CN111060911A - Vehicle anti-collision recognition method based on scene analysis - Google Patents

Vehicle anti-collision recognition method based on scene analysis Download PDF

Info

Publication number
CN111060911A
CN111060911A CN201811205690.9A CN201811205690A CN111060911A CN 111060911 A CN111060911 A CN 111060911A CN 201811205690 A CN201811205690 A CN 201811205690A CN 111060911 A CN111060911 A CN 111060911A
Authority
CN
China
Prior art keywords
obstacle
vehicle
confidence
barrier
information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201811205690.9A
Other languages
Chinese (zh)
Inventor
刘宗刚
肖伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin Soterea Automotive Technology Co Ltd
Original Assignee
Tianjin Soterea Automotive Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tianjin Soterea Automotive Technology Co Ltd filed Critical Tianjin Soterea Automotive Technology Co Ltd
Priority to CN201811205690.9A priority Critical patent/CN111060911A/en
Publication of CN111060911A publication Critical patent/CN111060911A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
    • G01S13/867—Combination of radar systems with cameras

Abstract

The invention discloses a vehicle anti-collision recognition method based on scene analysis, which comprises the following steps: the radar system collects barrier information and initializes the barrier information into a confidence value; the vision system analyzes the vehicle and the scene and judges whether the running direction of the vehicle has an obstacle or not; when the barrier information acquired by the vision system is effective, a confidence value confirmed by the vision system is added on the basis of the original confidence value; judging the current confidence value, if the confidence value is higher, considering the barrier as a real barrier, and adopting the barrier information; if the confidence coefficient is lower; the obstacle is considered to be a pseudo obstacle and its obstacle information is not adopted. The invention not only reduces the phenomena of false alarm and missing report, but also has higher distance measurement precision.

Description

Vehicle anti-collision recognition method based on scene analysis
Technical Field
The invention belongs to the technical field of vehicles, and particularly relates to a vehicle anti-collision recognition method based on scene analysis.
Background
The existing obstacle recognition systems used by many vehicles are single radar systems or single vision systems, and although the recognition efficiency is high, the phenomena of false alarm and missing report often occur; for a single radar system, particularly on a bumpy road surface, false alarm often occurs due to the fact that a radar scans on the road surface in a bumpy mode; for the single vision recognition system, vehicle and scene information can be collected, but the measured distance is not accurate, which also becomes a big problem in the single vision system.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides a vehicle anti-collision recognition method based on scene analysis, which not only reduces the phenomena of false alarm and missing report, but also has higher distance measurement precision.
In order to solve the technical problems, the invention adopts the technical scheme that: a vehicle anti-collision recognition method based on scene analysis comprises the following steps:
the radar system collects barrier information and initializes the barrier information into a confidence value;
the vision system analyzes the vehicle and the scene and judges whether the running direction of the vehicle has an obstacle or not;
when the barrier information acquired by the vision system is effective, a confidence value confirmed by the vision system is added on the basis of the original confidence value;
judging the current confidence value, if the confidence value is higher, considering the barrier as a real barrier, and adopting the barrier information; if the confidence coefficient is lower; the obstacle is considered to be a pseudo obstacle and its obstacle information is not adopted.
Preferably, the obstacle information is a vehicle, a pedestrian, or a road object.
Preferably, a single set of obstacle information collected by the radar system is defined as Hr，HrThe confidence level of including an obstacle is defined as Hr-cl，HrWhether or not an obstacle contained in (1) is present is defined as Hr-hasWherein 0 represents no obstacle and 1 represents an obstacle; the initial value of high confidence is defined as clhThe initial value of low confidence is defined as cllThen the initial value of the confidence of the obstacle is expressed as:
Figure BDA0001829993600000021
preferably, the obstacle information obtained by the visual system analysis is defined as HcWhether the obstacle is defined as H in the driving direction can be obtained based on scene analysisc-hasWherein 0 represents no obstacle and 1 represents an obstacle; when being visually confirmedThereafter, the confidence level of the obstacle is increased, the increased confidence level being defined as clcfThen the confidence of the obstacle after visual confirmation can be expressed as:
Figure BDA0001829993600000022
preferably, the obstacle is judged to be a real obstacle or a fake obstacle, and the authenticity of the obstacle is defined as Hf-hasWherein 0 represents a pseudo obstacle and 1 represents a real obstacle; the authenticity of the obstacle can be expressed as:
Figure BDA0001829993600000023
compared with the prior art, the invention has the beneficial effects that: the invention is based on a radar and vision fusion barrier recognition system, takes barrier information acquired by a radar as main information, and takes vision vehicle and scene analysis as auxiliary judgment basis, thereby not only reducing the phenomena of misinformation and missing report, but also inheriting the higher distance measurement precision of a single radar system.
Drawings
FIG. 1 is a schematic view of an embodiment of the present invention;
FIG. 2 is a schematic view of an embodiment of the present invention;
FIG. 3 is a schematic view of an embodiment of the present invention;
FIG. 4 is a schematic view of an embodiment of the present invention;
fig. 5 is a schematic diagram of an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
The embodiment of the invention discloses a vehicle anti-collision recognition method based on scene analysis, which comprises the following steps:
the radar system collects barrier information and initializes the barrier information into a confidence value;
the vision system analyzes the vehicle and the scene and judges whether the running direction of the vehicle has an obstacle or not;
when the barrier information acquired by the vision system is effective, a confidence value confirmed by the vision system is added on the basis of the original confidence value;
judging the current confidence value, if the confidence value is higher, considering the barrier as a real barrier, and adopting the barrier information; if the confidence coefficient is lower; the obstacle is considered to be a pseudo obstacle and its obstacle information is not adopted.
In this embodiment, the obstacle information is a vehicle, a pedestrian, or a road object.
In this embodiment, a single set of obstacle information collected by the radar system is defined as Hr，HrThe confidence level of including an obstacle is defined as Hr-cl，HrWhether or not an obstacle contained in (1) is present is defined as Hr-hasWherein 0 represents no obstacle and 1 represents an obstacle; the initial value of high confidence is defined as clhThe initial value of low confidence is defined as cllThen the initial value of the confidence of the obstacle is expressed as:
Figure BDA0001829993600000031
in this embodiment, the obstacle information obtained by the vision system analysis is defined as HcWhether the obstacle is defined as H in the driving direction can be obtained based on scene analysisc-hasWherein 0 represents no obstacle and 1 represents an obstacle; when visually confirmed, the confidence level of the obstacle is increased, and the increased confidence level is defined as clcfThen the confidence of the obstacle after visual confirmation can be expressed as:
Figure BDA0001829993600000041
in this embodiment, it is determined whether the obstacle is a real obstacle or a pseudo obstacle, and whether the obstacle is true or false is defined as Hf-hasWherein 0 represents a false obstacle and 1 represents a real obstacleAn obstruction; the authenticity of the obstacle can be expressed as:
Figure BDA0001829993600000042
in the embodiment, the position, the direction and the relative speed information of the obstacle are acquired by using the radar, whether the obstacle exists in the driving direction of the vehicle is analyzed according to the visual scene to confirm the obstacle, and if the obstacle is acquired by using the radar and the obstacle also exists in the driving direction through visual analysis, the confidence coefficient of the obstacle is higher; if the radar acquires the obstacle, the confidence coefficient of the obstacle is low if no obstacle exists in the driving direction through visual analysis; when the confidence of the obstacle is low, the obstacle is a false obstacle, and when the confidence of the obstacle is high, the obstacle is a real obstacle.
The first embodiment is as follows:
as shown in fig. 1, when there is no front vehicle in front of the vehicle, the radar monitors an obstacle, when the vehicle bumps, the radar scans millimeter wave reflectors such as a manhole cover and the like, and a radar scanning point appears, the camera analyzes whether there is a vehicle in the driving direction of the vehicle in the scene, and if not, the target is determined to be a false target.
Example two:
as shown in fig. 2, there is a vehicle in front of the vehicle, and the radar detects an obstacle. When the vehicle jolts, different reflection points of the front vehicle are scanned by the radar, radar scanning points appear, the camera can analyze whether the vehicle exists in the driving direction of the vehicle in the scene, and if the vehicle exists, the target is determined to be a real target.
Example three:
as shown in fig. 3, the vehicle in front quickly changes lane to the lane in which the vehicle is traveling, the vehicle is traveling normally in the lane, enters one vehicle quickly from the side, and becomes the vehicle in front after the lane, the radar recognizes that there is an obstacle and generates a radar scanning point, the camera analyzes the scene at this time, determines whether there is a vehicle in the traveling direction of the vehicle, and if so, determines that the target is a real target.
Example four:
as shown in fig. 4, the vehicle changes lanes, and there is no front vehicle after the lane change. When the vehicle changes lanes, the radar scans the guard bar capable of reflecting millimeter waves and forms a radar scanning point, the camera analyzes a scene at the moment, whether the vehicle exists in the driving direction of the vehicle is judged, and when the vehicle does not exist, the obstacle is considered to be a pseudo obstacle.
Example five:
as shown in fig. 5, the vehicle changes lane, and there is a front vehicle behind the lane change. When the vehicle changes lanes, the radar scans the front vehicle of the adjacent lane and forms a radar scanning point, the camera analyzes the scene at the moment, whether the vehicle exists in the driving direction of the vehicle is judged, and when the vehicle exists, the obstacle is considered to be a real obstacle.
The present invention has been described in detail with reference to the embodiments, but the description is only illustrative of the present invention and should not be construed as limiting the scope of the present invention. The scope of the invention is defined by the claims. The technical solutions of the present invention or those skilled in the art, based on the teaching of the technical solutions of the present invention, should be considered to be within the scope of the present invention, and all equivalent changes and modifications made within the scope of the present invention or equivalent technical solutions designed to achieve the above technical effects are also within the scope of the present invention. It should be noted that for the sake of clarity, parts of the description of the invention have been omitted where there is no direct explicit connection with the scope of protection of the invention, but where components and processes are known to those skilled in the art.

Claims (5)

1. A vehicle anti-collision recognition method based on scene analysis is characterized by comprising the following steps:
the radar system collects barrier information and initializes the barrier information into a confidence value;
the vision system analyzes the vehicle and the scene and judges whether the running direction of the vehicle has an obstacle or not;
when the barrier information acquired by the vision system is effective, a confidence value confirmed by the vision system is added on the basis of the original confidence value;
judging the current confidence value, if the confidence value is higher, considering the barrier as a real barrier, and adopting the barrier information; if the confidence coefficient is lower; the obstacle is considered to be a pseudo obstacle and its obstacle information is not adopted.
2. The vehicle collision avoidance identification method based on scene analysis according to claim 1, wherein the obstacle information is a vehicle, a pedestrian or a road object.
3. The vehicle collision avoidance identification method based on scene analysis according to claim 1, wherein a single set of obstacle information collected by a radar system is defined as Hr，HrThe confidence level of including an obstacle is defined as Hr-cl，HrWhether or not an obstacle contained in (1) is present is defined as Hr-hasWherein 0 represents no obstacle and 1 represents an obstacle; the initial value of high confidence is defined as clhThe initial value of low confidence is defined as cllThen the initial value of the confidence of the obstacle is expressed as:
Figure FDA0001829993590000011
4. the method as claimed in claim 1, wherein the obstacle information obtained by the vision system analysis is defined as HcWhether the obstacle is defined as H in the driving direction can be obtained based on scene analysisc-hasWherein 0 represents no obstacle and 1 represents an obstacle; when visually confirmed, the confidence level of the obstacle is increased, and the increased confidence level is defined as clcfThen the confidence of the obstacle after visual confirmation can be expressed as:
Figure FDA0001829993590000012
5. the vehicle anti-collision recognition method based on scene analysis as claimed in claim 1, wherein the obstacle is determined to be a real obstacle or a pseudo obstacle, and the authenticity of the obstacle is defined as Hf-hasWherein 0 represents a pseudo obstacle and 1 represents a real obstacle; the authenticity of the obstacle can be expressed as:
Figure FDA0001829993590000021
CN201811205690.9A 2018-10-16 2018-10-16 Vehicle anti-collision recognition method based on scene analysis Pending CN111060911A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811205690.9A CN111060911A (en) 2018-10-16 2018-10-16 Vehicle anti-collision recognition method based on scene analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811205690.9A CN111060911A (en) 2018-10-16 2018-10-16 Vehicle anti-collision recognition method based on scene analysis

Publications (1)

Publication Number Publication Date
CN111060911A true CN111060911A (en) 2020-04-24

Family

ID=70296684

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811205690.9A Pending CN111060911A (en) 2018-10-16 2018-10-16 Vehicle anti-collision recognition method based on scene analysis

Country Status (1)

Country Link
CN (1) CN111060911A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112394737A (en) * 2021-01-19 2021-02-23 广州赛特智能科技有限公司 Mobile robot self-adaptive speed adjusting method based on obstacle detection
CN113093178A (en) * 2021-04-21 2021-07-09 中国第一汽车股份有限公司 Obstacle target detection method and device, domain controller and vehicle
CN113253299A (en) * 2021-06-09 2021-08-13 深圳市速腾聚创科技有限公司 Obstacle detection method, obstacle detection device and storage medium
CN113534157A (en) * 2021-06-07 2021-10-22 北方天途航空技术发展（北京）有限公司 Multi-target radar detection method and system based on stack filtering
CN113888892A (en) * 2021-12-08 2022-01-04 禾多科技（北京）有限公司 Road information prompting method and device, electronic equipment and computer readable medium
CN114155476A (en) * 2022-02-07 2022-03-08 天津所托瑞安汽车科技有限公司 AEB (automatic Emergency bank) accident scene identification method, device, equipment and medium
US11624831B2 (en) 2021-06-09 2023-04-11 Suteng Innovation Technology Co., Ltd. Obstacle detection method and apparatus and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104290730A (en) * 2014-06-20 2015-01-21 郑州宇通客车股份有限公司 Radar and video information fusing method applied to advanced emergency brake system
CN104573646A (en) * 2014-12-29 2015-04-29 长安大学 Detection method and system, based on laser radar and binocular camera, for pedestrian in front of vehicle
CN104569979A (en) * 2013-10-17 2015-04-29 株式会社电装 Target detection apparatus
CN106379319A (en) * 2016-10-13 2017-02-08 上汽大众汽车有限公司 Automobile driving assistance system and control method
CN107515394A (en) * 2017-08-11 2017-12-26 武汉雷毫科技有限公司 Millimetre-wave radar sensing device and system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104569979A (en) * 2013-10-17 2015-04-29 株式会社电装 Target detection apparatus
CN104290730A (en) * 2014-06-20 2015-01-21 郑州宇通客车股份有限公司 Radar and video information fusing method applied to advanced emergency brake system
CN104573646A (en) * 2014-12-29 2015-04-29 长安大学 Detection method and system, based on laser radar and binocular camera, for pedestrian in front of vehicle
CN106379319A (en) * 2016-10-13 2017-02-08 上汽大众汽车有限公司 Automobile driving assistance system and control method
CN107515394A (en) * 2017-08-11 2017-12-26 武汉雷毫科技有限公司 Millimetre-wave radar sensing device and system

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112394737A (en) * 2021-01-19 2021-02-23 广州赛特智能科技有限公司 Mobile robot self-adaptive speed adjusting method based on obstacle detection
CN112394737B (en) * 2021-01-19 2021-05-18 广州赛特智能科技有限公司 Mobile robot self-adaptive speed adjusting method based on obstacle detection
CN113093178A (en) * 2021-04-21 2021-07-09 中国第一汽车股份有限公司 Obstacle target detection method and device, domain controller and vehicle
CN113534157A (en) * 2021-06-07 2021-10-22 北方天途航空技术发展（北京）有限公司 Multi-target radar detection method and system based on stack filtering
CN113253299A (en) * 2021-06-09 2021-08-13 深圳市速腾聚创科技有限公司 Obstacle detection method, obstacle detection device and storage medium
CN113253299B (en) * 2021-06-09 2022-02-01 深圳市速腾聚创科技有限公司 Obstacle detection method, obstacle detection device and storage medium
US11624831B2 (en) 2021-06-09 2023-04-11 Suteng Innovation Technology Co., Ltd. Obstacle detection method and apparatus and storage medium
US11927672B2 (en) 2021-06-09 2024-03-12 Suteng Innovation Technology Co., Ltd. Obstacle detection method and apparatus and storage medium
CN113888892A (en) * 2021-12-08 2022-01-04 禾多科技（北京）有限公司 Road information prompting method and device, electronic equipment and computer readable medium
CN114155476A (en) * 2022-02-07 2022-03-08 天津所托瑞安汽车科技有限公司 AEB (automatic Emergency bank) accident scene identification method, device, equipment and medium

Similar Documents

Publication Publication Date Title
CN111060911A (en) Vehicle anti-collision recognition method based on scene analysis
Ogawa et al. Pedestrian detection and tracking using in-vehicle lidar for automotive application
CN106991389B (en) Device and method for determining road edge
JP5892129B2 (en) Road shape recognition method, road shape recognition device, program, and recording medium
US6670912B2 (en) Method for detecting stationary object located above road
EP2993654B1 (en) Method and system for forward collision warning
US7545956B2 (en) Single camera system and method for range and lateral position measurement of a preceding vehicle
US8040227B2 (en) Method for detecting moving objects in a blind spot region of a vehicle and blind spot detection device
US20180022351A1 (en) Travelled-route selecting apparatus and method
CN107389084B (en) Driving path planning method and storage medium
US20100030474A1 (en) Driving support apparatus for vehicle
US9102329B2 (en) Tracking control apparatus
EP3410146B1 (en) Determining objects of interest for active cruise control
US10846546B2 (en) Traffic signal recognition device
JP6557923B2 (en) On-vehicle radar device and area detection method
US20160188984A1 (en) Lane partition line recognition apparatus
CN111332288A (en) Vehicle and pedestrian collision avoidance method based on vision system
CN114415171A (en) Automobile travelable area detection method based on 4D millimeter wave radar
CN111899562A (en) Vehicle meeting prompting method for curve blind area
CN106405539B (en) Vehicle radar system and method for removing a non-interesting object
Dietmayer et al. Roadway detection and lane detection using multilayer laserscanner
JP2006140636A (en) Obstacle detecting device and method
Kim et al. An intelligent and integrated driver assistance system for increased safety and convenience based on all-around sensing
Jung et al. Isrss: Integrated side/rear safety system
US20220375231A1 (en) Method for operating at least one environment sensor on a vehicle

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination