206 results about "Lane detection" patented technology

A method includes obtaining, by a processing device, input data derived from a set of sensors of an autonomous vehicle (AV), generating, by the processing device using a set of lane detection classifier heads, at least one heatmap based on a fused bird's eye view (BEV) feature generated from the input data, obtaining, by the processing device, a set of polylines using the at least one heatmap, wherein each polyline of the set of polylines corresponds to a respective track of a first set of tracks for a first frame, and generating, by the processing device, a second set of tracks for a second frame after the first frame by using a statistical filter based on a set of extrapolated tracks for the second frame and a set of track measurements for the second frame, wherein each track measurement of the set of track measurements corresponds to a respective updated polyline obtained for the second frame.

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.

This disclosure relates to automatic lane and and / or terrain detection and recognition under various ambient and driving conditions for robotic / vehicular control purposes / applications. In one aspect, a rule-based detection system is configured to perform lane recognition using optical images. Various edge detection thresholds are adaptively tuned from frame to frame using a feedback signal derived from a fuzzy logic inference mechanism. Such detection techniques may also be adapted for drivable region detection, which may be fused together with drivable region detection based on LiDAR cloud point. Such detection techniques may be further adapted for a preprocessing of optical images of road to generate preprocessed images that may then be processed by learning-based lane detection models. In another aspect, an intelligent terrain classification system may be configured to include a fusion of both a vision-based terrain classification convolutional neural network (CNN) and a parallel proprioception-based terrain classification CNN. These CNNs may be configured to process a small number of selected set of proprioceptive signals and to adaptively detect / classify the terrain as platform-independent as possible.

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 is an autonomous driving control apparatus which includes a sensor device, a memory, and a controller. For example, the autonomous driving control apparatus may determine at least one lane detection result regarding a lane in which a host vehicle is traveling, using at least one of a first sensor included in a sensor device or a second sensor included in the sensor device, or any combination thereof, generate at least one driving route, based on the at least one lane detection result, and determine a final driving route for autonomous driving of the host vehicle, based on the at least one driving route.

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.

The invention discloses a video lane line detection method and system based on instance feature guidance, and the method comprises the steps: constructing a video lane line detection network which comprises a backbone network, a neck network, and a line anchor feature interaction fusion module; the backbone network and the neck network form two multi-level feature extraction branch networks sharing weights; obtaining a current frame image and a reference frame image, and respectively sending the two images into the two multi-level feature extraction branch networks to obtain multi-level image features of the two images; initializing line anchors distributed on the images, sending the line anchors and multi-level image features of the two images into a line anchor feature interaction fusion module, and gradually refining the positions of the line anchors from a high level to a low level to obtain a lane detection result; and training and optimizing the constructed video lane line detection network to obtain an optimal video lane line detection network for lane detection. Under the condition of a difficult scene, time sequence information contained in a video can be fully utilized, lane line instance features in a reference frame are combined to serve as supplement and prompt, a complete lane line instance can be effectively reasoned, detection of a current frame is assisted, and the accuracy and robustness of a model are improved.

The invention discloses a map topological relation reasoning method fused with an SD map, and belongs to the technical field of three-dimensional reconstruction. The method comprises the following steps: acquiring an SD map and carrying out vectorization processing to obtain an SD map broken line sequence; encoding the SD map broken line sequence to obtain SD map features; adjusting the 3D lane coordinates by using the SD map position codes to obtain lane position embedding; and carrying out inter-lane topological relation reasoning by fusing the SD map features and the 3D lane features. According to the method, 3D lane coordinates and SD map position codes are combined to generate lane position embedding, in the process, initialization of a topological relation is assisted by the SD map, and lane geometric information provided by the SD map is effectively fused in a topological reasoning stage; the method not only considers the inherent geometrical characteristics of the lane, but also significantly reduces the influence of the inherent endpoint shift on the topological relation in the lane detection.

The invention provides a lane detection method. Comprising the steps of obtaining laser radar point cloud data of a vehicle, performing feature extraction based on the laser radar point cloud data to obtain a feature sequence, performing feature embedding by using a Transform model based on the feature sequence, initializing a generated lane query model by using the encoded point cloud feature sequence, and performing lane query based on the initialized lane query model. Inputting the lane query features and the lane features into a multi-layer perceptron for lane detection to obtain a lane detection result, wherein the lane query features are obtained through the initialized generated lane query model; the lane features are obtained by inputting the encoded point cloud feature sequence and the lane query features into a Transform model decoder. Through the combination of the three-dimensional sparse convolutional network and the Transform model, the rapid and accurate feature extraction of the point cloud data is realized, then the lane detection is performed by using the multilayer perceptron, the information of the input features is fully utilized, and the lane detection precision is improved.

A method includes obtaining, by a processing device, input data derived from a set of sensors of an autonomous vehicle (AV), generating, by the processing device, at least one heat map based on fused bird's-eye view (BEV) features generated from the input data using a set of lane detection classifier heads, obtaining, by the processing device, a set of fold lines using the at least one heat map, wherein each fold line of the set of fold lines corresponds to a respective trajectory of the first set of trajectories of the first frame, and generating, by the processing device, a second set of trajectories of a second frame following the first frame based on a set of extrapolated trajectories of the second frame and a set of trajectory measurements of the second frame by using a statistical filter, wherein each trajectory measurement of the set of trajectory measurements corresponds to a respective updated fold line obtained for the second frame.

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.