57 results about "Lane detection" patented technology

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.

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.

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 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.

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.

According to an embodiment of the present disclosure, a signal processing device and a vehicle control device including same comprise a processor for receiving a front image from a camera mounted in a vehicle and processing same, wherein the processor: performs lane detection on the basis of the front image from the camera; executes a lane keeping mode on the basis of the lane detection; according to a first mode during the lane keeping mode, controls a steering driving unit to maintain a first distance from a first lane among the first lane and a second lane adjacent to each other; and according to a second mode during the lane keeping mode, controls the steering driving unit to maintain a second distance from the first lane, the second distance differing from the first distance. Accordingly, a lane distance can be adaptively adjusted by applying a driving situation during operation of the lane keeping mode.

A vehicle driving support device includes a surrounding environment recognition unit, a travel control unit, and a collision avoidance controller. The collision avoidance controller is configured to estimate a position of a vehicle and generate a forecast traveling path thereof when turning across an opposite lane at an intersection, recognize an oncoming vehicle traveling on each of lanes of the opposite lane, based on surrounding environment information acquired by the surrounding environment recognition unit, detect, for each lane, a collision forecast position at which the forecast traveling path intersects with a traveling path of the oncoming vehicle, and forecast a collision of the vehicle with the oncoming vehicle, determine whether to execute collision avoidance control in which the travel control unit operates a brake driver, for the collision forecast position, and dispose the collision avoidance control at a collision avoidance position on the forecast traveling path.

The invention provides a lane detection method and system based on image quality dynamic control, and relates to the technical field of computer vision, and the method comprises the steps: carrying out the Canny edge processing of a current video frame, and obtaining a current edge processing image; calculating the intersection-to-union ratio and the Love ratio of the current edge processing image and the historical edge processing image; if the Love ratio is greater than a set threshold value within continuous preset duration or a preset frame number and the intersection-to-union ratio is continuously greater than a first threshold value, judging that the picture of the current video frame is in an abnormal static state due to abnormal image quality, and pausing to output the lane detection result; and if the radio ratio is less than or equal to a set threshold value within continuous preset duration or a preset frame number, or the intersection-parallel ratio is continuously less than or equal to a first threshold value, outputting a lane detection result. Therefore, when mosaic, lagging, abnormal static and other quality problems occur in the video stream, the lane detection result output strategy can be adjusted in time, false alarms are avoided, and the real-time performance and the deployment convenience are considered at the same time.

The invention relates to a method for detecting deviations in the lane detection of a vehicle's lane (50), wherein boundary information (10) describing the detected lane boundaries (31l, 31r) is obtained, wherein the obtained boundary information (10) is i) supplied as input data to a trained machine learning model (4), wherein the trained machine learning model (4) is trained to detect an error in lane detection based on at least the boundary information (10), and / or ii) supplied as input data to a rule-based detection system (5), wherein the rule-based detection system (5) is configured to detect an error in lane detection based on at least the boundary information (10); wherein a signal (20) is generated and provided based on the detection.Furthermore, the invention relates to a device (1) for detecting deviations in the lane detection of a vehicle lane (50).

This invention discloses a definition and online monitoring method and system for the operational design domain (ODD) of autonomous driving. Taking lane keeping function as an example, the method includes: acquiring an observation dataset; establishing a structural causal graph (OCD) between the lane detection accuracy of the autonomous driving system and the elements of the operational design domain based on the observation dataset; fitting the causal transmission path (i.e., structural causal equation) of the ODD based on the observed samples; acquiring various combinations of operating environments based on the operating parameter space of the autonomous vehicle; applying the acquired structural equation to perform counterfactual inference on the autonomous driving performance (taking lane detection accuracy as an example) under various combinations of operating environments; selecting an environment combination whose counterfactual calculation result is greater than a threshold to characterize the designed operational domain; if the lane detection accuracy in the autonomous driving performance indicators is consistently less than a set threshold, activating a function degradation strategy or prompting the driver to take over. This invention effectively improves the safety of autonomous vehicles through ODD online monitoring.

The application discloses a kind of deep learning blind path detection algorithm based on multi-scale feature fusion, comprising the following steps: collecting blind path data and marking, collecting multi-scale features, fusion model architecture design, creating blind path identification model, extracting blind path model key area features, enhancing the blind path edge features of feature extraction network, training the blind path identification model of key feature area, reconstructing blind path identification model, optimizing and post-processing the reconstructed model, verifying and evaluating experimental results;The application collects and marks multiple sources of data, strengthens the generalization ability of the model, covers diverse scenarios in data collection, fully simulates the actual use environment, collects different dimensions in layers, ensures data richness and diversity, uses the way of combining pixel-by-pixel segmentation and bounding box detection in the marking link, ensures balanced data distribution, so that the model can still maintain stable detection performance in complex environment, significantly enhances the generalization ability.

This application provides a lane detection method, apparatus, electronic device, storage medium, and program product, relating to the interdisciplinary fields of intelligent driving and computer vision. The method includes: inputting an image to be detected into a lane detection model to obtain a predicted lane and its left lane line, right lane line, and center line; the lane detection model is trained using images annotated with combinations of the left lane line, right lane line, and center line of the same lane as training samples, and using geometric constraints between lane lines and / or morphological constraints of lane lines as loss functions. The method provided in this application annotates the left lane line, right lane line, and center line of the same lane in the training samples as combinations, achieving an accurate representation of the overall spatial structure of the lane; using geometric constraints between lane lines and morphological constraints of lane lines as loss functions enables the model to perceive the rationality of the lane's geometric structure; thus improving the accuracy of lane detection.

The invention provides a lane detection method, system and device and a medium, and the method comprises the steps: predicting the height probability distribution of each pixel in roadside image data from a ground reference height to obtain road curved surface data, and accurately describing a real road structure; by randomly adding disturbance in an external parameter matrix and suppressing height probability distribution of a non-road area, the influence of external parameters of shooting equipment on three-dimensional lane reconstruction can be reduced, and stable and accurate road curved surface data can be generated; the characteristics of different types of lane data sets are progressively utilized in a staged mode, hierarchical optimization from geometric perception to semantic understanding is achieved, the problem that a shooting device is unclear in a long-distance lane structure can be solved, and lane semantic segmentation data are accurately generated; by combining road curved surface data and lane semantic segmentation data, high-precision detection and reconstruction of three-dimensional lane lines can be carried out on roadside image data collected by shooting equipment of roadside facilities.

The present invention relates to a method for providing an automatic labeling assistance service, comprising: a) when an annotation terminal obtains an automatic labeling assistance service request information, a server provides a labeling interface to the annotation terminal, enabling the annotator to select a specific lane detection model suitable for the target image from the first lane detection model to the nth lane detection model by referring to at least one lane detection result from the first lane detection result to the nth lane detection result through the labeling interface displayed in the annotation terminal; and b) when the annotator obtains the first point information to the kth point information on the specific lane through the labeling interface, the server causes a semi-automatic labeling module to generate a first spline model by referring to at least a portion of the first point information to the kth point information obtained from the labeling interface and the segmentation map and clustering map corresponding to the specific lane detection result of the specific lane detection model, and displays it through the labeling interface to provide an automatic labeling assistance service.

A vehicle driving control system including a vehicle detector to detect a target vehicle and calculate position information and movement information on the target vehicle, a lane detector to recognize a lane in which a subject vehicle is traveling and to calculate lane information on the lane, and a determiner to determine cut-in or cut-out of the target vehicle based on relative movement between the subject vehicle and the target vehicle in a horizontal direction or change in a length of the lane.

This invention discloses a method for dynamic control of virtual lane lines for intelligent vehicle-road interaction, relating to the field of lane line dynamic adjustment technology. The method includes: obtaining pavement deflection data for each lane of a target road segment using a non-destructive lane detection method, and calculating the relative damage index for each lateral position of each lane; establishing a load distribution model to calculate the load pressure exerted by traffic flow on each point of the pavement; establishing an overall damage risk model after virtual centerline offset, and solving for the optimal overall offset; determining the final virtual centerline position of each lane based on the optimal offset, and propagating the optimized lanes to intelligent driving vehicles in the target road segment; and actively and dynamically allocating traffic loads from structurally weak areas to robust areas.

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.

Lane detection system (10) with - an optical lane detection system (12) and - a GNSS-based position detector (14), wherein - the GNSS-based position detector (14) is designed to determine information on a lane path from digital map data (16) depending on a detected position, a known position detection accuracy (44) and known accuracy limits (42) of the digital map data and to transmit data on the determined lane path to the optical lane detector, and wherein - the optical lane detection device (12) is configured to take into account the data on the determined lane course from the position detection device during lane detection, characterized in that the GNSS-based position detection device (14) is further configured to - depending on the detected position, information on the lane course can be determined from the digital map data (16), - to compare the determined lane path with the known position detection accuracy (44) and the known accuracy limits (42) of the digital map data, and - to transmit data on the determined lane path to the optical lane detector (12) if the determined lane path remains unchanged during a distance that is greater than the sum of the position detection accuracy (44) and the known accuracy limits (42) of the digital map data.

This document provides a method and server for providing an auto-labeling support service for generating training data. [Solution] The method includes S120, in which the server causes the labeler to select a specific lane detection model suitable for a target image through a labeling interface displayed on the labeler terminal, and S130, in which, once first point information to the k-th point information (where k is an integer of 2 or more) on the specific lane selected by the labeler to label the specific lane among at least one lane located in the target image is obtained through the labeling interface, the server generates a first spline model having m spline points (where m is an integer of 2 or more) corresponding to the specific lane in the target image and displays it through the labeling interface, thereby providing an auto-labeling assistance service.

A driver monitoring system for a vehicle includes a communication module, and at least one imager module in operable communication with to the communication module that is configured to capture a lane position of the associated vehicle and a driver's behavior. A processor receives the captured lane position and the captured driver's location from the at least one imager module. A memory includes instructions that, when executed by the processor, cause the processor to monitor the captured lane position and the captured driver's behavior for a sign of low alertness of the driver and generate an alert with the communications module upon detecting the sign of low alertness.

A vehicle speed control device, a vehicle speed control method, and a computer program for vehicle speed control are provided. The vehicle speed control device includes: a lane detection unit (31) that detects the vehicle's own lane while the vehicle (10) is traveling; a curvature estimation unit (32) that detects the starting point of a road section within a predetermined distance ahead of the vehicle (10) that is a curve, and estimates the curvature of the vehicle's own lane in the road section; a determination unit (33) that determines whether the vehicle's own lane is a high-speed lane or a low-speed lane; a reference speed setting unit (34) that sets a reference speed in such a way that the greater the curvature of the vehicle's own lane, the lower the reference speed of the vehicle (10), and the reference speed when the vehicle's own lane is a high-speed lane is higher than the reference speed when the vehicle's own lane is a low-speed lane; and a control unit (35) that controls the vehicle's speed so that the vehicle's speed when the vehicle reaches the starting point of the aforementioned road section is below the reference speed.

The invention discloses a branch and confluence lane detection method and device. The method comprises the following steps: acquiring candidate branch and confluence lane data; obtaining an enhanced feature map of a road geometric identifier in the candidate branch and confluence lane data according to feature coding processing of the candidate branch and confluence lane data, and obtaining position coding data of the road geometric identifier according to position information of the road geometric identifier in the candidate branch and confluence lane data; performing prior query coding processing on the position coding data to obtain a prior fixed reference point and prior position coding data in prior query; and according to the priori fixed reference point, the priori position coding data and the enhanced feature map, determining whether the candidate branch and confluence lane data belongs to the branch and confluence lane. Therefore, the anti-noise capability of diversion and convergence lane detection can be improved.

This application discloses a lane line detection method, apparatus, electronic device, and storage medium. The method is applied to an in-vehicle terminal and includes: acquiring an environmental image of the vehicle; performing edge feature point recognition on the environmental image to obtain edge feature points of each lane marker contained in the environmental image, the edge feature points including multiple first edge feature points and multiple second edge feature points; pairing the multiple first edge feature points and multiple second edge feature points to obtain multiple target feature point pairing groups corresponding to each lane marker; selecting the lane marker closest to the vehicle as the target lane line based on the multiple target feature point pairing groups corresponding to each lane marker; and fitting the target lane line according to the multiple target feature point pairing groups corresponding to the target lane line to obtain the fitting result corresponding to the target lane line. Implementing this application embodiment can improve the accuracy of lane line detection.

To achieve simple restoration of automatic calibration.SOLUTION: A calculation device according to an embodiment includes a controller having a function of restoring automatic calibration of an in-vehicle camera. When receiving an error notification of the auto calibration executed based on a detection result of a lane from an image captured by the in-vehicle camera during traveling of a vehicle, the controller determines a point where a recognition degree in image recognition of the lane is high based on operation record data of the vehicle, and calculates a reference position for the auto calibration from an image captured by the in-vehicle camera at the point where the recognition degree is high, when a degree of divergence between the calculated reference position and an existing value that is a value being set for the reference position is equal to or greater than a threshold value, the existing value is updated with the calculated reference position.SELECTED DRAWING: Figure 6

A method for providing auto labeling assistance service is disclosed. The method includes steps of: (a) providing a labeling interface to the labeler terminal, to thereby allow a labeler to select a specific lane detection model suitable for a target image among a first lane detection model to an n-th lane detection model by referring to at least one lane detection result among a first lane detection result to an n-th lane detection result, by the labeling interface displayed on the labeler terminal; and (b) in response to acquiring first point information to k-th point information on a specific lane selected to label the specific lane among lanes located in the target image, allowing a semi-auto labeling module to generate a first spline model having m spline points corresponding to the specific lane and to display the first spline model, to thereby provide the auto labeling assistance service.

A vehicle control method for causing an own vehicle to stop in a way that an interval between the own vehicle and a preceding vehicle coincides with a predetermined target distance includes: determining whether or not there is a crossing within a predetermined distance from the own vehicle ahead of the own vehicle and a traveling road on which the own vehicle travels includes a target lane in which a vehicle travels in the same direction as the own vehicle and an opposite lane; detecting a leading vehicle in the target lane in a section up to the crossing as a target vehicle and determining whether or not the own vehicle is a following vehicle positioned immediately behind the target vehicle; and when the own vehicle is a following vehicle, setting the target distance longer than the target distance when the own vehicle is not a following vehicle.

An end-to-end lane detection uncertainty prediction system that includes the following: a sensor device for a carrier vehicle that can be operated on a road surface within a driving environment including lane markings, wherein the sensor device is operable to generate data relating to the road surface within the driving environment; a navigation control system that includes a computer-based processor capable of being operated for: Monitoring the data, including an input image from the sensor device; Using a convolutional neural network to analyze the input image and output a lane prediction and a lane uncertainty prediction; and Generating a commanded navigation display based on lane prediction and lane uncertainty prediction; and a vehicle control system that controls the carrier vehicle based on the commanded navigation display; the neural convolutional network is initially configured using an association and The training focuses on error calculation per point, with the association and error calculation per point including the following: First, mapping a selected basic truth track to a selected set of data points that are related to a predicted track, and Secondly, mapping at least one point of the selected basic truth track to a corresponding data point from the selected set of data points relating to the predicted track.