Systems and methods analyze a data set including a plurality of images. In one implementation, at least one processor receives a plurality of images acquired by one or more cameras associated with at least one vehicle; and analyzes the plurality of images using an active learning system configured to determine a relative priority ranking among the plurality of images. The relative priority ranking indicates an ordered sequence for the plurality of images, and is determined based on at least one indicator, determined for each of the plurality of images, of a complexity level and a diversity level associated with representations of one or more objects represented in the plurality of images. The at least one processor then outputs information indicating the relative priority ranking among the plurality of images.

A method of retrieving a map is disclosed. The method includes receiving a grid data of the map comprising lane segments, wherein the grid data includes an array of grids each associated with a list including none or at least one of the lane segments intersecting the respective grid; receiving coordinates of a location; identifying a first grid including the location based on the grid data; identifying a target grid that has an associated list including at least one of the lane segments as first lane segment; and outputting the first lane segment.

A vehicular vision system includes a camera disposed at and viewing exterior and rearward of a vehicle. The system, as the vehicle is driven forward along a traffic lane of a road, and responsive to processing of image data captured by the camera, determines a traffic lane marker rearward of the vehicle. The system, responsive to determining the traffic lane marker, determines a position of the vehicle within the traffic lane the vehicle is moving along. The system, responsive to determining the position of the vehicle within the traffic lane is within a threshold distance of a side of the traffic lane, alerts an occupant of the vehicle.

In some implementations, a device may receive an image that depicts an environment associated with a vehicle. The device may partition the image into a plurality of subsections. The device may analyze the plurality of subsections to determine respective subsection information, wherein subsection information, for an individual subsection, indicates: a probability score that the subsection includes a line segment associated with an object class, a position of a representative point of the line segment, and a direction of the line segment. The device may identify, based on the respective subsection information of the plurality of subsections, a line associated with the object class that is associated with a set of subsections of the plurality of subsections. The device may perform one or more actions based on identifying the line associated with the object class.

Provided are systems and methods for auto calibrating a vehicle using a calibration target that is generated from the vehicle's sensor data. In one example, the method may include receiving sensor data associated with a road captured by one or more sensors of a vehicle, identifying lane line data points within the sensor data, generating a representation which includes positions of a plurality of lane lines of the road based on the identified lane line data points, and adjusting a calibration parameter of a sensor from among the one or more sensors of the vehicle based on the representation of the plurality of lane lines.

The present disclosure provides a method, an electronic device and a storage medium for detecting a position change of a lane line. The method includes: converting a first change in a target region of first measurement data of a distance between a lane line and a reference line to a first equivalent position change, the first measurement data being obtained from first road data collected by a high-precision device on the road; correcting second measurement data of the distance with the first measurement data, the second measurement data being obtained from second road data collected by a low-precision device on the road; converting a second change of the corrected second measurement data to a second equivalent position change; and detecting a position change of the lane line in the target region based on a comparison of the first equivalent position change and the second equivalent position change.

A vehicle-assistance system for classifying objects in a vehicle's surroundings. The system includes: at least one memory configured to store classification information for classifying a plurality of objects; and at least one processor configured to receive a plurality of detection results associated with light detection and ranging system (LIDAR) detection results, each detection result including location information, and further information indicative of at least two of the following detection characteristics: object surface reflectivity; temporal spreading of signal reflected from the object; object surface physical composition; ambient illumination measured at a LIDAR dead time; difference in detection information from a previous frame; and confidence level associated with another detection characteristic. The at least one processor is also configured to: access the classification information; and based on the classification information and the detection results, classify an object in the vehicle's surroundings.

Aspects of the disclosure relate to dynamic driving metric output platforms that utilize improved computer vision methods to determine vehicle metrics from video footage. A computing platform may receive video footage from a vehicle camera. The computing platform may determine that a reference marker in the video footage has reached a beginning and an end of a road marker based on brightness transitions, and may insert time stamps into the video accordingly. Based on the time stamps, the computing platform may determine an amount of time during which the reference marker covered the road marking. Based on a known length of the road marking and the amount of time during which the reference marker covered the road marking, the computing platform may determine a vehicle speed. The computing platform may generate driving metric output information, based on the vehicle speed, which may be displayed by an accident analysis platform. Based on known dimensions of pavement markings the computing platform may obtain the parameters of the camera (e.g., focal length, camera height above ground plane and camera tilt angle) used to generate the video footage and use the camera parameters to determine the distance between the camera and any object in the video footage.

Artificial intelligence using convolutional neural network with Hough Transform. In an embodiment, a convolutional neural network (CNN) comprises convolution layers, a Hough Transform (HT) layer, and a Transposed Hough Transform (THT) layer, arranged such that at least one convolution layer precedes the HT layer, at least one convolution layer is between the HT and THT layers, and at least one convolution layer follows the THT layer. The HT layer converts its input from a first space into a second space, and the THT layer converts its input from the second space into the first space. The CNN may be applied to an input image to perform semantic image segmentation, so as to produce an output image representing a result of the semantic image segmentation.

A diagnostic vehicle (1) which diagnoses operation situations of magnetic markers (10) laid in or on a traveling road so as to be magnetically detectable by a vehicle includes sensor unit (11) which obtains a one-dimensional magnetic distribution by measuring a magnitude of magnetism with which any of magnetic markers (10) acts therearound, line sensor camera (13) which obtains a marker image, which is one-dimensional image information, by imaging magnetic marker (10), and diagnosing unit (15) which determines the presence or absence of a flaw in magnetic marker (10) based on a comparison between a magnetic distribution and the marker image.