Automobile environment perception and obstacle avoidance system based on visual image technology

Abstract

The application provides a vehicle environment perception obstacle avoidance system based on visual image technology, comprising: starting laser radar scanning when the vehicle is driving, combining SLAM technology to construct a driving map of the vehicle, determining a plurality of environmental objects within a specified range of the vehicle, acquiring driving data of the vehicle and marking the driving data on the driving map to perform synchronous positioning on the vehicle, determining a collision probability between the vehicle and each environmental object, screening a plurality of driving obstacles in the driving map, establishing an obstacle avoidance plan according to an obstacle attribute corresponding to each driving obstacle and performing auxiliary obstacle avoidance, recording a driver's obstacle avoidance process, determining a driving preference of the driver through training, determining a preference degree of the driver to different obstacle avoidance modes, generating an obstacle avoidance optimization suggestion and displaying the obstacle avoidance optimization suggestion, and being capable of identifying and tracking other vehicles, pedestrians and obstacles in real time, so as to help the driver to avoid potential collisions.

Description

Technical Field

[0001] This invention relates to the field of automotive obstacle avoidance technology, and in particular to an automotive environmental perception and obstacle avoidance system based on visual imaging technology. Background Technology

[0002] As one of the most common means of transportation in our daily lives, cars play an increasingly important role. With advancements in artificial intelligence, sensors, control, drive systems, and materials, automobile manufacturing technology has matured, transforming cars from luxury items into everyday consumer goods. Due to the increased number of cars on the road, many drivers, lacking experience, inevitably experience minor collisions. Data shows that when encountering obstacles at high speeds, drivers have very little reaction time, easily leading to collisions and traffic accidents. Intelligent vehicles equipped with obstacle avoidance systems possess the decision-making and execution capabilities to avoid hazards, reacting promptly to prevent collisions. Therefore, designing an environmental perception obstacle avoidance system is essential to address these safety issues.

[0003] Current vehicle obstacle avoidance systems are designed only for the kinematic model of a car traveling at low speeds. When a car is traveling at high speeds, the internal cyclic dynamics of the car need to be considered. In order to accurately calculate the car's driving state, the vehicle obstacle avoidance system needs to be calculated using a complex physical dynamic model, which increases the reaction time of the vehicle obstacle avoidance, increases the risk of car collisions, has poor safety performance, and leads to limited use.

[0004] Therefore, the present invention provides an automotive environmental perception and obstacle avoidance system based on visual imaging technology. Summary of the Invention

[0005] This invention discloses an automotive environmental perception and obstacle avoidance system based on visual imaging technology, which can identify and track other vehicles, pedestrians, and obstacles in real time, thereby helping drivers avoid potential collisions.

[0006] This invention provides a vehicle environmental perception and obstacle avoidance system based on visual imaging technology, comprising:

[0007] An environmental perception module is used to activate lidar scanning when the vehicle is in motion, and combine it with SLAM technology to construct a driving map of the vehicle and identify several environmental objects within a specified range of the vehicle.

[0008] The perception and analysis module is used to acquire the vehicle's driving data and mark it on the driving map to synchronously locate the vehicle and determine the first collision probability between the vehicle and each of the environmental objects.

[0009] The obstacle avoidance module is used to filter several driving obstacles in the driving map based on the first collision probability, and to establish an obstacle avoidance plan and perform assisted obstacle avoidance according to the obstacle attributes corresponding to each driving obstacle.

[0010] The obstacle avoidance training module is used to record the driver's obstacle avoidance process, train the obstacle avoidance process to determine the driver's driving preferences, determine the driver's preference for different obstacle avoidance methods, generate and display the optimal obstacle avoidance suggestions.

[0011] In one feasible approach

[0012] Also includes:

[0013] The in-vehicle obstacle avoidance module is used to obtain real-time information about the vehicle within a specified range when the vehicle is stopped.

[0014] Using the real-time information, identify several dynamic items within the specified range of the vehicle, and establish the activity characteristics of the items within the vehicle's stationary range;

[0015] Based on the activity characteristics of the items, the second collision probability between each dynamic item and each door of the car is determined;

[0016] When the second collision probability is greater than the safe probability, the corresponding dangerous door is located and locked.

[0017] In one feasible approach

[0018] Also includes:

[0019] A non-straight-line obstacle avoidance module is used to determine the vehicle's forward direction based on the vehicle's turn signal status;

[0020] Obtain road condition information related to the direction of travel;

[0021] The vehicle assistance driving suggestion is generated and displayed based on the road condition information.

[0022] In one feasible approach

[0023] The environment perception module includes:

[0024] The synchronous scanning unit is used to perform synchronous scanning when the vehicle starts, obtain environmental information within a specified range of the vehicle, and perform distortion removal processing on the environmental information to obtain the synchronous sensing scene within the specified range of the vehicle.

[0025] The map building unit is used to perform contour recognition on the synchronous sensing scene using SLAM technology, obtain the contours of several items within a specified range, and build a driving map within the specified range by combining the historical sensing scene.

[0026] The item recognition unit is used to find the appearance attributes corresponding to each item outline, and to perform depth recognition on the item outline using the appearance attributes to determine a number of environmental items within the specified range.

[0027] In one feasible approach

[0028] The map building unit includes:

[0029] The contour recognition subunit is used to locate several key points in the synchronous sensing scene using SLAM technology, and to perform radial diffusion search with each key point as the center to obtain the intersection information between the synchronous sensing scene and each search line, and to establish several sparse contours of the synchronous sensing scene.

[0030] The contour improvement subunit is used to perform boundary expansion on each of the sparse contours to obtain the corresponding complete contour, obtain the smoothness of each complete contour, determine the filtering level of each complete contour based on the smoothness, and perform classification filtering on the complete contours to obtain several object contours in the synchronous sensing scene.

[0031] The feature de-examination subunit is used to identify each of the object outlines in the historical sensing scene and obtain the original features, repeated features and unique features corresponding to each object outline.

[0032] The map construction subunit is used to determine the fixed position of the corresponding item outline within the specified range based on the original features, determine the distribution position of the corresponding item outline within the specified range based on the repeating features, determine the movement position of the corresponding item outline within the specified range based on the unique features, and generate a driving map within the specified range.

[0033] In one feasible approach

[0034] The perception and analysis module includes:

[0035] The data acquisition and processing unit is used to acquire the driving data of the vehicle, establish the driving trajectory of the vehicle based on the driving data, and mark the driving trajectory on the driving map to obtain the coverage and overlap information of the vehicle and the ground surface.

[0036] A depth positioning unit is used to obtain several overlapping positions of the overlapping information in the driving map, obtain the road features corresponding to each overlapping position, and use the road features to perform synchronous positioning of the vehicle to determine the real-time position of the vehicle.

[0037] The collision analysis unit is used to acquire the activity speed characteristics and activity direction characteristics corresponding to each of the environmental objects, and to determine the first collision probability between the environmental objects and each of the environmental objects based on the forward direction of the vehicle.

[0038] In one feasible approach

[0039] The collision analysis unit includes:

[0040] The feature analysis subunit is used to locate each of the environmental objects in the driving map, collect the position change information of the environmental objects at different times, and construct the activity speed feature and activity direction feature corresponding to each environmental object;

[0041] The spatial analysis subunit is used to establish a vehicle spatial vector based on the vehicle's forward direction and forward speed, filter target environmental items corresponding to the target activity direction features that intersect with the vehicle spatial vector, and establish an item spatial vector corresponding to each environmental item using the target activity speed features and target activity direction features corresponding to the target environmental items.

[0042] The collision analysis subunit is used to obtain the overlap duration between each of the object's spatial vector and the vehicle's spatial vector, construct a first collision probability between the vehicle and the target environmental object based on the overlap duration, and regard the first collision probability of environmental objects with no matching collision probability as 0.

[0043] In one feasible approach

[0044] The obstacle avoidance module includes:

[0045] An obstacle avoidance preprocessing unit is used to locate each driving obstacle in the driving map and sort the driving obstacles in descending order of the first collision probability to generate the vehicle's obstacle avoidance queue.

[0046] The obstacle avoidance pre-analysis unit is used to obtain the obstacle attributes corresponding to each of the obstacles, determine the remaining obstacle avoidance distance between the vehicle and each of the driving obstacles based on the obstacle attributes, and determine the probability of the vehicle successfully avoiding each of the driving obstacles in the current lane by combining the obstacle avoidance queue.

[0047] The obstacle avoidance unit is used to locate target driving obstacles with a success probability lower than the standard probability, and to change lanes to avoid the target driving obstacles. It also establishes and displays the obstacle avoidance plan of the vehicle based on the avoidance measures corresponding to the vehicle in the current lane.

[0048] In one feasible approach

[0049] The obstacle avoidance training module includes:

[0050] An obstacle avoidance recording unit is used to record the driver's obstacle avoidance process and determine the driver's avoidance method for each of the driving obstacles.

[0051] A similar training unit is used to classify the avoidance methods according to the obstacle attributes, generate a corresponding set of avoidance measures, and select several habitual actions of the driver with a repetition frequency higher than a preset frequency from the set of avoidance measures.

[0052] The preference analysis unit is used to simulate each of the habitual actions, obtain the driving results corresponding to each habitual action, generate several preferred obstacle avoidance methods, and determine the preference degree of each preferred obstacle avoidance method according to the corresponding repetition frequency.

[0053] The obstacle avoidance optimization unit is used to match the target result of the current obstacle avoidance with the driving result when performing obstacle avoidance, determine the corresponding preferred obstacle avoidance method based on the matching result, generate and display the preferred obstacle avoidance suggestion based on the preferred obstacle avoidance method.

[0054] In one feasible approach

[0055] Also includes:

[0056] The road condition analysis module is used to determine the smoothness features of the current road where the vehicle is located based on the driving map;

[0057] When the smoothness feature is abnormal, it is determined that there is a collapse in the current road, and an early warning message is generated.

[0058] The beneficial effects of the above technical solution are as follows: To achieve synchronous obstacle avoidance and efficient obstacle avoidance, radar scanning is performed simultaneously while the car is driving. Then, SLAM technology is used to construct a driving map. By identifying environmental objects in the driving map and combining them with the car's driving data, the collision probability between the car and different environmental objects is analyzed. Then, assisted obstacle avoidance is performed for driving obstacles with a high collision probability. At the same time, the driver's obstacle avoidance process is recorded. Through long-term training, the obstacle avoidance method preferred by the driver is determined. When the same obstacle is encountered again, the driver's preferred obstacle avoidance method is selected first. In this way, not only can obstacle identification and avoidance be achieved simultaneously, but the driver's proficiency in obstacle avoidance methods can also be enhanced through continuous training, thereby continuously optimizing the obstacle avoidance process, reducing obstacle avoidance time, and improving obstacle avoidance efficiency.

[0059] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0060] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0061] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0062] Figure 1 This is a schematic diagram of the composition of an automotive environmental perception and obstacle avoidance system based on visual imaging technology in an embodiment of the present invention;

[0063] Figure 2 This is a schematic diagram of the environmental perception module of an automotive environmental perception and obstacle avoidance system based on visual imaging technology, as described in an embodiment of the present invention. Detailed Implementation

[0064] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0065] Example 1

[0066] This embodiment provides an automotive environmental perception and obstacle avoidance system based on visual imaging technology, such as... Figure 1 As shown, it includes:

[0067] An environmental perception module is used to activate lidar scanning when the vehicle is in motion, and combine it with SLAM technology to construct a driving map of the vehicle and identify several environmental objects within a specified range of the vehicle.

[0068] The perception and analysis module is used to acquire the vehicle's driving data and mark it on the driving map to synchronously locate the vehicle and determine the first collision probability between the vehicle and each of the environmental objects.

[0069] The obstacle avoidance module is used to filter several driving obstacles in the driving map based on the first collision probability, and to establish an obstacle avoidance plan and perform assisted obstacle avoidance according to the obstacle attributes corresponding to each driving obstacle.

[0070] The obstacle avoidance training module is used to record the driver's obstacle avoidance process, train the obstacle avoidance process to determine the driver's driving preferences, determine the driver's preference for different obstacle avoidance methods, generate and display the optimal obstacle avoidance suggestions.

[0071] In this example, the lidar scanning system consists of a wide-angle camera, a detection radar, a door lock system, an alarm system, and a central processing unit. One wide-angle camera and one detection radar are installed on each of the left and right rearview mirrors of the vehicle. The rearview mirrors are made of one-way mirror glass. The lens of the wide-angle camera is hidden behind the mirror glass. The detection radar is installed at the end of the rearview mirror furthest from the vehicle body and can tilt and swing relative to the mirror. Both the wide-angle camera and the detection radar can exchange data with the central processing unit. Each door of the vehicle is equipped with a door lock system, which can be an external door lock or a vehicle-integrated door lock, and is controlled by the central processing unit. The alarm system can be an external alarm system or a vehicle-integrated alarm system, and is also controlled by the central processing unit. A manual intervention device is used to intervene in the opening and closing of the entire vision-based intelligent driving assistance system or simply to intervene in the opening and closing of the door lock system.

[0072] In this example, environmental items refer to items that exist in the environment where the car is located;

[0073] In this example, SLAM technology represents a technique for simultaneously performing self-localization and environmental mapping in an unknown environment;

[0074] In this example, the driving map represents a map used to show the route a car takes while driving;

[0075] In this example, the first collision probability represents the probability of a collision between the car and an environmental object;

[0076] In this example, when the probability of the first collision is greater than 75%, the corresponding environmental object is considered an obstacle to driving.

[0077] In this example, obstacle attributes represent the appearance, specifications, and material of the obstacle;

[0078] In this example, the role of obstacle avoidance assistance is to provide the driver with obstacle avoidance solutions, improve the driver's obstacle avoidance efficiency, and reduce thinking time;

[0079] In this example, the defined range represents the area centered on the car, with the car's volume doubled.

[0080] In this example, the specific workflow of this system is as follows:

[0081] (1) Collect real vehicle data and simulate the environmental perception and chassis drive-by-wire system assembly and adjustment process through text, voice, and perspective positioning prompts. In view of the shortcomings of traditional ultrasonic obstacle avoidance systems, which are easily affected by road conditions, temperature and other driving environment interference, have low detection accuracy and high cost, laser sensors are used to achieve high-precision detection of the car and obstacles at medium and long distances;

[0082] (2) Analyze real vehicle data, simulate phenomena such as abnormal CAN line waveforms and unresponsive upper computer drive-by-wire systems, and provide real-time feedback on operation results. Design a matrix filter to process the detection data from the laser sensor and improve the reliability of the detection data;

[0083] (3) Combining the detection data of laser and wheel speed sensors, the motion state of the car is systematically analyzed and controlled through neural network algorithms to achieve emergency braking of the car;

[0084] (4) Based on the system functional requirements, complete the design of hardware components such as the laser emission system and the SLAM audiovisual system;

[0085] (5) Complete the software design of the intelligent connected vehicle environmental perception system and conduct system simulation and virtual debugging;

[0086] (6) Implement software and hardware integration of the intelligent vehicle obstacle avoidance system to improve system performance.

[0087] The working principle and beneficial effects of the above technical solution are as follows: To achieve synchronous and efficient obstacle avoidance, radar scanning is performed simultaneously while the car is moving. Then, SLAM technology is used to construct a driving map. By identifying environmental objects in the driving map and combining them with the car's driving data, the collision probability between the car and different environmental objects is analyzed. Then, assisted obstacle avoidance is performed for driving obstacles with a high collision probability. At the same time, the driver's obstacle avoidance process is recorded. Through long-term training, the obstacle avoidance methods preferred by the driver are determined. When the same obstacle is encountered again, the driver's preferred obstacle avoidance method is selected first. In this way, not only can obstacle identification and avoidance be achieved simultaneously, but the driver's proficiency in obstacle avoidance methods can also be enhanced through continuous training, thereby continuously optimizing the obstacle avoidance process, reducing obstacle avoidance time, and improving obstacle avoidance efficiency.

[0088] Example 2

[0089] Based on Embodiment 1, the vehicle environment perception and obstacle avoidance system based on visual imaging technology further includes:

[0090] The in-vehicle obstacle avoidance module is used to obtain real-time information about the vehicle within a specified range when the vehicle is stopped.

[0091] Using the real-time information, identify several dynamic items within the specified range of the vehicle, and establish the activity characteristics of the items within the vehicle's stationary range;

[0092] Based on the activity characteristics of the items, the second collision probability between each dynamic item and each door of the car is determined;

[0093] When the second collision probability is greater than the safe probability, the corresponding dangerous door is located and locked.

[0094] In this example, the second collision probability represents the probability of a collision between a dynamic object and a car door;

[0095] In this example, the probability of safety is 45%.

[0096] The working principle and beneficial effects of the above technical solution are as follows: When the car stops and the passenger wants to open the door, the system can detect whether there are any vehicles on the side and rear of the car in advance. If there are, it can detect information such as their distance and movement trend. The door lock system can prevent the passenger from opening the door rashly. In addition, the advanced processing can also detect whether there is any danger in advance when the driver is about to change lanes, turn, or pull over to the side of the road and issue an alarm. The system has a high degree of intelligence.

[0097] Example 3

[0098] Based on Embodiment 2, the vehicle environment perception and obstacle avoidance system based on visual imaging technology further includes:

[0099] A non-straight-line obstacle avoidance module is used to determine the vehicle's forward direction based on the vehicle's turn signal status;

[0100] Obtain road condition information related to the direction of travel;

[0101] The vehicle assistance driving suggestion is generated and displayed based on the road condition information.

[0102] The working principle and beneficial effects of the above technical solution are as follows: When the car stops and the passenger wants to open the door, the system can detect whether there are any vehicles on the side and rear of the car in advance. If there are, it can detect information such as their distance and movement trend. The door lock system can prevent the passenger from opening the door rashly. In addition, the advanced processing can also detect whether there is any danger in advance when the driver is about to change lanes, turn, or pull over to the side of the road and issue an alarm. The system has a high degree of intelligence.

[0103] Example 4

[0104] Based on Example 1, the aforementioned vehicle environmental perception and obstacle avoidance system based on visual imaging technology, such as Figure 2 As shown, the environment perception module includes:

[0105] The synchronous scanning unit is used to perform synchronous scanning when the vehicle starts, obtain environmental information within a specified range of the vehicle, and perform distortion removal processing on the environmental information to obtain the synchronous sensing scene within the specified range of the vehicle.

[0106] The map building unit is used to perform contour recognition on the synchronous sensing scene using SLAM technology, obtain the contours of several items within a specified range, and build a driving map within the specified range by combining the historical sensing scene.

[0107] The item recognition unit is used to find the appearance attributes corresponding to each item outline, and to perform depth recognition on the item outline using the appearance attributes to determine a number of environmental items within the specified range.

[0108] In this example, distortion correction refers to the process of correcting image distortion caused by factors such as lens distortion and shooting angle in environmental information.

[0109] In this example, the synchronous sensing scene represents the construction of a virtual scene that is consistent with the actual driving state of the car;

[0110] In this example, the historical sensing scene refers to several synchronous sensing scenes that the car passes through during this driving process. When a new synchronous sensing scene appears, the previous synchronous sensing scene is regarded as the historical sensing scene.

[0111] In this example, the appearance attribute represents the appearance of the item's outline;

[0112] In this example, depth recognition refers to the process of inputting appearance attributes and object outlines into big data for recognition, and determining the name of the object outline.

[0113] The working principle and beneficial effects of the above technical solution are as follows: When the car starts to drive, a synchronous scan is performed. Then, distortion removal processing is used to eliminate deformation in the environmental information, ensuring that the generated synchronous sensing scene is consistent with the actual scene of the car's environment, thus ensuring the accuracy of obstacle recognition and obstacle avoidance. Then, SLAM technology is used for contour recognition, thereby combining historical sensing scenes to build a driving map. Finally, depth recognition analysis is performed on the contours of objects to determine the name of each object, and finally, the environmental objects within the specified range are obtained. In this way, the entire driving process of the car can be presented, which is convenient for fault identification.

[0114] Example 5

[0115] Based on Example 4, the map building unit of the vehicle environment perception and obstacle avoidance system based on visual imaging technology includes:

[0116] The contour recognition subunit is used to locate several key points in the synchronous sensing scene using SLAM technology, and to perform radial diffusion search with each key point as the center to obtain the intersection information between the synchronous sensing scene and each search line, and to establish several sparse contours of the synchronous sensing scene.

[0117] The contour improvement subunit is used to perform boundary expansion on each of the sparse contours to obtain the corresponding complete contour, obtain the smoothness of each complete contour, determine the filtering level of each complete contour based on the smoothness, and perform classification filtering on the complete contours to obtain several object contours in the synchronous sensing scene.

[0118] The feature de-examination subunit is used to identify each of the object outlines in the historical sensing scene and obtain the original features, repeated features and unique features corresponding to each object outline.

[0119] The map construction subunit is used to determine the fixed position of the corresponding item outline within the specified range based on the original features, determine the distribution position of the corresponding item outline within the specified range based on the repeating features, determine the movement position of the corresponding item outline within the specified range based on the unique features, and generate a driving map within the specified range.

[0120] In this example, key points refer to several points randomly selected in the synchronous sensing scenario, which are arranged at equal intervals.

[0121] In this example, radial diffusion search refers to a search process that radiates outward from a key point as the center and the total number of key points as the radial lines. During the search, when the radial lines intersect with the contours in the synchronously sensed scene, an intersection point is recorded and the intersection information is updated.

[0122] In this example, the sparse contour represents the contour generated after a radial diffusion search;

[0123] In this example, boundary dilation refers to the process of comparing each pixel in a sparse contour with other pixels in its neighborhood, thereby expanding the boundary of a sparse image.

[0124] In this example, the higher the smoothness, the lower the filtering level;

[0125] In this example, the original features represent the outlines of objects that have existed in the historical synchronous sensing scene, the repeated features represent the outlines of objects that appear repeatedly in the historical synchronous sensing scene, and the unique features represent the outlines of objects that appear for the first time in the synchronous sensing scene.

[0126] The working principle and beneficial effects of the above technical solution are as follows: In order to further improve the driving map and reduce the error of object recognition, SLAM technology is first used to locate several key points in the synchronous sensing scene. Then, a radial diffusion search is performed starting from these points to establish sparse contours using the cross information obtained from the search. The sparse contours are further expanded and filtered to obtain the object contours in the synchronous sensing scene. Then, the features of each object contour are identified and located accordingly. Finally, the driving map is generated. By processing the object contours multiple times, the accuracy of the generated driving map can be guaranteed, and synchronous positioning can be better achieved.

[0127] Example 6

[0128] Based on Example 1, the vehicle environment perception and obstacle avoidance system based on visual imaging technology includes a perception and analysis module comprising:

[0129] The data acquisition and processing unit is used to acquire the driving data of the vehicle, establish the driving trajectory of the vehicle based on the driving data, and mark the driving trajectory on the driving map to obtain the coverage and overlap information of the vehicle and the ground surface.

[0130] A depth positioning unit is used to obtain several overlapping positions of the overlapping information in the driving map, obtain the road features corresponding to each overlapping position, and use the road features to perform synchronous positioning of the vehicle to determine the real-time position of the vehicle.

[0131] The collision analysis unit is used to acquire the activity speed characteristics and activity direction characteristics corresponding to each of the environmental objects, and to determine the first collision probability between the environmental objects and each of the environmental objects based on the forward direction of the vehicle.

[0132] In this example, the overlap information indicates the overlap between the car and the ground surface;

[0133] In this example, the activity speed feature represents the speed at which an environmental object travels, and the activity direction feature represents the direction in which an environmental object travels. If the environmental object is stationary, then the activity speed feature is 0, and the activity direction feature is perpendicular to the ground.

[0134] The working principle and beneficial effects of the above technical solution are as follows: By processing the vehicle's driving data, the vehicle's trajectory is determined. Then, by combining the overlap information between the vehicle and the ground surface, synchronous positioning is achieved. Finally, by analyzing the speed and direction characteristics of environmental objects, the collision probability between the vehicle and different objects is determined. This allows for real-time monitoring of the vehicle's movement. It is applicable not only to private cars but also to commercial vehicles, public transportation, and autonomous vehicles, providing drivers with a safer and smarter driving experience. It not only reduces the risk of traffic accidents but also helps improve road traffic efficiency.

[0135] Example 7

[0136] Based on Example 6, the collision analysis unit of the vehicle environmental perception and obstacle avoidance system based on visual imaging technology includes:

[0137] The feature analysis subunit is used to locate each of the environmental objects in the driving map, collect the position change information of the environmental objects at different times, and construct the activity speed feature and activity direction feature corresponding to each environmental object;

[0138] The spatial analysis subunit is used to establish a vehicle spatial vector based on the vehicle's forward direction and forward speed, filter target environmental items corresponding to the target activity direction features that intersect with the vehicle spatial vector, and establish an item spatial vector corresponding to each environmental item using the target activity speed features and target activity direction features corresponding to the target environmental items.

[0139] The collision analysis subunit is used to obtain the overlap duration between each of the object's spatial vector and the vehicle's spatial vector, construct a first collision probability between the vehicle and the target environmental object based on the overlap duration, and regard the first collision probability of environmental objects with no matching collision probability as 0.

[0140] In this example, the car space vector represents the car's movement in three-dimensional space, and the item space vector represents the item's movement in three-dimensional space.

[0141] The working principle and beneficial effects of the above technical solution are as follows: After identifying the environmental objects contained in the driving map, the speed and direction characteristics of each environmental object are analyzed to establish a corresponding spatial vector. By analyzing the collision situation between spatial vectors, the collision probability between the car and the environmental objects is determined, thus completing obstacle recognition and laying the foundation for subsequent obstacle avoidance.

[0142] Example 8

[0143] Based on Embodiment 1, the vehicle environment perception and obstacle avoidance system based on visual imaging technology, wherein the obstacle avoidance module includes:

[0144] An obstacle avoidance preprocessing unit is used to locate each driving obstacle in the driving map and sort the driving obstacles in descending order of the first collision probability to generate the vehicle's obstacle avoidance queue.

[0145] The obstacle avoidance pre-analysis unit is used to obtain the obstacle attributes corresponding to each of the obstacles, determine the remaining obstacle avoidance distance between the vehicle and each of the driving obstacles based on the obstacle attributes, and determine the probability of the vehicle successfully avoiding each of the driving obstacles in the current lane by combining the obstacle avoidance queue.

[0146] The obstacle avoidance unit is used to locate target driving obstacles with a success probability lower than the standard probability, and to change lanes to avoid the target driving obstacles. It also establishes and displays the obstacle avoidance plan of the vehicle based on the avoidance measures corresponding to the vehicle in the current lane.

[0147] In this example, the standard probability is 95%.

[0148] The working principle and beneficial effects of the above technical solution are as follows: When avoiding obstacles, the obstacle avoidance lane is selected first, which can not only achieve obstacle avoidance, but also reduce danger, avoid distraction caused by the driver performing multiple operations at the same time, and in order to improve the quality of the driver's obstacle avoidance and avoid interfering with the driver's judgment of the actual situation, only auxiliary obstacle avoidance is used to cooperate with the driver during obstacle avoidance, thereby improving the success rate of obstacle avoidance.

[0149] Example 9

[0150] Based on Example 1, the obstacle avoidance training module of the vehicle environment perception and obstacle avoidance system based on visual imaging technology includes:

[0151] An obstacle avoidance recording unit is used to record the driver's obstacle avoidance process and determine the driver's avoidance method for each of the driving obstacles.

[0152] A similar training unit is used to classify the avoidance methods according to the obstacle attributes, generate a corresponding set of avoidance measures, and select several habitual actions of the driver with a repetition frequency higher than a preset frequency from the set of avoidance measures.

[0153] The preference analysis unit is used to simulate each of the habitual actions, obtain the driving results corresponding to each habitual action, generate several preferred obstacle avoidance methods, and determine the preference degree of each preferred obstacle avoidance method according to the corresponding repetition frequency.

[0154] The obstacle avoidance optimization unit is used to match the target result of the current obstacle avoidance with the driving result when performing obstacle avoidance, determine the corresponding preferred obstacle avoidance method based on the matching result, generate and display the preferred obstacle avoidance suggestion based on the preferred obstacle avoidance method.

[0155] In this example, the preset frequency is 30%.

[0156] The working principle and beneficial effects of the above technical solution are as follows: When the driver avoids obstacles, his obstacle avoidance actions are recorded, and then the driver's habitual actions are selected. When the driver encounters obstacles that have appeared before, the driver's preferred obstacle avoidance method is selected first. This allows the driver to adapt to the vehicle and improve the speed and efficiency of obstacle avoidance through repeated training, thereby reducing the probability of danger.

[0157] Example 10

[0158] Based on Embodiment 1, the vehicle environment perception and obstacle avoidance system based on visual imaging technology further includes:

[0159] The road condition analysis module is used to determine the smoothness features of the current road where the vehicle is located based on the driving map;

[0160] When the smoothness feature is abnormal, it is determined that there is a collapse in the current road, and an early warning message is generated.

[0161] The working principle and beneficial effects of the above technical solution are as follows: it analyzes road conditions while the driver is driving, further reducing the probability of danger and ensuring the safety of the driver and passengers.

[0162] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A vehicle environmental perception and obstacle avoidance system based on visual imaging technology, characterized in that, include: An environmental perception module is used to activate lidar scanning when the vehicle is in motion, and combine it with SLAM technology to construct a driving map of the vehicle and identify several environmental objects within a specified range of the vehicle. The perception and analysis module is used to acquire the vehicle's driving data and mark it on the driving map to synchronously locate the vehicle and determine the first collision probability between the vehicle and each of the environmental objects. The obstacle avoidance module is used to filter several driving obstacles in the driving map based on the first collision probability, and to establish an obstacle avoidance plan and perform assisted obstacle avoidance according to the obstacle attributes corresponding to each driving obstacle. The obstacle avoidance training module is used to record the driver's obstacle avoidance process, train the obstacle avoidance process to determine the driver's driving preferences, determine the driver's preference for different obstacle avoidance methods, generate and display the optimal obstacle avoidance suggestions; The environmental perception module includes: The synchronous scanning unit is used to perform synchronous scanning when the vehicle starts, obtain environmental information within a specified range of the vehicle, and perform distortion removal processing on the environmental information to obtain the synchronous sensing scene within the specified range of the vehicle. The map building unit is used to perform contour recognition on the synchronous sensing scene using SLAM technology, obtain the contours of several items within a specified range, and build a driving map within the specified range by combining the historical sensing scene. The item recognition unit is used to find the appearance attributes corresponding to each item outline, and use the appearance attributes to perform depth recognition on the item outline to determine a number of environmental items within the specified range. The map construction unit includes: The contour recognition subunit is used to locate several key points in the synchronous sensing scene using SLAM technology, and to perform radial diffusion search with each key point as the center to obtain the intersection information between the synchronous sensing scene and each search line, and to establish several sparse contours of the synchronous sensing scene. The contour improvement subunit is used to perform boundary expansion on each of the sparse contours to obtain the corresponding complete contour, obtain the smoothness of each complete contour, determine the filtering level of each complete contour based on the smoothness, and perform classification filtering on the complete contours to obtain several object contours in the synchronous sensing scene. The feature de-examination subunit is used to identify each of the object outlines in the historical sensing scene and obtain the original features, repeated features and unique features corresponding to each object outline. The map construction subunit is used to determine the fixed position of the corresponding item outline within the specified range based on the original features, determine the distribution position of the corresponding item outline within the specified range based on the repeating features, determine the movement position of the corresponding item outline within the specified range based on the unique features, and generate a driving map within the specified range.

2. The vehicle environmental perception and obstacle avoidance system based on visual imaging technology as described in claim 1, characterized in that, Also includes: The in-vehicle obstacle avoidance module is used to obtain real-time information about the vehicle within a specified range when the vehicle is stopped. Using the real-time information, identify several dynamic items within the specified range of the vehicle, and establish the activity characteristics of the items within the vehicle's stationary range; Based on the activity characteristics of the items, the second collision probability between each dynamic item and each door of the car is determined; When the second collision probability is greater than the safe probability, the corresponding dangerous door is located and locked.

3. The vehicle environmental perception and obstacle avoidance system based on visual imaging technology as described in claim 2, characterized in that, Also includes: A non-straight-line obstacle avoidance module is used to determine the vehicle's forward direction based on the vehicle's turn signal status; Obtain road condition information related to the direction of travel; The vehicle assistance driving suggestion is generated and displayed based on the road condition information.

4. The vehicle environmental perception and obstacle avoidance system based on visual imaging technology as described in claim 1, characterized in that, The perception and analysis module includes: The data acquisition and processing unit is used to acquire the driving data of the vehicle, establish the driving trajectory of the vehicle based on the driving data, and mark the driving trajectory on the driving map to obtain the coverage and overlap information of the vehicle and the ground surface. A depth positioning unit is used to obtain several overlapping positions of the overlapping information in the driving map, obtain the road features corresponding to each overlapping position, and use the road features to perform synchronous positioning of the vehicle to determine the real-time position of the vehicle. The collision analysis unit is used to acquire the activity speed characteristics and activity direction characteristics corresponding to each of the environmental objects, and to determine the first collision probability between the environmental objects and each of the environmental objects based on the forward direction of the vehicle.

5. The vehicle environmental perception and obstacle avoidance system based on visual imaging technology as described in claim 4, characterized in that, The collision analysis unit includes: The feature analysis subunit is used to locate each of the environmental objects in the driving map, collect the position change information of the environmental objects at different times, and construct the activity speed feature and activity direction feature corresponding to each environmental object; The spatial analysis subunit is used to establish a vehicle spatial vector based on the vehicle's forward direction and forward speed, filter target environmental items corresponding to the target activity direction features that intersect with the vehicle spatial vector, and establish an item spatial vector corresponding to each environmental item using the target activity speed features and target activity direction features corresponding to the target environmental items. The collision analysis subunit is used to obtain the overlap duration between each of the object's spatial vector and the vehicle's spatial vector, construct a first collision probability between the vehicle and the target environmental object based on the overlap duration, and regard the first collision probability of environmental objects with no matching collision probability as 0.

6. The vehicle environmental perception and obstacle avoidance system based on visual imaging technology as described in claim 1, characterized in that, The obstacle avoidance module includes: An obstacle avoidance preprocessing unit is used to locate each driving obstacle in the driving map and sort the driving obstacles in descending order of the first collision probability to generate the vehicle's obstacle avoidance queue. The obstacle avoidance pre-analysis unit is used to obtain the obstacle attributes corresponding to each of the obstacles, determine the remaining obstacle avoidance distance between the vehicle and each of the driving obstacles based on the obstacle attributes, and determine the probability of the vehicle successfully avoiding each of the driving obstacles in the current lane by combining the obstacle avoidance queue. The obstacle avoidance unit is used to locate target driving obstacles with a success probability lower than the standard probability, and to change lanes to avoid the target driving obstacles. It also establishes and displays the obstacle avoidance plan of the vehicle based on the avoidance measures corresponding to the vehicle in the current lane.

7. The vehicle environmental perception and obstacle avoidance system based on visual imaging technology as described in claim 1, characterized in that, The obstacle avoidance training module includes: An obstacle avoidance recording unit is used to record the driver's obstacle avoidance process and determine the driver's avoidance method for each of the driving obstacles. A similar training unit is used to classify the avoidance methods according to the obstacle attributes, generate a corresponding set of avoidance measures, and select several habitual actions of the driver with a repetition frequency higher than a preset frequency from the set of avoidance measures. The preference analysis unit is used to simulate each of the habitual actions, obtain the driving results corresponding to each habitual action, generate several preferred obstacle avoidance methods, and determine the preference degree of each preferred obstacle avoidance method according to the corresponding repetition frequency. The obstacle avoidance optimization unit is used to match the target result of the current obstacle avoidance with the driving result when performing obstacle avoidance, determine the corresponding preferred obstacle avoidance method based on the matching result, generate and display the preferred obstacle avoidance suggestion based on the preferred obstacle avoidance method.

8. The vehicle environmental perception and obstacle avoidance system based on visual imaging technology as described in claim 1, characterized in that, Also includes: The road condition analysis module is used to determine the smoothness features of the current road where the vehicle is located based on the driving map; When the smoothness feature is abnormal, it is determined that there is a collapse in the current road, and an early warning message is generated.

Images