An apparatus for detecting a lane boundary includes one or more processors configured to: input an image representing a region around a vehicle into a classifier to identify the types of objects represented in respective pixels of the image, and detect a boundary of the travel lane by determining, for each of pixel lines in a direction crossing the travel lane in the image, whether the position corresponding to a pixel group including a predetermined number of contiguous pixels is inside the travel lane in order along a scanning direction from one end to the other end of the pixel line, depending on the order of the types of objects represented in the pixel group and the result of determination whether the position corresponding to the immediately preceding pixel group with respect to the scanning direction is inside the travel lane.

Methods and systems for real-time road flare detection using templates and appropriate color spaces are described. A computing device of a vehicle may be configured to receive an image of an environment of the vehicle. The computing device may be configured to identify a given pixels in the plurality of pixels having one or more of: (i) a red color value greater than a green color value, and (ii) the red color value greater than a blue color value. Further, the computing device may be configured to make a comparison between one or more characteristics of a shape of an object represented by the given pixels in the image and corresponding one or more characteristics of a predetermined shape of a road flare; and determine a likelihood that the object represents the road flare.

In an image processing apparatus, an image data acquisition unit acquires image data including R-pixels which are red pixels, holding red luminance values, B-pixels which are blue pixels, holding blue luminance values, G-pixels which are green pixels, holding green luminance values, and C-pixels which are clear pixels, holding luminance values in a wavelength range including wavelength ranges corresponding to red, blue and green. In the apparatus, a determination unit determines whether or not an inequality given by Valc−Valx<α is satisfied, where Valx is a luminance value of a pixel of interest that is one of the R-, B-, and G-pixels in the image data, Valc is a luminance value of the C-pixel or pixels closest to the pixel of interest, and α is a constant, and if the inequality is satisfied, a correction unit corrects the luminance value Valx to be less than the luminance value Valc.

A method and apparatus for determining lane center line are provided. The method may include obtaining a target lane in a first road segment from a database, the first road segment being a road segment having a changed lane quantity, the target lane being an added or subtracted lane, two side lane lines of the target lane being respectively connected to two side lane lines of a first lane at two endpoints of a first end of the target lane, the two side lane lines of the target lane intersecting at an intersection point at a second end of the target lane and the intersection point being connected to a side lane line of a second lane.

A method includes acquiring at least one image with at least one camera associated with at least one mobile robot; and extracting a plurality of straight lines from the at least one image; creating at least one dataset comprising data related to the plurality of straight lines extracted from the at least one image; forming a plurality of hypotheses for a walkway boundary based on the at least one dataset and determining at least one hypothesis with the highest likelihood of representing a walkway boundary; and using the at least one hypothesis to adjust a direction and/or speed of motion of the at least one mobile robot.

Disclosed are a method and an apparatus for determining a vehicle location based on optical camera communication (OCC). According to an embodiment of the present disclosure, the method for determining a vehicle location based on OCC may include the steps of receiving information on a distance between a plurality of rear lamps of a front vehicle and size information of the plurality of rear lamps by using a single camera provided in a vehicle, acquiring a rear side image of the front vehicle through the single camera, determining a rear lamp area in the rear side image of the front vehicle by using a pre-trained artificial neural network, determining a driving lane of the front vehicle based on the rear lamp area, determining a distance between the single camera and each of the plurality of rear lamps based on the rear lamp area, and deriving location information of the front vehicle, based on the received information on the distance between the plurality of rear lamps, the size information, the distance between the single camera and each of the plurality of rear lamps, and the driving lane.

An in-vehicle surrounding environment recognition device includes: a photographic unit that photographs a road surface around a vehicle and acquires a photographic image; an application execution unit that recognizes another vehicle on the basis of the photographic image, and detects a relative speed of the other vehicle with respect to the vehicle; a reflection determination unit that, on the basis of the photographic image, determines upon presence or absence of a reflection of a background object from the road surface; a warning control unit that controls output of a warning signal on the basis of the result of recognition of the other vehicle; and a warning prevention adjustment unit that suppresses output of the warning signal on the basis of the relative speed of the other vehicle, if it has been determined that there is the reflection of the background object from the road surface.

An in-vehicle imaging device is provided with a detection region setting unit for setting a detection region, which corresponds to a predetermined object to be detected within an imaging screen; a color signal determination unit for setting a specific color corresponding to the object to be detected, and for determining whether the color data of pixels contained in the detection region are close to the specific color; and a gain control unit for averaging the color data of pixels (approximate color pixels) that were determined to be close to the specific color within the detection region and for adjusting the color gain of the image signal on the basis of a differential value of the color data of the specific color and the average value of the color data of the approximate color pixels.

A system and method for estimating free space including applying a machine learning model to camera images of a navigation area, where the navigation area is broken into cells, synchronizing point cloud data from the navigation area with the processed camera images, and associating probabilities that the cell is occupied and object classifications of objects that could occupy the cells with cells in the navigation area based on sensor data, sensor noise, and the machine learning model.

A road surface gradient detection device is provided. The road surface gradient detection device includes an image area setting unit configured to divide a captured image to set a plurality of image areas, a weighting setting unit configured to set the weighting of the pixel range, a representative height calculation unit configured to calculate the representative parallax of each image area and the representative height of each image area based on the parallax of each pixel range, the coordinates of each pixel range, and a magnitude of the weighting of each pixel range, and a road surface gradient detection unit configured to detect the road surface gradient from the captured image based on the representative parallax of each image area and the representative height of each image area.