# US 10,503,983 B2 · Lane recognition apparatus and lane recognition method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,503,983 B2 - Document ID: US10503983B2 - Status: Granted - Kind: B2 - Application number: 15/740,199 - Filed: 2015-08-19 - Published: 2018-06-28 - Granted: 2019-12-10 - Earliest claimed: 2015-08-19 - Assignees: Mitsubishi Electric Corporation - Applicants: Mitsubishi Electric Corporation - Inventors: Mitsuo Shimotani; Keisuke Inoue; Yasushi Kodaka - Web page: https://patentgrep.com/patent/US10503983B2 ## CPC - G06V 20/588: {Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road} - G01S 7/412: {based on a comparison between measured values and known or stored values} - G01S 13/931: of land vehicles - G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80) - 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 - G08G 1/167: {Driving aids for lane monitoring, lane changing, e.g. blind spot detection} - G01S 2013/9322: {using additional data, e.g. driver condition, road state or weather data} - G01S 2013/9323: {Alternative operation using light waves} - G01S 2013/9324: {Alternative operation using ultrasonic waves} - G01S 2013/93274: {on the side of the vehicles} - G06T 2207/30256: Lane; Road marking - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93}) ## Abstract A lane recognition apparatus according to the present invention includes: a subject vehicle position calculation unit that calculates a current position of a subject vehicle; a traveling lane estimation unit that estimates a lane in which the subject vehicle is traveling and a position, in a direction perpendicular to a traveling direction, of the subject vehicle in the lane based on the current position of the subject vehicle, subject vehicle surroundings information indicating a positional relationship between a road structure being a three-dimensional structure existing in relation to a road and the subject vehicle, and road information associating the road structure with a lane of a road in terms of a positional relationship therebetween; and a traveling lane final determination unit that determines the lane in which the subject vehicle is traveling and the position of the subject vehicle in the lane based on results of estimation. ## Claims ### Claim 1 A lane recognition apparatus comprising: a processor to execute a program; and a memory to store the program which, when executed by the processor, performs processes of: calculating a current position of a subject vehicle, estimating a lane in which the subject vehicle is traveling and a position, in a direction perpendicular to a traveling direction, of the subject vehicle in the lane based on the calculated current position of the subject vehicle, subject vehicle surroundings information indicating a positional relationship between a road structure and the subject vehicle and including a distance between the road structure and the subject vehicle, and road information associating a distance between the road structure and a lane of a road with each position on the road and being stored in a road structure storage, the road structure being a three-dimensional structure existing in relation to the road, wherein the estimation includes acquiring the road information from the road structure storage and acquiring the subject vehicle surroundings information from a surrounding environment detection unit that detects an object including the road structure around the subject vehicle; determining that the surrounding environment detection unit is not capable e of detecting the road structure; and determining the lane in which the subject vehicle is traveling and the position of the subject vehicle in the lane based on results of the estimation using only the road information and information on behavior of the subject vehicle. ### Claim 2 (depends on 1) The lane recognition apparatus according to claim 1, wherein the subject vehicle surroundings information includes, as a planer pattern being a two-dimensionally visible pattern, a line defining the lane or a road marking, the estimation includes estimating the lane in which the subject vehicle is traveling and the position of the subject vehicle in the lane based on the current position of the subject vehicle and the line defining the lane or the road marking, the determination includes determining the lane in which the subject vehicle is traveling and the position of the subject vehicle in the lane based on results of the estimation based on the current position of the subject vehicle, the subject vehicle surroundings information, and the road information and results of the estimation based on the current position of the subject vehicle and the line defining the lane or the road marking, and the estimation includes acquiring the subject vehicle surroundings information from an image recognition unit that recognizes the planar pattern by image processing. ### Claim 3 (depends on 2) The lane recognition apparatus according to claim 2, wherein the estimation based on the current position of the subject vehicle and the line defining the lane or the road marking includes acquiring the road information from a planar pattern storage that stores the road information associating the planar pattern with the line defining the lane. ### Claim 4 (depends on 1) The lane recognition apparatus according to claim 1, wherein the road structure includes at least one of a sidewalk, a side wall, and a dividing strip, and the road information includes at least one of a distance from a roadway outside line to the sidewalk, a height of the sidewalk, a distance from the roadway outside line to the side wall, a height of the side wall, a distance from the roadway outside line to the dividing strip, and a height of the dividing strip. ### Claim 5 (depends on 1) The lane recognition apparatus according to claim 1, wherein the road information includes an installation pattern and an installation range of the road structure installed repeatedly at regular intervals. ### Claim 6 (depends on 1) The lane recognition apparatus according to claim 1, wherein the road information includes sensing reference information expected to be detected by the surrounding environment detection unit based on a material, a shape, or a color of the road structure. ### Claim 7 (depends on 6) The lane recognition apparatus according to claim 6, wherein the sensing reference information represents intensity or a detection pattern of a detection signal detected by the surrounding environment detection unit. ### Claim 8 (depends on 2) The lane recognition apparatus according to claim 2, wherein when the image recognition unit is not capable of recognizing the planar pattern, the lane in which the subject vehicle is traveling and the position of the subject vehicle in the lane are estimated based on the road information and information on behavior of the subject vehicle. ### Claim 9 (depends on 2) The lane recognition apparatus according to claim 2, wherein the determination includes determining the lane in which the subject vehicle is traveling and the position of the subject vehicle in the lane based on at least one of first reliability and second reliability, the first reliability being reliability of the results of the estimation based on the current position of the subject vehicle, the subject vehicle surroundings information, and the road information, the second reliability being reliability of results of the estimation based on the current position of the subject vehicle and the line defining the lane or the road marking. ### Claim 10 (depends on 9) The lane recognition apparatus according to claim 9, wherein the road information includes, as a parameter used when the first reliability is calculated, ease of detection of the road structure by a surrounding environment detection unit. ### Claim 11 (depends on 9) The lane recognition apparatus according to claim 9, wherein the road information includes, as a parameter used when the second reliability is calculated, case of recognition of the planar pattern by the image recognition unit. ### Claim 12 (depends on 10) The lane recognition apparatus according to claim 10, wherein at the estimation, the first reliability is decreased with increasing frequency with which the surrounding environment detection unit detects an object other than the road structure. ### Claim 13 (depends on 10) The lane recognition apparatus according to claim 10, wherein when accuracy of detection of the road structure by the surrounding environment detection unit is low, the first reliability is decreased with decreasing accuracy at the estimation. ### Claim 14 (depends on 11) The lane recognition apparatus according to claim 11, wherein when accuracy of recognition of the planar pattern by the image recognition unit is low, the second reliability is decreased with decreasing accuracy. ### Claim 15 (depends on 1) The lane recognition apparatus according to claim 1, wherein when executed by the processor, the program further performs a process of outputting the determined lane in which the subject vehicle is traveling and the determined position of the subject vehicle in the lane. ### Claim 16 A lane recognition method comprising: calculating a current position of a subject vehicle; estimating a lane in which the subject vehicle is traveling and a position, in a direction perpendicular to a traveling direction, of the subject vehicle in the lane based on the calculated current position of the subject vehicle, subject vehicle surroundings information indicating a positional relationship between a road structure and the subject vehicle and including a distance between the road structure and the subject vehicle, and road information associating a distance between the road structure and a lane of a road with each position on the road and being stored in a road structure storage, the road structure being a three-dimensional structure existing in relation to the road; wherein the estimation includes acquiring the road information from the road structure storage and acquiring the subject vehicle surroundings information from a surrounding environment detection unit that detects an object including the road structure around the subject vehicle; determining that the surrounding environment detection unit is not capable of detecting the road structure; and determining the lane in which the subject vehicle is traveling and the position of the subject vehicle in the lane based on results of the estimation using only the road information and information on behavior of the subject vehicle. ### Claim 17 (depends on 16) The lane recognition method according to claim 16, wherein at the estimation, the road information is acquired from the road structure storage, and the subject vehicle surroundings information is acquired from a surrounding environment detection unit that detects an object including the road structure around the subject vehicle. ### Claim 18 A lane recognition apparatus comprising: a processor to execute a program; and a memory to store the program which, when executed by the processor, performs processes of, calculating a current position of a subject vehicle, estimating a lane in which the subject vehicle is traveling and a position, in a direction perpendicular to a traveling direction, of the subject vehicle in the lane based on the calculated current position of the subject vehicle, subject vehicle surroundings information indicating a positional relationship between a road structure and the subject vehicle and including a distance between the road structure and the subject vehicle, and road information associating a distance between the road structure and a lane of a road with each position on the road and being stored in a road structure storage, the road structure being a three-dimensional structure existing in relation to the road, and determining the lane in which the subject vehicle is traveling and the position of the subject vehicle in the lane based on results of the estimation, wherein the subject vehicle surroundings information includes, as a planer pattern being a two-dimensionally visible pattern, a line defining the lane or a road marking, the estimation includes estimating the lane in which the subject vehicle is traveling and the position of the subject vehicle in the lane based on the current position of the subject vehicle and the line defining the lane or the road marking, the determination includes determining the lane in which the subject vehicle is traveling and the position of the subject vehicle in the lane based on results of the estimation based on the current position of the subject vehicle, the subject vehicle surroundings information, and the road information and results of the estimation based on the current position of the subject vehicle and the line defining the lane or the road marking, the estimation includes acquiring the subject vehicle surroundings information from an image recognition unit that recognizes the planar pattern by image processing, and when the image recognition unit is not capable of recognizing the planar pattern, the lane in which the subject vehicle is traveling and the position of the subject vehicle in the lane are estimated based on the road information and information on behavior of the subject vehicle.