Intelligent driving lane changing system based on image analysis

Abstract

The invention relates to the technical field of intelligent driving lane changing, in particular to an intelligent driving lane changing system based on image analysis, which comprises an image acquisition module, an analysis module, a judgment module and an automatic lane changing module, according to the method, the image information in the vehicle driving process is obtained through the judgment model, the image information at different moments is judged, and once it is found that the blocking degree in the vehicle driving process exceeds a set value, lane changing driving is conducted immediately, so that the driving speed is increased, and the driving efficiency is improved. By accurately judging the influence of the front road information on the visual field of the vehicle, a lane changing decision is made in time, traffic accidents caused by visual field blocking are avoided, the risk of collision with obstacles is avoided in advance, and the safety of automatic driving is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent driving lane changing, and in particular to an intelligent driving lane changing system based on image analysis. Background Art

[0002] With the continuous development of science and technology, intelligent driving technology has attracted more and more attention. When driving on the highway, the driver needs to pay attention to the road conditions ahead at all times so as to make lane change decisions in time. However, on the highway, due to the different levels of drivers, drivers with younger driving experience drive at a slower speed during driving, which can easily lead to rear-end collisions with the following vehicles. In addition, when following a vehicle, if the vehicle is blocked by the vehicle in front during driving, in case of emergencies, for example, there is an obstacle in front of the vehicle in front during following, and the vehicle in front changes lanes near the obstacle, if the vehicle cannot obtain the road conditions of the vehicle in front in real time during following, it is easy for the vehicle to avoid in time, resulting in scratches on the vehicle chassis, and even traffic accidents. In view of this, an intelligent driving lane change system based on image analysis is proposed. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent driving lane changing system based on image analysis to solve the problems raised in the above background technology.

[0004] To achieve the above purpose, an intelligent driving lane changing system based on image analysis is provided, including an image acquisition module, an analysis module, a judgment module and an automatic lane changing module; The image acquisition module is used to select a driving lane according to the user's driving habits, collect image information around the vehicle during driving, and pre-process the collected image information; The analysis module is used to process and analyze the collected image information, identify road signs, lane lines, moving vehicles and obstacles, and calculate the distance and relative position between the vehicle and them; The judgment module is used to input the recognized image information into the judgment model, and the judgment model automatically outputs the lane change judgment strategy according to the picture information, wherein the judgment model is obtained through machine learning training using multiple sets of data, and the multiple sets of data include a first category of data and a second category of data, and each set of data in the first category of data includes: pictures of vehicles that meet the lane change standards; each set of data in the second category of data includes: pictures of vehicles that do not meet the lane change standards.

[0005] The automatic lane changing module controls the lane changing behavior of the vehicle based on the lane changing judgment strategy of the judgment module. If the vehicle does not meet the lane changing criteria, the vehicle continues to travel at a normal uniform speed in the lane according to the set speed. If the vehicle meets the lane changing criteria and obtains the road condition information of the target lane, the vehicle automatically changes lanes.

[0006] As a further improvement of the technical solution, the image acquisition module obtains image information of the front vehicle at different times during driving through a high-definition camera, and then denoises the obtained image information through Gaussian filtering to improve image quality.

[0007] As a further improvement of the technical solution, the analysis module includes a recognition unit and a distance measurement unit; The recognition unit uses a deep learning algorithm to recognize objects in the image acquired by the image acquisition module; The distance measuring unit calculates the distance and relative position between the vehicle and surrounding objects through triangulation according to the results of object recognition and lane line detection in the recognition unit.

[0008] As a further improvement of the technical solution, the triangulation method is used to calculate the distance and relative position of the vehicle and surrounding objects as follows: , where d represents the distance between the vehicle and the object; b represents the baseline length of the camera, that is, the horizontal distance between the two cameras; h represents the focal length of the camera; and x represents the parallax of the object in the image, that is, the horizontal position difference of the object in the two camera images.

[0009] As a further improvement of the technical solution, the judgment module includes an image annotation unit and a model judgment unit; The image annotation unit is used to collect image data of the vehicle in different scenarios, annotate the image data in different scenarios, clarify the driving requirements corresponding to the different image data, the driving requirements include driving with lane change and driving without lane change, and divide the data of the standard number into a training set, a verification set and a test set; The model judgment unit is used to establish a judgment model, train the model through a standard training set, enable the judgment model to automatically make lane change judgments on input image information, and regularly optimize and update the judgment model to adapt to different road conditions and driving environments.

[0010] As a further improvement of the present technical solution, the judgment module also includes a deviation setting unit, which is used to obtain the lane change judgment information in the model judgment unit, keep the vehicle's driving speed unchanged and make the vehicle deviate from the lane by a certain distance during the following process, set a timing threshold, and judge whether the vehicle needs to change lanes within the timing threshold through the judgment model in the model judgment unit. If lane change is required, send information to the automatic lane change module.

[0011] As a further improvement of the technical solution, the automatic lane change module includes a control unit and a position detection unit; The control unit is used to receive the lane change judgment information in the model judgment unit, and if the vehicle needs to change lanes, control the vehicle to drive to the adjacent lane; if the vehicle does not need to change lanes, the vehicle continues to drive normally in the driving lane; The position detection unit is used to detect the position and offset of the vehicle in the target lane after the vehicle changes lanes, so as to ensure that the vehicle travels in the center of the lane.

[0012] As a further improvement of the present technical solution, the control unit performs automatic lane change for the vehicle, and performs multiple safety checks during the automatic lane change process, including but not limited to ensuring that the target lane is idle and free of potential dangers, and continuously monitoring the vehicle status and surrounding environment changes during the lane change process, and being ready to take emergency braking and other measures at any time.

[0013] As a further improvement of the technical solution, the position detection unit detects the position and offset of the vehicle in the target lane, including the following steps: Data collection and monitoring: Utilize sensors on the vehicle to continuously collect data, including but not limited to camera images, wheel speed sensor data, and steering angle sensor data; Position and offset determination: Process the images captured by the camera to identify the lane lines of the target lane; Adjustment strategy formulation: formulate corresponding adjustment strategies based on the determined position and offset; Execute adjustment actions: Convert the formulated steering adjustment strategy into specific steering instructions, send them to the vehicle's steering system, and adjust the vehicle's speed appropriately according to the vehicle's position and driving status in the target lane.

[0014] Compared with the prior art, the present invention has the following beneficial effects: In this intelligent driving lane-changing system based on image analysis, the judgment model is used to obtain image information during the vehicle's driving process. By judging the image information at different times, once it is found that the degree of obstruction during the vehicle's driving process exceeds the set value, the lane is changed immediately. By accurately judging the impact of the road information ahead on the vehicle's field of vision, a lane-changing decision is made in a timely manner to avoid traffic accidents caused by obstructed vision, avoid the risk of collision with obstacles in advance, and improve the safety of autonomous driving; In this intelligent driving lane change system based on image analysis, the analysis module is used to quickly and accurately identify objects in front during vehicle driving. The algorithm can complete object recognition tasks within milliseconds and can accurately identify objects such as vehicles, obstacles, road signs, etc., providing reliable environmental perception information for the intelligent driving system, helping to make more accurate decisions, improving driving safety, and not being interfered with by human factors, reducing the risk of accidents caused by human errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the working principle of the overall module of the present invention; Figure 2 A schematic diagram of the overall module of the present invention; The meaning of each number in the figure is: 100, image acquisition module; 200, analysis module; 300, judgment module; 400, automatic lane change module. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] See also Figure 1-Figure 2 As shown, an intelligent driving lane changing system based on image analysis is provided, including an image acquisition module 100, an analysis module 200, a judgment module 300 and an automatic lane changing module 400; The image acquisition module 100 is used to select a driving lane according to the user's driving habits, collect image information around the vehicle during driving, and pre-process the collected image information; Considering that during high-speed driving, the driver needs to concentrate highly, and long-term high concentration of the mind can easily lead to fatigue. Therefore, the image acquisition module 100 obtains image information of the front vehicle at different times during driving through a high-definition camera, and then denoises the obtained image information through the Gaussian filter method to improve the image quality. A high-resolution, high-frame-rate high-definition camera is selected, and the focal length, viewing angle, aperture and other parameters of the camera are adjusted to obtain the best image effect, ensuring that the image information around the vehicle can be clearly captured. The camera is installed at the front, rear and both sides of the vehicle. The front camera can be installed above the windshield or at the bumper to capture the road conditions ahead; the rear camera is installed at the rear of the vehicle to observe the rear vehicles and road conditions; the cameras on both sides can be installed near the rearview mirror to expand the field of view of the vehicle, connect the camera to the image acquisition system, and use wireless connections such as Wi-Fi, Bluetooth, etc. to ensure stable and reliable data transmission. The collected image is denoised by Gaussian filtering to remove noise and interference in the image. The camera replaces the driver to collect images of the road conditions, avoids driver fatigue driving, and improves driving safety.

[0018] The analysis module 200 is used to process and analyze the collected image information, identify road signs, lane lines, moving vehicles and obstacles, and calculate the distance and relative position between the vehicle and them; On highways, vehicles travel at high speeds and need to quickly and accurately identify objects in front. The algorithm can complete object recognition tasks within milliseconds and can accurately identify objects such as vehicles, obstacles, and road signs. It provides reliable environmental perception information for the intelligent driving system, helps to make more accurate decisions, improves driving safety, is not affected by human factors, and reduces the risk of accidents caused by human errors.

[0019] In order to achieve high accuracy in complex object recognition tasks during vehicle driving, the analysis module 200 includes a recognition unit and a distance measurement unit; The recognition unit uses a deep learning algorithm to recognize objects in the image acquired by the image acquisition module 100; The distance measurement unit calculates the distance and relative position between the vehicle and surrounding objects through triangulation based on the results of object recognition and lane line detection in the recognition unit.

[0020] The triangulation method calculates the distance and relative position of the vehicle and surrounding objects as follows: , where d represents the distance between the vehicle and the object; b represents the baseline length of the camera, that is, the horizontal distance between the two cameras; h represents the focal length of the camera; and x represents the parallax of the object in the image, that is, the horizontal position difference of the object in the two camera images.

[0021] Focal length h: The focal length of the camera determines the viewing angle and magnification of the image. A camera with a shorter focal length has a wider viewing angle, but the size of the object in the image is smaller; a camera with a longer focal length has a narrower viewing angle, but the size of the object in the image is larger. In actual applications, the focal length value needs to be determined based on the specifications and installation location of the camera. The focal length parameters can be obtained from the camera's technical manual or actual measurements.

[0022] Baseline length b: The baseline length refers to the horizontal distance between the two cameras. If there is only one camera, the baseline length can be simulated by the width of the vehicle or other known dimensions. The larger the baseline length, the higher the accuracy of triangulation, but it will also increase the complexity and cost of the system. In practical applications, it is necessary to determine the appropriate baseline length based on the accuracy requirements of the system and the size of the vehicle.

[0023] Disparity calculation x for two cameras: When using two cameras for triangulation, it is necessary to calculate the disparity of the object in the two camera images. Disparity refers to the difference in the horizontal position of an object in two images. The image matching algorithm can be used to determine the corresponding position of the object in the two images, and then calculate the disparity. Commonly used image matching algorithms include feature point matching and area matching. For example, for the feature point matching algorithm, feature points can be extracted from the two images, and then the position of the corresponding feature points can be determined through feature description and matching algorithms. The disparity is the difference in the horizontal coordinates of the corresponding feature points in the two images.

[0024] For a single camera: If there is only one camera, the parallax can be calculated by the position change of the object at different times. Suppose the vehicle takes two images at time and respectively, and the positions of the object in the two images are x1, y1 and x2, y2 respectively.

[0025] The displacement of an object in real space can be calculated by the vehicle's speed and time difference, and then the parallax can be calculated based on the camera's focal length and image size.

[0026] For example, suppose the vehicle's speed is v and the time difference is , then the displacement of the object in real space is If the focal length of the camera is h and the width of the image is w, then the parallax .

[0027] Distance calculation: Substitute the known camera parameters focal length h and baseline length b and the calculated parallax into the formula , the distance d between the vehicle and the object can be calculated.

[0028] Through triangulation, the distance and relative position of the vehicle and surrounding objects can be calculated, providing important environmental perception information for the intelligent driving system.

[0029] The deep learning algorithm recognizes the objects in the acquired image, which specifically includes the following steps: Data collection: Collect a large amount of image data containing various objects. This data should cover different scenes, lighting conditions, angles, and object states. For example, for highway scenes, collect images containing vehicles, obstacles, road signs, and other objects. Data can be obtained from public data sets, actual images, or simulated images. Ensure the diversity and representativeness of the data to improve the generalization ability of the model, annotate the collected image data, determine the category and location information of each object in the image, and preprocess the annotated images. The preprocessing steps include image scaling and normalization. Model training: Build the selected convolutional neural network architecture and divide the preprocessed image data into training set, validation set and test set. The training set is used for model training, the validation set is used to adjust the model's hyperparameters and evaluate the model's performance, and the test set is used to finally evaluate the model's generalization ability. They are usually divided according to a certain ratio, for example, 70% of the images are used for training, 20% of the images are used for validation, and 10% of the images are used for testing. The image data of the training set is input into the constructed convolutional neural network. Through the back-propagation algorithm and optimizer, such as stochastic gradient descent, the parameters of the model are continuously adjusted to make the output of the model gradually approach the actual annotation results. Model evaluation and optimization: Use the test set to conduct a final evaluation of the trained model, and calculate the model's accuracy, recall rate, F1 value and other indicators on the test set. The evaluation results can reflect the generalization ability of the model and the actual application effect. According to the evaluation results and actual needs, the model is optimized so that the vehicle can quickly and accurately identify objects in front when driving at high speed on the highway, complete the object recognition task within milliseconds, and accurately identify objects such as vehicles, obstacles, and road signs. Provide reliable environmental perception information for the intelligent driving system, help make more accurate decisions, improve driving safety, and not be interfered with by human factors, reducing the risk of accidents caused by human errors.

[0030] The judgment module 300 is used to input the recognized image information into the judgment model, and the judgment model automatically outputs the lane change judgment strategy according to the picture information, wherein the judgment model is obtained through machine learning training using multiple sets of data, and the multiple sets of data include a first category of data and a second category of data, and each set of data in the first category of data includes: pictures of vehicles that meet the lane change standards; each set of data in the second category of data includes: pictures of vehicles that do not meet the lane change standards.

[0031] During driving on a highway, in order to prevent the vehicle's field of vision from being blocked by the vehicle in front, which may affect the vehicle's timely lane change decision and cause a traffic accident, the judgment module 300 includes an image annotation unit and a model judgment unit; The image annotation unit is used to collect image data of vehicles in different scenarios and annotate the image data in different scenarios. For example, if the high-definition image information obtained by the camera is blocked by the vehicle in front by less than 30%, it is marked as no need to change lanes. If the image information summarized during driving shows that your field of vision is blocked by the vehicle in front by more than 30%, it is marked as needing to change lanes. Because the degree of obstruction of the field of vision is higher than 30% during driving, it is easy to make it impossible to accurately judge the road conditions, so the driving requirements corresponding to different image data are clarified. The driving requirements include the need to change lanes and the need not to change lanes. The standard number data is divided into a training set, a validation set, and a test set. The model judgment unit is used to establish a judgment model, train the model through a standard training set, and enable the judgment model to automatically make lane change judgments based on the input image information. The judgment model is regularly optimized and updated to adapt to different road conditions and driving environments. When obtaining image information during the vehicle's driving process, the image information at different times is judged. Once it is found that the degree of obstruction during the vehicle's driving process exceeds 30%, the lane is changed immediately. By accurately judging the impact of the road information ahead on the vehicle's field of vision, a lane change decision is made in a timely manner to avoid traffic accidents caused by obstructed vision and improve the safety of autonomous driving.

[0032] Taking into account that in the process of high-speed driving, in order to avoid frequent lane changes of the vehicle, the risk of increased collision and the impact on the stability of the vehicle, the judgment module 300 also includes a setting deviation unit. The deviation unit is used to obtain the lane change judgment information in the model judgment unit. While keeping the vehicle's driving speed unchanged, the vehicle deviates from the lane by a certain distance during the following process, and sets a timing threshold. The threshold time can be set to 10 seconds. Within the timing threshold, the model judgment unit determines whether the vehicle needs to change lanes. If lane change is required, the information is sent to the automatic lane change module 400. During the vehicle driving process, when the judgment model determines that the vehicle needs to change lanes, the deviation unit is used to determine whether the vehicle needs to change lanes. The vehicle will deviate from the lane by 10% to reduce the degree of obstruction. If the front vehicle is always driving at a low speed during driving, the proportion of the vehicle's field of vision obstruction will continue to increase within the technical threshold. The driver of the front vehicle is likely to be a novice driver. Following the vehicle behind him is prone to safety accidents. Therefore, when the vehicle deviates from the lane and exceeds the set timely threshold time, the judgment model also prompts that a lane change is required, and the lane change strategy information is sent to the automatic lane change module 400 for lane change, thereby avoiding frequent lane changes of the vehicle and improving driving safety. At the same time, it avoids following the vehicle behind a novice vehicle and avoids safety hazards in advance.

[0033] The automatic lane changing module 400 controls the lane changing behavior of the vehicle based on the lane changing judgment strategy of the judgment module 300. If the vehicle does not meet the lane changing criteria, the vehicle continues to travel at a normal uniform speed in the lane according to the set speed. If the vehicle meets the lane changing criteria and obtains the road condition information of the target lane, the vehicle automatically changes lanes.

[0034] When changing lanes, in order to enhance driving comfort and safety, the automatic lane changing module 400 includes a control unit and a position detection unit; The control unit is used to receive the lane change judgment information in the model judgment unit, and if the vehicle needs to change lanes, the vehicle is controlled to drive to an adjacent lane; if the vehicle does not need to change lanes, the vehicle continues to drive normally in the driving lane; The position detection unit is used to detect the position and offset of the vehicle in the target lane after the vehicle completes the lane change, to ensure that the vehicle is driving in the center of the lane.

[0035] The vehicle in the control unit automatically changes lanes and performs multiple safety checks during the process, including but not limited to ensuring that the target lane is idle and free of potential dangers, and continuously monitoring the vehicle status and surrounding environment changes during the lane change process, and being ready to take emergency braking and other measures at any time.

[0036] During the lane changing process, the vehicle's status is continuously monitored, including speed, acceleration, steering angle, and tire status. These parameters can reflect the vehicle's driving stability and handling performance. If any abnormal situation is found in the vehicle, such as tire slippage, steering loss of control, etc., the system needs to take corresponding measures immediately, such as adjusting the steering angle, reducing speed, etc., to ensure the safety of the vehicle. Sensors are used to continuously monitor changes in the surrounding environment, including the position and speed changes of other vehicles, and changes in road conditions. If it is found that surrounding vehicles suddenly accelerate, decelerate or change lanes, or obstacles appear on the road, the system needs to respond in time to avoid them. At the same time, the system always keeps the emergency braking system ready so that braking measures can be taken quickly when necessary.

[0037] The position detection unit detects the position and offset of the vehicle in the target lane, including the following steps: Data collection and monitoring: Utilize sensors on the vehicle to continuously collect data, including but not limited to camera images, wheel speed sensor data, and steering angle sensor data; Position and offset determination: Process the images captured by the camera to identify the lane lines of the target lane; Adjustment strategy formulation: formulate corresponding adjustment strategies based on the determined position and offset; Execute adjustment actions: Convert the formulated steering adjustment strategy into specific steering instructions, send them to the vehicle's steering system, and adjust the vehicle's speed appropriately according to the vehicle's position and driving status in the target lane.

[0038] By ensuring that the target lane is free and free of potential hazards, it can effectively avoid collisions with vehicles, obstacles or other objects in the target lane. For example, on a busy highway, accurately judging the vehicle spacing and potential hazards in the target lane can prevent side collisions with other vehicles when changing lanes. This verification mechanism greatly reduces the incidence of traffic accidents.

[0039] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. Intelligent driving lane changing system based on image analysis, characterized by: It comprises an image acquisition module (100), an analysis module (200), a judgment module (300) and an automatic lane change module (400); The image acquisition module (100) is used to select a driving lane according to a user's driving habits, to collect image information around the vehicle during driving, and to pre-process the collected image information; The analysis module (200) is used to process and analyze the collected image information, identify road signs, lane lines, moving vehicles and obstacles, and calculate the distance and relative position between the vehicle and the obstacles; The judgment module (300) is used to input the recognized image information into the judgment model, and the judgment model automatically outputs a lane change judgment strategy according to the image information, wherein the judgment model is obtained by machine learning training using multiple sets of data, and the multiple sets of data include a first type of data and a second type of data, each set of data in the first type of data includes: a picture including a vehicle that meets the lane change standard; each set of data in the second type of data includes: a picture including a vehicle that does not meet the lane change standard; The automatic lane changing module (400) controls the lane changing behavior of the vehicle based on the lane changing judgment strategy of the judgment module (300); if the vehicle does not meet the lane changing standard, the vehicle continues to travel at a normal uniform speed in the lane according to the set speed; if the vehicle meets the lane changing standard, the target lane road condition information is obtained, and the vehicle automatically changes lanes.

2. The intelligent driving lane changing system based on image analysis according to claim 1, characterized in that: The image acquisition module (100) acquires image information of the preceding vehicle at different times during driving by means of a high-definition camera, and then removes noise from the acquired image information by means of a Gaussian filter method, thereby improving image quality.

3. The intelligent driving lane changing system based on image analysis according to claim 2 is characterized in that: The analysis module (200) comprises a recognition unit and a distance measurement unit; The recognition unit uses a deep learning algorithm to recognize an object in an image acquired by the image acquisition module (100); The distance measuring unit calculates the distance and relative position between the vehicle and surrounding objects through triangulation according to the results of object recognition and lane line detection in the recognition unit.

4. The intelligent driving lane changing system based on image analysis according to claim 3 is characterized in that: The triangulation method is used to calculate the distance and relative position of the vehicle and surrounding objects as follows: , where d represents the distance between the vehicle and the object; b represents the baseline length of the camera, that is, the horizontal distance between the two cameras; h represents the focal length of the camera; and x represents the parallax of the object in the image, that is, the horizontal position difference of the object in the two camera images.

5. The intelligent driving lane changing system based on image analysis according to claim 3 is characterized in that: The judgment module (300) comprises an image annotation unit and a model judgment unit; The image annotation unit is used to collect image data of the vehicle in different scenarios, annotate the image data in different scenarios, clarify the driving requirements corresponding to the different image data, the driving requirements include driving with lane change and driving without lane change, and divide the data of the standard number into a training set, a verification set and a test set; The model judgment unit is used to establish a judgment model, train the model through a standard training set, enable the judgment model to automatically make lane change judgments on input image information, and regularly optimize and update the judgment model to adapt to different road conditions and driving environments.

6. The intelligent driving lane changing system based on image analysis according to claim 5 is characterized in that: The judgment module (300) further comprises a deviation setting unit, wherein the deviation unit is used to obtain lane change judgment information in the model judgment unit, keep the vehicle's driving speed unchanged so that the vehicle deviates from the lane by a certain distance during the following process, set a timing threshold, and judge whether the vehicle needs to change lanes within the timing threshold through the judgment model in the model judgment unit. If lane change is required, send information to the automatic lane change module (400).

7. The intelligent driving lane changing system based on image analysis according to claim 6, characterized in that: The automatic lane changing module (400) comprises a control unit and a position detection unit; The control unit is used to receive the lane change judgment information in the model judgment unit, and if the vehicle needs to change lanes, control the vehicle to drive to the adjacent lane; if the vehicle does not need to change lanes, the vehicle continues to drive normally in the driving lane; The position detection unit is used to detect the position and offset of the vehicle in the target lane after the vehicle changes lanes, so as to ensure that the vehicle travels in the center of the lane.

8. The intelligent driving lane changing system based on image analysis according to claim 7 is characterized in that: The vehicle in the control unit performs automatic lane change and performs multiple safety checks during the automatic lane change process, including but not limited to ensuring that the target lane is idle and free of potential dangers, and continuously monitoring the vehicle status and surrounding environment changes during the lane change process, and being ready to take emergency braking and other measures at any time.

9. The intelligent driving lane changing system based on image analysis according to claim 7, characterized in that: The position detection unit detects the position and offset of the vehicle in the target lane, including the following steps: Data collection and monitoring: Utilize sensors on the vehicle to continuously collect data, including but not limited to camera images, wheel speed sensor data, and steering angle sensor data; Position and offset determination: Process the images captured by the camera to identify the lane lines of the target lane; Adjustment strategy formulation: formulate corresponding adjustment strategies based on the determined position and offset; Execute adjustment actions: Convert the formulated steering adjustment strategy into specific steering instructions, send them to the vehicle's steering system, and adjust the vehicle's speed appropriately according to the vehicle's position and driving status in the target lane.

Images