# US 2023/0410318 A1 · Vehicle and method of controlling the same > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0410318 A1 - Document ID: US20230410318A1 - Status: Published application - Kind: A1 - Application number: 18/179,513 - Filed: 2023-03-07 - Published: 2023-12-21 - Earliest claimed: 2022-05-19 - Assignees: Hyundai Motor Company; Kia Corporation - Applicants: Hyundai Motor Company; Kia Corporation - Inventors: Hayeon Lee; Deuk Hyeon Kim - Web page: https://patentgrep.com/patent/US20230410318A1 ## CPC - G06T 7/12: Edge-based segmentation - G06T 3/40: Scaling of whole images or parts thereof, e.g. expanding or contracting - G06T 5/70: Denoising; Smoothing - G06T 7/174: involving the use of two or more images - G06V 10/44: Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components - G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle - G06V 20/58: Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads - B60R 1/12: Mirror assemblies combined with other articles, e.g. clocks - B60R 2001/1223: {with sensors or transducers} - G06T 2207/20021: Dividing image into blocks, subimages or windows - G06T 2207/20192: Edge enhancement; Edge preservation - G06T 2207/30252: Vehicle exterior; Vicinity of vehicle - G06T 2207/30256: Lane; Road marking - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - B60R: VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR ## Abstract Disclosed are apparatus and method for determining a mask region for a side field of view of a vehicle. A vehicle may include an image capturing device configured to acquire a plurality of images associated with a side field of view of the vehicle. The vehicle may generate, based on accumulated edge values, a first map and generate, based on accumulated brightness difference values, a second map, wherein the accumulated edge values and the accumulated brightness difference values are obtained by processing the plurality of images; determine a boundary between a vehicle region and a detection region in the side field of view based on: at least one first value for at least one pixel of the first map; and at least one second value for at least one pixel of the second map; and determine, based on the determined boundary, a mask region of the side field of view. ## Claims ### Claim 1 A vehicle comprising: an image capturing device associated with a side field of view of the vehicle and configured to acquire a plurality of images associated with the side field of view; and a controller configured to: receive the plurality of images; generate, based on accumulated edge values, a first map and generate, based on accumulated brightness difference values, a second map, wherein the accumulated edge values and the accumulated brightness difference values are obtained by processing the plurality of images; determine a boundary between a vehicle region and a detection region in the side field of view based on: at least one first value for at least one pixel of the first map; and at least one second value for at least one pixel of the second map; and determine, based on the determined boundary, a mask region of the side field of view. ### Claim 2 (depends on 1) The vehicle of claim 1, wherein the controller is configured to: perform a blur processing on a partial region of each of the plurality of images; and generate, based on the plurality of images on which the blur processing has been performed, the first map and the second map. ### Claim 3 (depends on 1) The vehicle of claim 1, wherein the controller is configured to: generate the first map in which an edge value for the at least one pixel of the first map is reflected by performing an edge detection on the plurality of images; and acquire, from the first map, coordinates of the at least one first value including coordinates of a white pixel. ### Claim 4 (depends on 1) The vehicle of claim 1, wherein the controller is configured to: acquire, based on a first brightness value of a first image of the plurality of images and a second brightness value of a second image of the plurality of images, a brightness difference value for the at least one pixel of the second map; determine a pixel associated with a brightness difference value satisfying a threshold as a white pixel; determine a pixel associated with a brightness difference value not satisfying the threshold as a black pixel; and acquire, from the second map, coordinates of the at least one second value including coordinates of the white pixel and coordinates of the black pixel. ### Claim 5 (depends on 4) The vehicle of claim 4, wherein the controller is configured to: perform a convolution processing along a y-axis on the brightness difference value for the at least one pixel of the second map, and generate the at least one second value by performing scaling on the brightness difference value for the at least one pixel of the second map. ### Claim 6 (depends on 3) The vehicle of claim 3, wherein the controller is configured to generate the at least one first value by performing scaling on the edge value for the at least one pixel of the first map. ### Claim 7 (depends on 1) The vehicle of claim 1, wherein the controller is configured to: determine the boundary further based on smoothness associated with pixels of the plurality of images; apply a first weight to the at least one first value to determine a first weighted value; apply a second weight to the at least one second value to determine a second weighted value; apply a third weight to the smoothness to determine weighted smoothness; and acquire saliency based on the first weighted value, the second weighted value, and the weighted smoothness. ### Claim 8 (depends on 1) The vehicle of claim 1, wherein the controller is configured to: acquire a y-coordinate value having a highest saliency on an x-axis; and determine, based on the acquired y-coordinate value, the boundary. ### Claim 9 (depends on 1) The vehicle of claim 1, wherein the controller is configured to: determine a region of interest (ROI) associated with a wheel in at least one of the plurality of images; and determine, based on a rotation degree of a steering wheel, the mask region by reflecting the ROI. ### Claim 10 (depends on 1) The vehicle of claim 1, wherein the controller is configured to detect an object that is included in the detection region but not included in the mask region, and wherein the image capturing device is configured to capture the plurality of images when a speed of the vehicle is higher than a threshold. ### Claim 11 A method of controlling a vehicle, comprising: acquiring, by an image capturing device, a plurality of images associated with a side field of view of the vehicle; receiving, by a controller, the plurality of images; generating, based on accumulated edge values, a first map and generating, based on accumulated brightness difference values, a second map, wherein the accumulated edge values and the accumulated brightness difference values are obtained by processing the plurality of images; determining a boundary between a vehicle region and a detection region in the side field of view based on: at least one first value for at least one pixel of the first map; and at least one second value for at least one pixel of the second map; and determining, based on the determined boundary, a mask region of the side field of view. ### Claim 12 (depends on 11) The method of claim 11, wherein the generating of the first map and the second map comprises: performing a blur processing on a partial region of each of the plurality of images; and generating, based on the plurality of images on which the blur processing has been performed, the first map and the second map. ### Claim 13 (depends on 11) The method of claim 11, wherein the generating of the first map and the second map comprises: generating the first map in which an edge value for the at least one pixel of the first map is reflected by performing an edge detection on the plurality of images; and acquiring, from the first map, coordinates of the at least one first value including coordinates of a white pixel. ### Claim 14 (depends on 11) The method of claim 11, wherein the generating of the first map and the second map comprises: acquiring, based on a first brightness value of a first image of the plurality of images and a second brightness value of a second image of the plurality of images, a brightness difference value for the at least one pixel of the second map; determining a pixel associated with a brightness difference value satisfying a threshold as a white pixel; determining a pixel associated with a brightness difference value not satisfying the threshold as a black pixel; and acquiring, from the second map, coordinates of the at least one second value including coordinates of the white pixel and coordinates of the black pixel. ### Claim 15 (depends on 14) The method of claim 14, wherein the acquiring of the coordinates of the at least one second value comprises: performing a convolution processing along a y-axis on the brightness difference value for the at least one pixel of the second map; and generating the at least one second value by performing scaling on the brightness difference value for the at least one pixel of the second map. ### Claim 16 (depends on 13) The method of claim 13, wherein the acquiring of the coordinates of the at least one first value comprises: generating the at least one first value by performing scaling on the edge value for the at least one pixel of the first map. ### Claim 17 (depends on 11) The method of claim 11, further comprising: applying a first weight to the at least one first value to determine a first weighted value; applying a second weight to the at least one second value to determine a second weighted value; applying a third weight to smoothness associated with pixels of the plurality of images to determine weighted smoothness; and acquiring saliency based on the first weighted value, the second weighted value, and the weighted smoothness, wherein the determining of the boundary is further based on the smoothness. ### Claim 18 (depends on 11) The method of claim 11, wherein the determining of the boundary comprises: acquiring a y-coordinate value having a highest saliency on an x-axis; and determining, based on the acquired y-coordinate value, the boundary. ### Claim 19 (depends on 11) The method of claim 11, wherein the determining of the mask region comprises: determining a region of interest (ROI) associated with a wheel in at least one of the plurality of images; and determining, based on a rotation degree of a steering wheel, the mask region by reflecting the ROI. ### Claim 20 (depends on 11) The method of claim 11, further comprising: detecting an object that is included in the detection region but not included in the mask region, wherein the plurality of images are captured by the image capturing device when a speed of the vehicle is higher than a threshold.