

Abstract

The invention relates to the technical field of vehicles, in particular to an intelligent driving safety auxiliary method and device, a vehicle and a storage medium, and the method comprises the steps: obtaining an actual tracking period of a monocular vision sensor for tracking a front target; if the actual tracking period is smaller than the preset period, the detection distance between the vehicle and the front target and the first detection speed of the front target are determined according to images collected by the monocular vision sensor, and the second detection speed of the front target detected by other sensors is obtained; and fusing the first detection speed and the second detection speed to obtain a fusion speed of the front target, and controlling the vehicle to execute a safety auxiliary action according to the detection distance and / or the fusion speed. Therefore, the problems of low driving safety, poor driving experience and the like caused by poor target perception fusion adaptivity, possible false recognition, false braking of the vehicle due to low recognition precision of the driver and other targets in auxiliary driving in related technologies are solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to an intelligent driving safety assistance method, device, vehicle and storage medium. Background Art

[0002] With the development of technologies such as artificial intelligence, electronics, and communications, the level of vehicle automation and intelligence is getting higher and higher, and the application of intelligent assisted driving systems is becoming more and more extensive.

[0003] In the related art, an intelligent assisted driving system can be used, and the camera used in the main sensor of the intelligent assisted driving system includes monocular vision, binocular vision or trinocular vision, etc. For example, in patent CN201901101U (an automatic emergency braking method for electric vehicles), it includes an input device, an output device and a processor, the output device is a brake actuator, the input device includes a binocular camera, a speed sensor and a brake information sensor, the input device, the processor and the output device are electrically connected in sequence, the binocular camera is installed in the front windshield of the car, and the speed sensor is taken from the original car and is generally installed in the gearbox.

[0004] However, the recognition accuracy of the assisted driving systems in related technologies varies greatly and their adaptability is weak. The low recognition and detection accuracy may lead to untimely or misidentification of cyclists, causing the vehicle to brake incorrectly, resulting in low driving safety and a poor driving experience. Summary of the invention

[0005] One of the purposes of this application is to provide an intelligent driving safety assistance method to solve the problem in related technologies that the assisted driving has low recognition accuracy for targets such as cyclists, which leads to poor adaptability of the perception fusion of targets, possible misrecognition, and incorrect braking of the vehicle, resulting in low driving safety and poor driving experience; the second purpose is to provide an intelligent driving safety assistance device; the third purpose is to provide a vehicle; and the fourth purpose is to provide a storage medium.

[0006] In order to achieve the above purpose, the technical solution adopted in this application is as follows:

[0007] An intelligent driving safety assistance method comprises the following steps: obtaining an actual tracking period of a monocular vision sensor for tracking a front target; if the actual tracking period is less than a preset period, determining a detection distance between a vehicle and the front target and a first detection speed of the front target according to an image captured by the monocular vision sensor, and obtaining a second detection speed of the front target detected by other sensors; fusing the first detection speed and the second detection speed to obtain a fusion speed of the front target, and controlling the vehicle to perform a safety assistance action according to the detection distance and / or the fusion speed.

[0008] According to the above-mentioned technical means, the embodiment of the present application can obtain the fusion speed of the target ahead by fusing the first and second detection speeds of the target ahead obtained by different sensors, and use the fusion speed and the detection distance between the vehicle and the target ahead to judge the state of the vehicle and the target ahead, and perform corresponding safety auxiliary actions; thereby, the detection accuracy of the target ahead can be improved, the recognition anomalies that may be caused by the abnormal speed of the target ahead can be ignored, the detection adaptability can be improved, thereby reducing the vehicle braking coordination time, reducing the possibility of misbraking, and then improving driving safety and improving the user driving experience.

[0009] Furthermore, the controlling of the vehicle to perform safety auxiliary actions according to the detection distance and / or the fusion speed includes: if the detection distance is greater than a first preset distance, controlling the vehicle to prohibit acceleration actions; if the detection distance is less than or equal to the first preset distance and greater than a second preset distance, controlling the vehicle's braking system to perform pre-braking actions, wherein the first preset distance is greater than the second preset distance; if the detection distance is less than or equal to the second preset distance, calculating the distance change rate according to the fusion speed and the detection distance, and when the distance change rate is greater than the preset change rate, controlling the vehicle's braking system to perform braking actions.

[0010] According to the above-mentioned technical means, the embodiment of the present application can compare the detection distance between the vehicle and the target ahead and the first and second preset distances, and judge the safety status of the actual distance between the vehicle and the target ahead according to the size relationship of the three. When the distance is far, the throttle is reduced and acceleration is stopped. When the distance is medium, the brakes are applied. When the distance is close, the brakes are applied reasonably in accordance with the distance change rate, thereby reducing the safety risks caused by emergency braking or even untimely braking, improving the safety and rationality of the intelligent assisted driving solution, and improving the user driving experience.

[0011] Further, the fusing of the first detection speed and the second detection speed to obtain the fused speed of the target ahead includes: obtaining respective weights of the first detection speed and the second detection speed; and obtaining the fused speed by weighting according to the first detection speed, the second detection speed and the respective weights.

[0012] According to the above technical means, the embodiment of the present application can use the weights of the first and second detection speeds to obtain the fusion speed of the front target, avoid the possibility of misidentification due to abnormal speed of the front target, and improve the reliability of the front target speed data.

[0013] Further, when the actual tracking period is smaller than the preset period, the weight of the first detection speed is linearly related to the tracking period.

[0014] Furthermore, the intelligent driving safety assistance method of the embodiment of the present application also includes: if the actual tracking period is greater than or equal to the preset period, controlling the vehicle to perform safety assistance actions according to the distance and speed detected by the monocular vision sensor.

[0015] According to the above-mentioned technical means, the embodiment of the present application can, when the actual tracking period is greater than or equal to the preset period, consider that the driving status of the target ahead and the vehicle ahead is normal, and there is no abnormal impact on the speed of the target ahead, and then control the vehicle to perform safety assistance actions according to the sensor detection distance and speed, thereby improving the rationality and adaptability of the intelligent assisted driving solution.

[0016] Further, determining the detection distance between the vehicle and the target ahead and the first detection speed of the target ahead based on the image captured by the monocular vision sensor includes: identifying the size of the target ahead and the position of the bottom of the target ahead in the image; determining the detection distance between the vehicle and the target ahead based on the size of the target ahead and the position of the bottom of the target ahead in the image, and identifying the size change of the target ahead in two adjacent frames of images; and calculating the first detection speed of the target ahead based on the size change and the time difference between the two adjacent frames of images.

[0017] According to the above technical means, the embodiment of the present application can utilize the size change and position change of the front target in the image to calculate the first detection speed of the front target, improve the rationality and accuracy of the calculation scheme, and improve the credibility of the calculation results.

[0018] Furthermore, before identifying the size of the front object and the position of the bottom of the front object in the image, the method further includes: performing one or more of preprocessing, correction and normalization processing on the image.

[0019] According to the above-mentioned technical means, the embodiments of the present application can perform one or more of preprocessing, correction and normalization on the image before using the front target data in the image for calculation, thereby filtering random noise, enhancing image contrast, and improving stereo matching through preprocessing, improving accuracy and calculation speed through correction, reducing image brightness differences and enhancing image texture through normalization, thereby improving image quality, facilitating image recognition and calculation, and making calculation results more reliable.

[0020] An intelligent driving safety assistance device comprises: an acquisition module, used to acquire an actual tracking period of a monocular vision sensor tracking a front target; a processing module, used to determine the detection distance between a vehicle and the front target and a first detection speed of the front target according to an image collected by the monocular vision sensor if the actual tracking period is less than a preset period, and to acquire a second detection speed of the front target detected by other sensors; a fusion module, used to fuse the first detection speed and the second detection speed to obtain a fusion speed of the front target; and a regulation and control module, used to control the vehicle to perform a safety assistance action according to the detection distance and / or the fusion speed.

[0021] Furthermore, the regulation and control module is further used to: if the detection distance is greater than a first preset distance, control the vehicle to prohibit acceleration; if the detection distance is less than or equal to the first preset distance and greater than a second preset distance, control the braking system of the vehicle to perform a pre-braking action, wherein the first preset distance is greater than the second preset distance; if the detection distance is less than or equal to the second preset distance, calculate the distance change rate based on the fusion speed and the detection distance, and when the distance change rate is greater than the preset change rate, control the braking system of the vehicle to perform a braking action.

[0022] Furthermore, the fusion module is further used to: obtain respective weights of the first detection speed and the second detection speed; and obtain the fusion speed by weighting according to the first detection speed, the second detection speed and the respective weights.

[0023] Furthermore, the intelligent driving safety assistance device is further used for: when the actual tracking period is less than a preset period, the weight of the first detection speed is linearly related to the tracking period.

[0024] Furthermore, the intelligent driving safety assistance device is further used to: if the actual tracking period is greater than or equal to the preset period, control the vehicle to perform safety assistance actions according to the distance and speed detected by the monocular vision sensor.

[0025] Furthermore, the processing module is further used to: identify the size of the front target in the image and the position of the bottom of the front target in the image; determine the detection distance between the vehicle and the front target based on the size of the front target and the position of the bottom of the front target in the image, and identify the size change of the front target in two adjacent frames of images; calculate the first detection speed of the front target based on the size change and the time difference between the two adjacent frames of images.

[0026] Furthermore, the processing module is further used to: perform one or more of preprocessing, correction and normalization processing on the image.

[0027] A vehicle comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent driving safety assistance method as described in the above embodiment.

[0028] A computer-readable storage medium stores a computer program, which is executed by a processor to implement the intelligent driving safety assistance method as described in the above embodiment.

[0029] The embodiments of the present application have at least the following advantages:

[0030] (1) The embodiment of the present application can obtain the fusion speed of the front target by fusing the first and second detection speeds of the front target obtained by different sensors, and use the fusion speed and the detection distance between the vehicle and the front target to judge the state of the vehicle and the front target, and perform corresponding safety auxiliary actions; thereby, the detection accuracy of the front target can be improved, the recognition anomaly that may be caused by the abnormal speed of the front target can be ignored, the detection adaptability can be improved, thereby reducing the vehicle braking coordination time, reducing the possibility of misbraking, and thus improving driving safety and improving the user driving experience;

[0031] (2) The embodiment of the present application can compare the detection distance between the vehicle and the target ahead with the first and second preset distances, and judge the safety status of the actual distance between the vehicle and the target ahead according to the size relationship between the three. When the distance is far, the vehicle can stop accelerating, brake when the distance is medium, and brake reasonably according to the distance change rate when the distance is close, thereby reducing the safety risks caused by emergency braking or even untimely braking, improving the safety and rationality of the intelligent assisted driving solution, and improving the user's driving experience;

[0032] (3) The embodiment of the present application can use the weights of the first and second detection speeds to obtain the fusion speed of the front target, thereby avoiding the possibility of misidentification due to abnormal speed of the front target and improving the reliability of the front target speed data;

[0033] (4) In the embodiment of the present application, when the actual tracking period is greater than or equal to the preset period, it is considered that the driving status of the front target and the vehicle is normal, and the speed of the front target has no abnormal impact, and then the vehicle is controlled to perform safety assistance actions according to the sensor detection distance and speed, thereby improving the rationality and adaptability of the intelligent assisted driving solution;

[0034] (5) The embodiment of the present application can use the size change and position change of the front target in the image to calculate the first detection speed of the front target, thereby improving the rationality and accuracy of the calculation scheme and the credibility of the calculation results;

[0035] (6) The embodiments of the present application can perform one or more of preprocessing, correction and normalization on the image before using the front target data in the image for calculation, thereby filtering random noise, enhancing image contrast, and improving stereo matching through preprocessing, improving accuracy and calculation speed through correction, and reducing image brightness differences and enhancing image texture through normalization, thereby improving image quality, facilitating image recognition and calculation, and making calculation results more reliable.

[0036] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A schematic diagram of the process of an intelligent driving safety assistance method according to an embodiment of the present application;

[0038] Figure 2 A schematic diagram of the principle of an intelligent driving safety assistance method based on monocular vision optimization cyclist detection according to an embodiment of the present application;

[0039] Figure 3 A schematic diagram of an implementation process of intelligent driving safety assistance according to an embodiment of the present application;

[0040] Figure 4 This is a schematic diagram of the distance calculation principle of an embodiment of the present application;

[0041] Figure 5 This is a structural diagram of an intelligent driving safety assistance device according to an embodiment of the present application;

[0042] Figure 6 A schematic diagram of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0043] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, not for limiting the scope of protection of the present application.

[0044] It should be noted that the illustrations provided in the following embodiments are only used to illustrate the basic concept of the present application in a schematic manner. Therefore, the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0045] The advent of the car has changed the way people travel, increasing the convenience and mobility of transportation; with the advancement of science and technology, the performance and mileage of vehicles have been greatly improved, and they have evolved into mechanical and electronic equipment that integrates various technologies; in addition to travel functions, cars have also been given many connotations such as leisure, comfort, luxury, sports and fashion; for some people, cars have even become an extension and expression of their image and personality.

[0046] In order to improve the braking, handling and comfort performance of vehicles, some automation and intelligent systems are gradually introduced into vehicle control. The development of artificial intelligence, electronics, communications and other technologies has brought great impact on vehicles. The vehicles in the relevant technologies are equipped with a variety of sensors and electronic control systems, which can automatically realize a series of functions, thereby improving the travel experience, improving travel efficiency and ensuring travel safety; among them, these functions cover vehicle dynamics control (such as anti-lock control and traction control, etc.), travel path planning (such as navigation system and information service, etc.), vehicle driving and control (such as adaptive cruise control system and lane keeping system, etc.) and many other aspects. Smart cars are designed to use artificial intelligence, communication and other technologies to help people travel by improving maneuverability, safety, traffic efficiency and comfort.

[0047] In related technologies, the cameras used in the main sensors of intelligent driving assistance systems include monocular vision, binocular vision, and even trinocular vision; multi-camera cameras have different divisions of labor in the field of view detection process, and can play a more powerful role to make up for the shortcomings of monocular cameras; in terms of cost and detection of main targets, monocular cameras still play an irreplaceable role in intelligent driving.

[0048] However, the recognition accuracy of the assisted driving systems in related technologies varies and their adaptability is weak. The low recognition and detection accuracy may lead to untimely recognition of cyclists, etc., resulting in emergency braking or untimely braking of the vehicle, low driving safety, and poor driving experience.

[0049] Specifically, Figure 1 A flowchart of an intelligent driving safety assistance method provided in an embodiment of the present application.

[0050] like Figure 1 As shown, the intelligent driving safety assistance method includes the following steps:

[0051] In step S101, an actual tracking period of a monocular vision sensor tracking a front target is obtained.

[0052] The front target can be a moving target such as a cyclist in front of the vehicle, and the monocular vision sensor can be Figure 2The monocular camera shown is not specifically limited to this.

[0053] It can be understood that the monocular vision sensor of the embodiment of the present application can track the target in front of the vehicle. After receiving the target in front observed and tracked by the monocular vision sensor, the actual tracking period of the target can be obtained to ensure effective association with the target in front, which facilitates the calculation of the detection speed in subsequent embodiments.

[0054] In step S102, if the actual tracking period is less than the preset period, the detection distance between the vehicle and the front target and the first detection speed of the front target are determined according to the image collected by the monocular vision sensor, and the second detection speed of the front target detected by other sensors is obtained.

[0055] Among them, the preset period can be set according to actual conditions, for example, the preset period can be set to 8 periods, etc., and there is no specific limitation on this.

[0056] It can be understood that since the monocular vision sensor gradually converges with the increase of the tracking period during detection, that is, when the tracking period is short, the detection speed of the monocular vision sensor may be abnormal. Therefore, when the actual tracking period is less than the preset period, the embodiment of the present application not only detects the first detection speed of the front target through the monocular vision sensor, but also can associate the front target with other sensor targets and obtain the second detection speed of the front target detected by other sensors.

[0057] As a possible implementation method, the detection distance between the vehicle and the front target and the first detection speed of the front target are determined based on the image captured by the monocular vision sensor, including: identifying the size of the front target in the image and the position of the bottom of the front target in the image; determining the detection distance between the vehicle and the front target according to the size of the front target and the position of the bottom of the front target in the image, and identifying the size change of the front target in two adjacent frames of images; and calculating the first detection speed of the front target according to the size change and the time difference between two adjacent frames of images.

[0058] Specifically, (1) detection distance determination:

[0059] Before identifying the size of the front object in the image and the position of the bottom of the front object in the image, the method further includes: performing one or more of preprocessing, correction and normalization processing on the image.

[0060] like Figure 3As shown, the embodiment of the present application can first calibrate the monocular vision sensor. In the following embodiments, a monocular camera will be used as an example for explanation; after calibrating the camera, respective intrinsic parameters and extrinsic parameters are obtained; wherein, the intrinsic parameters include the intrinsic parameter matrix and the distortion coefficient, and the extrinsic parameters include the rotation vector and the translation vector. Then, the camera installed on the car is used to capture the image from the installation position, and the obtained image is preprocessed, corrected and normalized by one or more methods; wherein, the purpose of image preprocessing is to filter out random noise, enhance image contrast, and be more conducive to the completion of stereo matching; the purpose of correction is to improve accuracy and calculation speed; image normalization is to reduce the difference in image brightness and enhance image texture at the same time.

[0061] After processing the image, the embodiment of the present application can calculate the detection distance between the vehicle and the front target and the first detection speed of the front target. The monocular camera can first convert the image coordinates from millimeters to pixels, and then invert the image for processing. The farther the vehicle is, the smaller the distance between the bottom of the vehicle and the horizontal line in the image is. Figure 4 As shown; therefore, to determine the distance, it is necessary to first determine the contact point between the vehicle and the ground. The embodiment of the present application can identify the size of the front target in the image and the position of the bottom of the front target in the image.

[0062] It should be noted that in actual shooting scenes, the camera optical axis may not be parallel to the road surface, so that the horizontal line is not in the center of the image, and there are changes in pitch during the driving of the external vehicle; the embodiment of the present application can compensate for the non-planarity of the road by analyzing the lane markings and compensate for the change in pitch angle by self-learning. After compensating for the camera angle and road slope, the embodiment of the present application can determine the image coordinates of the contact point between the vehicle and the road; in the actual shot image, the contact point can be found within a certain pixel in the image; the details are as follows:

[0063] The embodiment of the present application can deduce the relationship between the distance error and the actual distance, such as Figure 4 As shown, according to the similar triangle formula, the relationship between the distance error and the actual distance in the embodiment of the present application is linear.

[0064]

[0065] In the embodiment of the present application, it can be assumed that the image resolution is 640x480, the horizontal FOV is 47°, the focal length is f=740 pixels, the camera installation height is 1.2 m, and the pixel error between the bottom of the vehicle and the road focus is less than 1 pixel. The calculated error at 45 m is 5%, which proves that monocular ACC (Adaptive Cruise Control) ranging is completely feasible, and the ranging analysis is completed.

[0066] (2) Determination of the first detection speed:

[0067] The speed calculation formula of the embodiment of the present application is:

[0068]

[0069] It is understandable that subtracting the noisy Z values ​​at two time points cannot produce an accurate result. In the embodiment of the present application, ΔZ can be calculated from the image size change Δs, and then the speed is calculated when Δt is infinitely small; the size of t determines the accuracy of the final speed. The process of calculating and selecting Δt in the embodiment of the present application can be as follows:

[0070] Assuming that W is the width of the vehicle, w and w' are the image sizes of the vehicle at distances Z and Z' in the image, respectively, the embodiment of the present application can obtain the relationship between the relative speed and the size of the image size change;

[0071] Assuming that the scale error Sacc is the ratio of the linear error Serr to the vehicle pixel width, and assuming that the distance Z is accurate, the embodiment of the present application can obtain the relative speed; wherein the relative speed error is independent of the relative speed, the relative speed error is proportional to the square of the distance, and the relative speed error is proportional to Δt. Increasing the focal length can linearly increase the Δt accuracy.

[0072] The distance error is also taken into consideration, because the distance error is proportional to the relative speed error, so that the total error becomes the speed error; and because a long Δt time will cause errors in speed calculation, the embodiment of the present application can substitute the obtained Δt after derivation and solution, thereby solving to obtain the first detection speed.

[0073] In an embodiment of the present application, if the actual tracking period is greater than or equal to the preset period, the vehicle is controlled to perform safety assistance actions based on the distance and speed detected by the monocular vision sensor.

[0074] It can be understood that since the monocular vision sensor gradually converges as the tracking period increases, that is, when the tracking period is long, the data detected by the monocular vision sensor is accurate. Therefore, when the actual tracking period is greater than or equal to the preset period, the embodiment of the present application can select appropriate safety assistance actions to control the vehicle according to the distance and speed detected by the monocular vision sensor.

[0075] In step S103, the first detection speed and the second detection speed are fused to obtain a fused speed of the target ahead, and the vehicle is controlled to perform safety assistance actions according to the detection distance and / or the fused speed.

[0076] It can be understood that the embodiment of the present application can execute a fusion compensation strategy after obtaining the first detection speed and the second detection speed, fuse the first detection speed and the second detection speed, thereby obtaining the fusion speed of the target ahead, and judge the state of the vehicle and the target ahead according to the detection distance and / or the fusion speed, thereby controlling the vehicle to perform safety assistance actions.

[0077] Specifically, fusing the first detection speed and the second detection speed to obtain the fused speed of the target ahead includes: obtaining respective weights of the first detection speed and the second detection speed; and weighting the first detection speed, the second detection speed and the respective weights to obtain the fused speed.

[0078] It can be understood that the embodiment of the present application can use the weights of the first detection speed and the second detection speed for weighting, thereby obtaining the fusion speed; and when the actual tracking period is less than the preset period, the weight of the first detection speed is linearly related to the tracking period, for example, the larger the detection period, the larger the corresponding weight of the first detection speed, and the smaller the detection period, the smaller the corresponding weight of the first detection speed.

[0079] Specifically: when the target tracking period of the front target is less than the preset period and the front target is associated with other sensor targets, the embodiment of the present application can cancel or reduce the speed measurement weight of the monocular vision, wherein the weight reduction strategy is related to the tracking period, the smaller the tracking period, the smaller the weight, and the larger the tracking period, the weight gradually recovers until the tracking period is greater than the preset period and returns to a normal level; similarly, after the front target is associated, if the speed of the fused target is within the preset period of monocular vision observation, the embodiment of the present application can give priority to the observation information of other sensors to reduce the speed weight of the monocular vision, and the weight reduction strategy is related to the tracking period; in the case of other normal speed measurement outputs, the original association and fusion strategy is adopted.

[0080] In an embodiment of the present application, the vehicle is controlled to perform safety assistance actions according to the detection distance and / or the fusion speed, including: if the detection distance is greater than a first preset distance, the vehicle is controlled to prohibit acceleration actions; if the detection distance is less than or equal to the first preset distance and greater than a second preset distance, the braking system of the vehicle is controlled to perform a pre-braking action, wherein the first preset distance is greater than the second preset distance; if the detection distance is less than or equal to the second preset distance, the distance change rate is calculated according to the fusion speed and the detection distance, and when the distance change rate is greater than the preset change rate, the braking system of the vehicle is controlled to perform a braking action.

[0081] The preset change rate can be set according to actual conditions and is not specifically limited thereto.

[0082] It can be understood that the embodiment of the present application can check the tracking period and detection sensor of the target after receiving the perceived fusion of the forward target; when the target detection sensor is a single visual detection target (which can be forward vision, peripheral vision or surround vision), and the target tracking period is less than the preset period, the speed of the target is likely to be abnormal, so the embodiment of the present application can perform braking control on the target to avoid misbraking; wherein, the embodiment of the present application can set a first preset distance and a second preset distance, etc., to judge the current fusion target and the state of the vehicle.

[0083] Specifically, when the target distance is greater than the first preset distance, it can be considered that the target distance is far, and the embodiment of the present application can cause the vehicle to reduce the throttle and stop accelerating; when the target distance is between the first preset distance and the second preset distance, that is, the target distance is medium, the vehicle can be pre-braked; when the target distance is less than the second preset distance, it can be considered that the target distance is close, and the vehicle is controlled to take reasonable braking measures, such as calculating the distance change rate based on the fusion speed and the detection distance, and when the distance change rate is greater than the preset change rate, it is considered that the target distance changes rapidly, and braking action is taken to avoid collision, etc.; in other cases of normal speed measurement output, the original association and fusion strategy is adopted.

[0084] It should be noted that the intelligent driving safety assistance method of the embodiment of the present application can be implemented based on the following basic functional units, including: an image acquisition unit, composed of a CCD (charge coupled device) camera, which can be used to collect image information around the vehicle in real time. The image acquisition power supply of the embodiment of the present application can be selected according to actual conditions, such as a front-view camera, etc.; a GPS (Global Positioning System) positioning unit, which is used to collect the current position and time information of the vehicle in real time; a data processing unit, including a microprocessor, a memory and a baseband processor, which is used to receive and process the information sent by the image acquisition unit and the GPS positioning unit in real time to determine whether the pedestrians in front and behind the vehicle are within a safe range; a display unit, which is used to display the image captured by the image acquisition unit; a pedal braking unit, which can control the up and down sliding of the car pedal according to the information sent by the data processing unit to achieve vehicle deceleration; and an on-board power supply, which can provide power for each unit.

[0085] In summary, the intelligent driving safety assistance method proposed in the embodiments of the present application has at least the following advantages:

[0086] (1) The embodiment of the present application can obtain the fusion speed of the front target by fusing the first and second detection speeds of the front target obtained by different sensors, and use the fusion speed and the detection distance between the vehicle and the front target to judge the state of the vehicle and the front target, and perform corresponding safety auxiliary actions; thereby, the detection accuracy of the front target can be improved, the recognition anomaly that may be caused by the abnormal speed of the front target can be ignored, the detection adaptability can be improved, thereby reducing the vehicle braking coordination time, reducing the possibility of misbraking, and thus improving driving safety and improving the user driving experience;

[0087] (2) The embodiment of the present application can compare the detection distance between the vehicle and the target ahead with the first and second preset distances, and judge the safety status of the actual distance between the vehicle and the target ahead according to the size relationship between the three. When the distance is far, the vehicle can stop accelerating, brake when the distance is medium, and brake reasonably according to the distance change rate when the distance is close, thereby reducing the safety risks caused by emergency braking or even untimely braking, improving the safety and rationality of the intelligent assisted driving solution, and improving the user's driving experience;

[0088] (3) The embodiment of the present application can use the weights of the first and second detection speeds to obtain the fusion speed of the front target, thereby avoiding the possibility of misidentification due to abnormal speed of the front target and improving the reliability of the front target speed data;

[0089] (4) In the embodiment of the present application, when the actual tracking period is greater than or equal to the preset period, it is considered that the driving status of the front target and the vehicle is normal, and the speed of the front target has no abnormal impact, and then the vehicle is controlled to perform safety assistance actions according to the sensor detection distance and speed, thereby improving the rationality and adaptability of the intelligent assisted driving solution;

[0090] (5) The embodiment of the present application can use the size change and position change of the front target in the image to calculate the first detection speed of the front target, thereby improving the rationality and accuracy of the calculation scheme and the credibility of the calculation results;

[0091] (6) The embodiments of the present application can perform one or more of preprocessing, correction and normalization on the image before using the front target data in the image for calculation, thereby filtering random noise, enhancing image contrast, and improving stereo matching through preprocessing, improving accuracy and calculation speed through correction, and reducing image brightness differences and enhancing image texture through normalization, thereby improving image quality, facilitating image recognition and calculation, and making calculation results more reliable.

[0092] Next, the intelligent driving safety assistance device proposed according to the embodiment of the present application is described with reference to the accompanying drawings.

[0093] Figure 5 It is a block diagram of an intelligent driving safety assistance device according to an embodiment of the present application.

[0094] like Figure 5 As shown, the intelligent driving safety assistance device 10 includes an acquisition module 100 , a processing module 200 , a fusion module 300 and a regulation and control module 400 .

[0095] Among them, the acquisition module 100 is used to obtain the actual tracking period of the monocular vision sensor for tracking the front target; the processing module 200 is used to determine the detection distance between the vehicle and the front target and the first detection speed of the front target based on the image collected by the monocular vision sensor if the actual tracking period is less than the preset period, and obtain the second detection speed of the front target detected by other sensors; the fusion module 300 is used to fuse the first detection speed and the second detection speed to obtain the fusion speed of the front target; the regulation and control module 400 is used to control the vehicle to perform safety auxiliary actions according to the detection distance and / or the fusion speed.

[0096] In the embodiment of the present application, the regulation and control module 400 is further used to control the vehicle to prohibit acceleration if the detection distance is greater than a first preset distance; to control the vehicle's braking system to perform a pre-braking action if the detection distance is less than or equal to the first preset distance and greater than a second preset distance, wherein the first preset distance is greater than the second preset distance; and to calculate the distance change rate based on the fusion speed and the detection distance if the detection distance is less than or equal to the second preset distance, and to control the vehicle's braking system to perform a braking action when the distance change rate is greater than the preset change rate.

[0097] In the embodiment of the present application, the fusion module 300 is further used to obtain the respective weights of the first detection speed and the second detection speed; and to obtain the fusion speed by weighting the first detection speed, the second detection speed and the respective weights.

[0098] In an embodiment of the present application, the intelligent driving safety assistance device 10 is further configured to, when the actual tracking period is less than a preset period, have a linear relationship between the weight of the first detection speed and the tracking period.

[0099] In an embodiment of the present application, the intelligent driving safety assistance device 10 is further used to control the vehicle to perform safety assistance actions according to the distance and speed detected by the monocular vision sensor if the actual tracking period is greater than or equal to the preset period.

[0100] In an embodiment of the present application, the processing module 200 is further used to identify the size of the front target in the image and the position of the bottom of the front target in the image; determine the detection distance between the vehicle and the front target based on the size of the front target and the position of the bottom of the front target in the image, and identify the size change of the front target in two adjacent frames of images; calculate the first detection speed of the front target based on the size change and the time difference between two adjacent frames of images.

[0101] In the embodiment of the present application, the processing module 200 is further used to perform one or more of preprocessing, correction and normalization processing on the image.

[0102] It should be noted that the aforementioned explanation of the embodiment of the intelligent driving safety assistance method is also applicable to the intelligent driving safety assistance device of this embodiment, and will not be repeated here.

[0103] According to the intelligent driving safety assistance device proposed in the embodiment of the present application, the fusion speed of the target ahead can be obtained by fusing the first and second detection speeds of the target ahead obtained by different sensors, and the status of the vehicle and the target ahead can be judged by using the fusion speed and the detection distance between the vehicle and the target ahead, and corresponding safety assistance actions can be performed; thereby, the detection accuracy of the target ahead can be improved, the recognition anomalies that may be caused by the abnormal speed of the target ahead can be ignored, the detection adaptability can be improved, thereby reducing the vehicle braking coordination time, reducing the possibility of misbraking, and thereby improving driving safety and improving the user driving experience.

[0104] Figure 6 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0105] A memory 601 , a processor 602 , and a computer program stored in the memory 601 and executable on the processor 602 .

[0106] When the processor 602 executes the program, the intelligent driving safety assistance method provided in the above embodiment is implemented.

[0107] Furthermore, the vehicle further comprises,

[0108] The communication interface 603 is used for communication between the memory 601 and the processor 602 .

[0109] The memory 601 is used to store computer programs that can be executed on the processor 602 .

[0110] The memory 601 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0111] If the memory 601, the processor 602 and the communication interface 603 are implemented independently, the communication interface 603, the memory 601 and the processor 602 can be connected to each other through a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0112] Optionally, in a specific implementation, if the memory 601, the processor 602 and the communication interface 603 are integrated on a chip, the memory 601, the processor 602 and the communication interface 603 can communicate with each other through an internal interface.

[0113] The processor 602 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0114] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the above-mentioned intelligent driving safety assistance method is implemented.

[0115] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0116] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0117] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0118] It should be understood that the various parts of the present application can be implemented in hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination, a discrete logic circuit with a logic gate circuit for implementing a logic function on a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.

[0119] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0120] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. An intelligent driving safety assistance method, characterized in that: The following steps are involved: Get the actual tracking period of the monocular vision sensor tracking the target in front; If the actual tracking period is less than the preset period, the detection distance between the vehicle and the front target and the first detection speed of the front target are determined according to the image collected by the monocular vision sensor, and the second detection speed of the front target detected by other sensors is obtained; The first detection speed and the second detection speed are fused to obtain a fusion speed of the front target, and the vehicle is controlled to perform a safety assistance action according to the detection distance and / or the fusion speed.

2. The intelligent driving safety assistance method according to claim 1, characterized in that: The controlling the vehicle to perform a safety auxiliary action according to the detection distance and / or the fusion speed includes: If the detection distance is greater than a first preset distance, controlling the vehicle to prohibit acceleration; If the detection distance is less than or equal to the first preset distance and greater than a second preset distance, controlling the braking system of the vehicle to perform a pre-braking action, wherein the first preset distance is greater than the second preset distance; If the detection distance is less than or equal to the second preset distance, the distance change rate is calculated according to the fusion speed and the detection distance, and when the distance change rate is greater than the preset change rate, the braking system of the vehicle is controlled to perform a braking action.

3. The intelligent driving safety assistance method according to claim 1, characterized in that: The fusing the first detection speed and the second detection speed to obtain the fusion speed of the front target includes: Obtaining respective weights of the first detection speed and the second detection speed; The fusion speed is obtained by weighting the first detection speed, the second detection speed and the respective weights.

4. The intelligent driving safety assistance method according to claim 3, characterized in that: When the actual tracking period is smaller than the preset period, the weight of the first detection speed is linearly related to the tracking period.

5. The intelligent driving safety assistance method according to claim 1, characterized in that: Also includes: If the actual tracking period is greater than or equal to the preset period, the vehicle is controlled to perform safety assistance actions according to the distance and speed detected by the monocular vision sensor.

6. The intelligent driving safety assistance method according to claim 1, characterized in that: The step of determining the detection distance between the vehicle and the front target and the first detection speed of the front target according to the image collected by the monocular vision sensor includes: Identify the size of the front object in the image and the position of the bottom of the front object in the image; Determine the detection distance between the vehicle and the front target according to the size of the front target and the position of the bottom of the front target in the image, and identify the size change of the front target in two adjacent frames of images; A first detection speed of the front target is calculated according to the size change and the time difference between the two adjacent frames of images.

7. The intelligent driving safety assistance method according to claim 6, characterized in that: Before identifying the size of the front target in the image and the position of the bottom of the front target in the image, the method further includes: The image is subjected to one or more of preprocessing, correction and normalization.

8. An intelligent driving safety assistance device, characterized in that: include: An acquisition module is used to acquire an actual tracking period of a monocular vision sensor tracking a target in front; A processing module, configured to determine the detection distance between the vehicle and the front target and the first detection speed of the front target according to the image collected by the monocular vision sensor if the actual tracking period is less than the preset period, and obtain the second detection speed of the front target detected by other sensors; a fusion module, configured to fuse the first detection speed and the second detection speed to obtain a fusion speed of the front target; The regulation and control module is used to control the vehicle to perform safety auxiliary actions according to the detection distance and / or the fusion speed.

9. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent driving safety assistance method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the intelligent driving safety assistance method as described in any one of claims 1 to 7.

Images