172 results about "Lane detection" patented technology

The invention relates to an adaptive lane detection method based on curvature and edge perception optimization, and belongs to the technical field of automatic driving. According to the method, the adaptability of various scenes is enhanced by introducing an adaptive weight mechanism, complex geometric features are captured by fusing Kolmogorov-Arnold Networks (KAN) convolution, and complex lane shapes and edge details are better processed by combining curvature constraint loss and edge detection loss. Through a series of improvements, good balance between the speed and the detection precision is realized, so that the lane line detection system can efficiently and stably operate in an automatic driving environment with limited resources. In order to verify the effectiveness of the proposed method, wide experiments are performed on a CULane data set. Experimental results show that the F1-score of the KAN-Lane in the curve and shielding scenes is 82.08% and 75.44% respectively, the detection precision and stability are remarkably improved, the method is superior to mainstream algorithms such as CLRNet and the like, and the efficient detection speed is kept. The KAN-Lane provides a more reliable lane detection scheme for automatic driving.

The embodiment of the invention provides an automatic driving map-oriented lane detection method, electronic equipment and a storage medium, and the method comprises the steps: obtaining an original all-round view image collected by a target vehicle in a driving process, carrying out the preprocessing, inputting the preprocessed original all-round view image into a pre-training residual network, and outputting a to-be-detected feature map; inputting the to-be-detected feature map into a pre-trained spatial-temporal feature network model, outputting spatial grid features, and randomly initializing a preset number of query features; determining decoded query features according to the query features and the spatial grid features; and inputting the decoded query features into a pre-trained lane detection network model to obtain the number of lanes of the target vehicle in the driving direction road section and the coordinates of the lane center lines of all lanes. According to the invention, through feature processing and structural information analysis, the lane detection result is rapidly and accurately obtained, and the stability of lane detection is improved.

The invention discloses a lane line detection and correction method based on a millimeter-wave radar, relates to the technical field of road traffic, and aims at the data characteristics of sparse point cloud data, large noise interference and difficulty in accurate lane recognition of the millimeter-wave radar, the quality of lane point cloud is improved by adopting a DBSCAN clustering method based on two dimensions of space and time, and the accuracy of lane line detection and correction is improved. The ICP algorithm is used for matching the point cloud number of the reference lane, the conversion matrix is accurately calculated, lane correction is achieved, then the lane shape is fitted through the principal component analysis method, smoothness and stability are enhanced, and therefore the smooth and stable lane line can be obtained through fitting of the point cloud data of the millimeter wave radar. The method can stably operate in different environments, has the advantages of high stability, high robustness, automation and low cost, can be suitable for multi-lane detection, complex traffic scenes and intelligent traffic systems, and provides a more reliable lane correction scheme for automatic driving.

Disclosed are methods, devices, and computer-readable media for detecting lanes and objects in image frames of a monocular camera. In one embodiment, a method is disclosed comprising receiving a sample set of image frames; detecting a plurality of markers in the sample set of image frames using a convolutional neural network (CNN); fitting lines based on the plurality of markers; detecting a plurality of vanishing points based on the lines; identifying a best fitting horizon for the sample set of image frames via a RANSAC algorithm; computing an inverse perspective mapping (IPM) based on the best fitting horizon; and computing a lane width estimate based on the sample set of image frames using the IPM in a rectified view and the parallel line fitting.

The invention provides a multi-modal fusion road topology reasoning method and system, and the method comprises the steps: converting an extracted lane mask into a semantic seed point in a historical point cloud, and carrying out the pseudo-label setting based on the semantic seed point. And performing model training based on the historical image with the pseudo tag and the historical point cloud to obtain a lane detection model. Obtaining lane line information from the real-time image and the real-time point cloud by using a lane detection model, mapping the lane line information to a bird's-eye view feature map, calculating a topological relation between lane lines based on the lane line information in the bird's-eye view feature map, obtaining a topological reasoning matrix, and obtaining a topological reasoning result; and obtaining a corresponding road topology reasoning result based on the graph neural network according to the topology reasoning matrix. According to the scheme, on the basis of a pseudo label generation mechanism, dependence on manual marking is reduced, data preparation cost is reduced, effective fusion of a lane line representation method based on bird's-eye view space unified mapping and lane topology reasoning is introduced, and a lane topology reasoning result with high precision and good topology consistency can be obtained.

Disclosed herein are methods and system of implementing an AI-enabled high-fidelity occupancy network, allowing for the prediction of signed distances of voxelized objects in a 3D space surrounding an ego, thereby facilitating enhanced object shape refinement. Through the utilization of camera feeds only, an AI model accurately calculates signed distance values for various voxels in the 3D space. The predicted values can also be rendered by translating signed distance field values into image layers and subsequently stacking the layers to form a 3D representation of the space surrounding the ego. Furthermore, the system can predict and display various ground markings, expanding its functionality beyond traditional lane detection.

Provided are methods, systems, and computer program products for lane keep tracking and / or localization of a vehicle using a radar to detect metallic particles in paint applied to lane markings or curb markings. An example method may include: causing a radar system of a vehicle to output radio waves; receiving a radar image from the radar system corresponding to returned radio waves; determining a portion of the radar image includes lane or curb markings, wherein the lane or curb markings are embedded with metallic particles; and determining a location of the vehicle based at least in part on the determined portion of the radar image that includes the lane or curb markings.

A vehicle, and a system and method of navigating the vehicle. The system includes a camera and a processor. The camera obtains an image of a road upon which the vehicle is moving. The processor is configured to extract a feature of the road from the image, perform a lane detection algorithm to detect a set of lane markers in the road using the image and the feature, and move the vehicle along the road by tracking the set of lane markers.

A computer system obtains a road image captured by a vehicle. The computer system determines whether the road image is ambiguous for lane marker classification. When the computer system determines that the road image is ambiguous for lane marker classification, the computer system generates a labeled road image and adds the labeled road image to a corpus of training data for training a model to generate an autonomous driving model. The computer system distributes the autonomous driving model to one or more vehicles. The autonomous driving model is configured to process road images captured by the one or more vehicles to facilitate at least partially autonomously driving the one or more vehicles.

This invention proposes a method, device, equipment, and medium for vehicle lane keeping and lane changing control. It detects lane lines in the road image directly in front of a target vehicle using an existing lane detection model; determines pixel reference points in the road image based on the target vehicle's speed; uses a greedy algorithm to iterate and filter the pixel groups corresponding to each lane line to find the pixels closest to the pixel reference points, obtaining the nearest pixel group; sorts the pixels in the nearest pixel group; calculates the average of adjacent nearest pixels based on the sorting result to determine the lane center pixel; and controls the target vehicle's lane keeping or lane changing based on the determined lane center pixel. This reduces the computational resource requirements of the lane keeping system and improves the system's real-time performance and stability.

The invention discloses a lane detection model post-training quantification method and device based on semantic sensitivity. The post-training quantification method for the lane detection model comprises the following steps: firstly, collecting an unlabeled training data set of the lane detection model; secondly, simulating and calculating semantic sensitivities of different semantic output heads in the same lane detection model by utilizing the lane deformation score and the noise level; based on the semantic sensitivities of the different semantic output heads, dynamically adjusting the weight coefficients of the different semantic output heads in a post-training quantization process, and performing post-training quantization through a region sensitivity loss function until the lane detection model converges; and finally, deploying the lane detection model after post-training quantization, and converting the weight of analog quantization into a fixed point number so as to reduce required computing resources and storage space.

The present invention relates to a method for training artificial neural network configured for 3D lane detection based on unlabelled image data from camera. The method includes generating a first set of 3D lane boundaries in first coordinate system based on first image, generating a second set of 3D lane boundaries in second coordinate system based on second image, transforming at least one of the second set of 3D lane boundaries and first set of 3D lane boundaries based on positional data associated with first image and second image, evaluating the first set of 3D lane boundaries against second set of 3D lane boundaries in common coordinate system in order to find matching lane pairs of first set of 3D lane boundaries and second set of 3D lane boundaries, and updating one or more model parameters of an artificial neural network based on a spatio-temporal consistency loss.

The invention discloses an urban road multi-device dynamic collaborative patrol method. The method comprises the following steps: S1, identifying road surface damage characteristics through a wide-area sensing layer and generating an event trigger signal; s2, analyzing the event trigger signal in real time through a digital intelligent decision-making layer, and generating a scheduling instruction including position coordinates and damage types; s3, the dynamic execution layer executes motor vehicle lane detection and driving vibration characteristics according to the scheduling instruction and executes sidewalk detection according to the scheduling instruction; s4, carrying out time domain-space domain correlation analysis on the image features and the vibration waveforms through a digital intelligent decision-making layer, and generating a detection result; and S5, the intelligent decision-making layer adjusts patrol paths and working parameters of the devices according to detection results of the terminals to form closed-loop feedback. According to the invention, the road patrol efficiency and quality are greatly improved, the optimal configuration of resources is realized, and the road quality problem can be found and solved more timely and comprehensively.

Disclosed herein are methods and system of implementing an AI-enabled high-fidelity occupancy network, allowing for the prediction of signed distances of voxelized objects in a 3D space surrounding an ego, thereby facilitating enhanced object shape refinement. Through the utilization of camera feeds only, an AI model accurately calculates signed distance values for various voxels in the 3D space. The predicted values can also be rendered by translating signed distance field values into image layers and subsequently stacking the layers to form a 3D representation of the space surrounding the ego. Furthermore, the system can predict and display various ground markings, expanding its functionality beyond traditional lane detection.

The invention discloses a space-time adaptive video lane line detection method based on differential memory and wavelet guidance, and mainly solves the problems of difficulty in collaborative modeling of space-time characteristics, easy loss of shallow geometric details and insufficient utilization of deep time sequence information in a dynamic scene in the prior art. According to the implementation scheme, the method comprises the following steps: acquiring marked video sequence data from a public video lane line detection data set, preprocessing the marked video sequence data, and dividing the preprocessed video sequence data into a training set and a test set; constructing a video lane line detection network comprising a feature extraction unit, a differential memory time sequence alignment unit, a wavelet-guided direction perception feature enhancement unit, a space-time adaptive fusion unit and a feature decoding unit; iteratively training the video lane line detection network through back propagation by using the training set; and inputting the test set into the trained video lane line detection network, and outputting a lane line. According to the method, the detection precision and robustness in challenging environments such as shielding, strong light and motion blur are remarkably improved, and the method can be used for realizing accurate extraction and stable tracking of lane lines in a dynamic driving scene.

Method (500) for detecting a lane (82) for lateral guidance of a vehicle (100), the lateral guidance of the vehicle (100) based on a road model (412), the method (500) comprising: Determine (504) of one or more characteristics (404), wherein one or several features (404) are suitable to influence the detection of the lane (82); and Detection (506) of a lane (82) based on a sensor system (406) of the vehicle (100); characterized in that the method further comprises: Determining a weighting of one or more elements (408; 86, 88) of the lane (82) detected by the sensors (406) of the vehicle (100); and Determining (508) the road model (412) based on the recorded lane (82), on the determined one or more features (404) and on the determined weighting.

The invention relates to the field of automatic driving, and particularly discloses a lane line detection method based on time sequence curvature and multi-scale context. The method comprises the following specific implementation steps of: giving a data set image and preprocessing the data set image; lane features of an image are extracted through a backbone network, a multi-scale feature map is generated, and the multi-scale feature map is continuously processed by a double-branch detection framework. According to the framework, two parallel branches of time sequence modeling and attention enhancement are fused, firstly, a feature map is sent into a multi-scale attention branch, multi-scale channels and spatial features are fused, and semantic information is enriched; and meanwhile, the time sequence optimization branch captures prior knowledge by using time sequence information, extracts context information and models curvature change. And finally, carrying out weighted fusion on the output features of the two branches and the original trunk features, processing and refining lane prediction through a loss function, and outputting a final result. According to the method, the problems that visual clues of lane lines are lacked in a complex scene and a long-distance dependency relationship is difficult to model in a curve scene are effectively solved, and the robustness and accuracy of the model are enhanced.

A Real-Time Traffic Flow Indicator device for vehicles, comprising an advanced sensor assembly with Time-of-Flight cameras, LIDAR, and FMCW radar to capture surrounding data, including lane markings, vehicle positions, speeds, and distances. Edge-based lane detection algorithms employing CNNs detect lane boundaries, while real-time traffic analysis algorithms utilizing sensor fusion assess traffic conditions. Color-coded light indicators on rear and front displays represent specific traffic scenarios, and a V2V communication module enables bidirectional transmission of lane-specific traffic information. An Intelligent Data Processing Algorithm processes integrated sensor and V2V data to assess traffic conditions, communicating assessments and hazards through an LCD interface and FPGA-powered safety alert subsystem. The device also detects emergency vehicles using machine vision, activating LED indicators to alert the driver.

A system for controlling a vehicle includes a positioning sensor, an obstacle detection sensor, a lane detection sensor, and a smart cruise control system configured to control steering, braking, and acceleration of the vehicle, based on readings from the sensors, to follow a recorded route. The system also includes a processor configured to, with the sensors, record a route while a driver is controlling the vehicle. The processor is also configured to receive a first user input to follow the recorded route; for a first complexity of a roadway on which the vehicle is traveling, activate the smart cruise control system to follow the recorded route; and for a second complexity of the roadway: deactivate the smart cruise control system; control the braking of the vehicle; receive a second user input; and upon receiving the second user input, activate the smart cruise control system to follow the recorded route.

The invention relates to a method for lane detection by a motor vehicle, wherein at least two trainable analysis units (NN1, NN2, NN3, NN4) are used to identify a lane in image data (12) acquired by the motor vehicle, each of the at least two analysis units (NN1, NN2, NN3, NN4) being trained with different sets of training data, each set of training data representing different environmental conditions (16). The invention further relates to a computer system (10), a computer program, and a machine-readable storage medium. The invention reduces the training effort required to train a lane detection system in a motor vehicle. Furthermore, the accuracy of the identification and modeling can be improved. Overall, the efficiency of lane detection can be enhanced.

This invention discloses a deep learning-based lane line detection method for low-light environments, comprising: acquiring the lane line dataset TuSimple and preprocessing it, dividing it into training and validation sets; training a lane line detection network using the training set, and selecting the optimal lane line detection network model using the validation set; acquiring the multi-exposure image dataset SCIE and using it to train a low-light enhancement network, selecting the optimal low-light enhancement network model; quantizing and deploying the lane line detection network model and the low-light enhancement network model; using the deployed low-light enhancement network model to enhance the illumination of the input image from an onboard front-facing camera to obtain an enhanced image; using the lane line detection network model to detect lane lines in the enhanced image, and outputting the detection results. This invention can detect lane lines more accurately and quickly in low-light environments, further improving the safety and reliability of autonomous driving.

This application provides a two-stage highway lane detection method and related equipment, belonging to the fields of computer vision and intelligent transportation technology. The method includes: a first stage, using a lane detection network to perform preliminary detection on the input image to obtain an initial set of lane lines; and a second stage, constructing a lane line topology refinement module. Using the initial lane lines as graph nodes, edge connections are constructed based on geometric attributes and visual features to form a lane line topology graph. Iterative message passing and feature aggregation are performed through a graph neural network to refine the initial detection results, enhancing the confidence and positioning accuracy of detected lane lines, and recovering missed lane lines based on topological relationship inference. This application can effectively improve the accuracy, completeness, and real-time performance of lane line detection in highway monitoring scenarios, and is suitable for lane-level fine-grained perception tasks in intelligent transportation systems.

This invention discloses a lane detection method combining super-resolution and knowledge distillation, comprising an image information acquisition module, an image preprocessing module, a lane detection module, and a model output postprocessing module. The image information acquisition module acquires image information in front of the vehicle using a camera. The image preprocessing module performs noise reduction on the image information transmitted from the image information acquisition module. The lane detection module performs semantic segmentation on the output of the image preprocessing module. The model output postprocessing module obtains lane information in the image based on the output of the lane detection module. While ensuring accuracy, this method effectively reduces computational load and can run on edge devices.

A vehicle control device and a vehicle control method, the vehicle control device comprising: a lane detection unit (31) for detecting a lane in which a vehicle (10) is traveling; a path setting unit (32) for setting a predetermined path for the vehicle (10) to travel along the detected lane; a detection unit (33) for detecting a lane dividing line dividing the lane in which the vehicle (10) is traveling and obstacles existing around the vehicle (10); a valid interval determination unit (34) for determining a valid interval in the predetermined path that is consistent with the detected lane dividing line; and a control unit (36) for controlling the behavior of the vehicle (10) in a manner to avoid a collision between the obstacle and the vehicle (10) when the position of the obstacle is included in the valid interval and the obstacle is located on the predetermined path.

The present invention discloses a lane line detection method based on a grid model of temporal information, comprising S1, obtaining sequential image frames of lane lines; S2, a data pre-storage stage; S3, a self-attention processing stage; S4, a memory extraction stage; S5, a decoding prediction stage; and S6, a prediction generation stage. The method achieves a network structure for memory generation and reading by combining self-attention, cross-attention, and multi-scale feature fusion. The present invention models the lane line detection problem as a classification problem by gridding the image, thereby reducing the amount of calculation and improving the calculation speed. The overall process of the model is divided into a current frame process and a historical frame process. The backbone of the model is the current frame process, and the historical process produces memory information for the current frame process to extract through a memory extraction module. The present invention reuses the features extracted from the image in the current frame process at previous moments in the historical frame process to avoid repeated calculations and further reduce the amount of calculation.

Vehicle display device (10) which displays a predetermined image in a display area (24, 25, 26) indicating a forward view of a vehicle (12), comprising: a memory (34); and a processor (30) connected to the memory (34), wherein the processor (30) is configured to: to identify a lane (70) on which the vehicle (12) is traveling; detect a position (O) of the vehicle (12) relative to the lane (70); based on the lane (70) and the position (O) of the vehicle (12) detected by the processor (30), determine whether there is a possibility that the vehicle (12) is deviating from the lane (70); and In a case where it has been determined that there is a possibility that the vehicle (12) may deviate from the lane (70), an image of a stereoscopic object (B) arranged along the lane (70) is to be displayed in the display area (24, 25, 26). characterized by the fact that the processor (30) is further configured to display the image of the stereoscopic object (B) in the display area (24, 25, 26) such that: the stereoscopic object (B) appears to move along the track (70) from a background side to a foreground side of the display area (24, 25, 26); and the stereoscopic object (B), whose movement has stopped at the foreground of the display area (24, 25, 26), appears to vibrate to simulate the movement of the vehicle (12) over a three-dimensional object such as a rumble strip, the image of the stereoscopic object (B) is caused to oscillate in a vertical, lateral or oblique direction, enabling the occupant to experience a realistic sensation as if the vehicle were vibrating as a result of driving over a rumble strip.

This specification provides a method for training a lane detection model. The method includes: determining lane line image samples and sample labels, wherein the sample labels are target lane lines in the lane line image samples; extracting features from the lane line image samples to obtain a first feature image and a second feature image; determining lane line clustering information and initial lane line key points based on the first feature image and the second feature image; performing clustering based on the lane line clustering information and the initial lane line key points to obtain predicted lane lines; and training a lane line detection model based on the predicted lane lines and the target lane lines. By integrating the clustering process of lane line key points into the entire lane line detection model training process, lane line key point clustering is performed simultaneously with network training, thereby improving the overall performance of the lane line detection model.

The present invention discloses a vehicle positioning method, device, equipment, storage medium and product, and relates to the field of vehicle positioning technology. The method includes: determining the local map determined based on the high-precision map corresponding to the original posture of the vehicle, determining the lateral distance between the vehicle and each map lane line in the local map and the lateral distance between the vehicle and each detected lane line in the lane detection result based on the original posture, determining the lane line polarity of each map lane line and the lane line polarity of each detected lane line according to the determined lateral distance, wherein the lane line polarity is used to characterize the lateral direction of the lane line located in the vehicle and the order of the lane lines in the lateral direction, matching the map lane line and the detected lane line corresponding to the lane line polarity to obtain target correction information, and correcting the original posture based on the target correction information to obtain the target posture of the vehicle. By adopting the above technical solution, the reliability of the positioning result can be improved.

A method for evaluating the running safety of a lane keeping assist driving function provided by the present invention performs multi-source data acquisition through multiple on-vehicle cameras as data acquisition devices, constructs a forward lane detection model and a front wheel crossing line classification model. Based on the data collected by the data acquisition device through the forward lane detection model, it judges the physical relationship between the front wheels of the vehicle to be evaluated and the lane lines. Through the front wheel crossing line classification model, it judges the types of the front wheels on both sides of the vehicle to be evaluated crossing the lane lines. From the two perspectives of the physical relationship between the front wheels of the vehicle and the lane lines and the types of the front wheels on both sides of the vehicle crossing the lane lines, it simultaneously judges the driving behavior of the vehicle to be evaluated, avoiding the occurrence of misjudgment problems, ensuring that the driving behavior of the vehicle can be accurately judged, and further ensuring the accuracy of the judgment on the recognition result of the lane assist driving system to the vehicle running safety risk behavior for the vehicle to be evaluated.