CN109101887B - Rail locomotive control method based on visual analysis - Google Patents
Rail locomotive control method based on visual analysis Download PDFInfo
- Publication number
- CN109101887B CN109101887B CN201810762547.3A CN201810762547A CN109101887B CN 109101887 B CN109101887 B CN 109101887B CN 201810762547 A CN201810762547 A CN 201810762547A CN 109101887 B CN109101887 B CN 109101887B
- Authority
- CN
- China
- Prior art keywords
- locomotive
- pantograph
- detection
- running
- camera
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61C—LOCOMOTIVES; MOTOR RAILCARS
- B61C17/00—Arrangement or disposition of parts; Details or accessories not otherwise provided for; Use of control gear and control systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Transportation (AREA)
- Automation & Control Theory (AREA)
- Mechanical Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention belongs to the technical field of automation, and particularly relates to a rail locomotive control method based on visual analysis, which is characterized by comprising the following steps of: step 1, positioning the locomotive in operation; step 2, signal lamp identification; step 3, detecting other objects such as people, vehicles, roadblocks and the like; step 4, identifying the characters of the locomotive serial numbers; and 5, judging the state of the pantograph. The invention realizes the automation of the locomotive system by using algorithms such as a stereoscopic vision principle, target detection, character recognition and the like to replace the control means of the traditional method. The non-contact visual control method not only saves manpower from the underground mine, but also is beneficial to a central control center to observe the underground mine situation in real time and perform operation control, introduces a binocular camera system, expands the traditional two-dimensional monitoring to a three-dimensional space, obtains three-dimensional position information of a target by utilizing a stereoscopic vision parallax principle, and realizes the functions which cannot be completed by the traditional plane camera system, such as operation positioning, target detection, distance estimation and the like of a rail locomotive by utilizing the information.
Description
Technical Field
The invention belongs to the technical field of automation, and particularly relates to a rail locomotive control method based on visual analysis.
Background
Rail-bound transportation systems are an important component of underground mine production. Due to poor production environment of underground mines and high labor intensity of personnel, the requirement of automatic operation of rail locomotives is stronger and stronger. The current automatic control system of the rail locomotive transmits control signals based on central master control, and a vehicle-mounted host receives control instructions to start and stop and the like. The scheme requires full network coverage underground, such as WiFi, Zigbee, 3G and the like, and the engineering investment is large because the full network coverage is required.
Disclosure of Invention
The invention aims to provide a rail vehicle control method based on visual analysis, which can enable a rail vehicle to start, stop, accelerate and decelerate and the like by identifying the conditions of signal lamps, tracks and roadways of a visual system.
The purpose of the invention is realized by the following technical scheme:
the invention relates to a rail vehicle control method based on visual analysis, which is characterized by comprising the following steps:
step 1, positioning locomotive operation
(1) In an underground mine, cameras are arranged at intervals along a locomotive running track, and whether a locomotive runs through or not is detected at fixed points; the distance interval for installing the cameras is determined by the effective shooting distance of the cameras so as to ensure that the locomotive is always within the operation range of the camera system;
(2) yellow rectangular marks are arranged on the side face and the back face of the locomotive, and the serial numbers of the locomotive are marked on the marks by using a uniform serial number rule, so that different locomotives can be effectively identified during detection;
(3) when the camera identifies the mark on the locomotive body, the locomotive target is considered to appear, and at the moment, the serial number on the mark is identified by character identification to determine the serial number information of the current vehicle;
(4) calculating the distance between the target locomotive and the camera by using a binocular vision principle, and positioning the running positions of different locomotives by combining the installation position information of the camera system;
step 2, signal lamp identification
(1) A binocular camera is arranged at the front end of the locomotive for identifying signal lamps and other objects;
(2) judging the distance between the locomotive and a track intersection or the position of a set signal lamp by using the position information feedback function of the locomotive, and starting the signal lamp identification function of the locomotive when the distance reaches a certain range;
(3) identifying the color displayed by a signal lamp in front of the locomotive by using color detection, and then feeding back to the locomotive to control the running state of the locomotive;
step 3, detection of other objects such as people, vehicles, roadblocks and the like
Detecting people, vehicles, roadblocks and other objects in front of the running locomotive by using a binocular camera at the front end of the locomotive; the running tracks of the locomotive are relatively fixed, the running state of the locomotive basically comprises four conditions of straight running, left turning, right turning and intersection, and for each condition, barrier-free normal running track imaging in a video shot by a binocular camera at the front end of the locomotive can be estimated, so that the normal running track imaging and the current track imaging under different conditions are compared to obtain whether an object appears in the current imaging;
step 4, character recognition of locomotive number
(1) A special mark is arranged at the rear part of the locomotive body, and whether other locomotives exist in front or not is detected according to the color detection or the characteristic matching of the mark;
(2) determining whether the front detection object is a person using the edge features;
(3) for a specially-arranged roadblock, the specially-arranged roadblock is set as an identifier with a special color, and judgment is carried out according to the set color or characteristics; and for other cases, the appearance of other objects is considered;
step 5, judging the state of the pantograph
Installing a camera at a position equivalent to the horizontal height of the transmission line to detect whether the pantograph is successfully contacted with the transmission line; because the angle between the upper frame and the lower wall rod is different when the pantograph is lifted and lowered, and the height of the transmission line is obviously changed when the transmission line is in contact with or not in contact with the pantograph, the geometric parameters are calculated by utilizing video data to judge the working state of the pantograph, and whether an abnormity occurs or not is checked.
In the signal lamp identification and the detection of other objects such as people, vehicles, roadblocks and the like, the processing of different targets is carried out by utilizing a three-dimensional video and image processing technology and integrating various characteristics such as colors, shapes, templates and the like.
In the state judgment of the pantograph, the position of the pantograph and the position of the transmission line are determined by utilizing image detection and segmentation, and then geometric parameters such as the angle of the pantograph and the height of the transmission line are estimated to judge the working state of the pantograph.
The invention has the advantages that:
the rail locomotive control method based on visual analysis breaks through the idea of traditional control, adopts algorithms such as a stereoscopic vision principle, target detection, character recognition and the like to replace the control means of the traditional method, and realizes the automation of a locomotive system by using computer vision. The non-contact intuitive control method not only saves manpower from the underground mine, but also is beneficial to a central control center to observe the underground mine situation in real time and perform operation control. Conventional video and image capturing is limited to the expression of plane information, and can only provide plane position information of a captured object, which is limited in many practical applications. The invention has the main innovation points that a binocular camera system is introduced based on computer vision, the traditional two-dimensional monitoring is expanded to a three-dimensional space, the three-dimensional position information of a target is obtained by utilizing a stereoscopic vision parallax principle, and the functions which cannot be finished by the traditional plane camera system, such as running positioning, target detection, distance estimation and the like of a rail locomotive, are realized by utilizing the information.
Detailed Description
The following further illustrates embodiments of the present invention.
The invention relates to a rail vehicle control method based on visual analysis, which is characterized by comprising the following steps:
step 1, positioning locomotive operation
(1) In an underground mine, cameras are arranged at intervals along a locomotive running track, and whether a locomotive runs through or not is detected at fixed points; the distance interval for installing the cameras is determined by the effective shooting distance of the cameras so as to ensure that the locomotive is always within the operation range of the camera system;
(2) yellow rectangular marks are arranged on the side face and the back face of the locomotive, and the serial numbers of the locomotive are marked on the marks by using a uniform serial number rule, so that different locomotives can be effectively identified during detection;
(3) when the camera identifies the mark on the locomotive body, the locomotive target is considered to appear, and at the moment, the serial number on the mark is identified by character identification to determine the serial number information of the current vehicle;
(4) calculating the distance between the target locomotive and the camera by using a binocular vision principle, and positioning the running positions of different locomotives by combining the installation position information of the camera system;
step 2, signal lamp identification
(1) A binocular camera is arranged at the front end of the locomotive for identifying signal lamps and other objects;
(2) judging the distance between the locomotive and a track intersection or the position of a set signal lamp by using the position information feedback function of the locomotive, and starting the signal lamp identification function of the locomotive when the distance reaches a certain range;
(3) identifying the color displayed by a signal lamp in front of the locomotive by using color detection, and then feeding back to the locomotive to control the running state of the locomotive;
step 3, detection of other objects such as people, vehicles, roadblocks and the like
Detecting people, vehicles, roadblocks and other objects in front of the running locomotive by using a binocular camera at the front end of the locomotive; the running tracks of the locomotive are relatively fixed, the running state of the locomotive basically comprises four conditions of straight running, left turning, right turning and intersection, and for each condition, barrier-free normal running track imaging in a video shot by a binocular camera at the front end of the locomotive can be estimated, so that the normal running track imaging and the current track imaging under different conditions are compared to obtain whether an object appears in the current imaging; the track area is the focus of our attention, so the detection is locked to a certain range around the track area. The detection here is not limited to people, vehicles and roadblocks, but also other objects in addition to this can be detected.
Step 4, character recognition of locomotive number
(1) A special mark is arranged at the rear part of the locomotive body, and whether other locomotives exist in front or not is detected according to the color detection or the characteristic matching of the mark;
(2) determining whether the front detection object is a person using the edge features;
(3) for a specially-arranged roadblock, the specially-arranged roadblock is set as an identifier with a special color, and judgment is carried out according to the set color or characteristics; and for other cases, the appearance of other objects is considered;
step 5, judging the state of the pantograph
Installing a camera at a position equivalent to the horizontal height of the transmission line to detect whether the pantograph is successfully contacted with the transmission line; because the angle between the upper frame and the lower wall rod is different when the pantograph is lifted and lowered, and the height of the transmission line is obviously changed when the transmission line is in contact with or not in contact with the pantograph, the geometric parameters are calculated by utilizing video data to judge the working state of the pantograph, and whether an abnormity occurs or not is checked.
In the signal lamp identification and the detection of other objects such as people, vehicles, roadblocks and the like, the processing of different targets is carried out by utilizing a three-dimensional video and image processing technology and integrating various characteristics such as colors, shapes, templates and the like.
In the state judgment of the pantograph, the position of the pantograph and the position of the transmission line are determined by utilizing image detection and segmentation, and then geometric parameters such as the angle of the pantograph and the height of the transmission line are estimated to judge the working state of the pantograph.
The method introduces a binocular camera shooting system, utilizes a real-time three-dimensional video image processing technology, and realizes the operation positioning of the locomotive, the identification of traffic lights at intersections, the real-time detection of people, vehicles and roadblocks in the operation process, the state of a pantograph of the locomotive and the like. The required equipment conditions are:
1) arranging yellow rectangular marks on the side and the back of the locomotive, and marking the serial number of the locomotive on the marks; the specific road block mark is also marked by a special color so as to be convenient for detection and identification;
2) in an underground mine, binocular cameras are arranged at intervals along a locomotive running track to form a positioning system;
3) installing a binocular camera in front of the locomotive to detect signal lamps and front objects;
4) arranging a camera at the position of the pantograph to be detected according to the horizontal height of the transmission line, and detecting the working state of the pantograph;
5) good lighting conditions in mines.
The specific implementation method comprises the following aspects:
1) estimation of target spatial information using the principle of stereo vision
The three-dimensional position information of the target can be estimated by utilizing the video shot by the binocular camera, the distance between the locomotive to be positioned and the camera can be further estimated so as to realize the running positioning of the locomotive, the distance between the signal lamp and the intersection and the locomotive can be estimated so as to control the locomotive to continue running or stop running, and the distance between the object appearing in front of the locomotive and the locomotive can be estimated so as to adjust the speed of the locomotive.
In stereoscopic vision, important technical points include binocular camera rectification, image stereo matching and parallax calculation. The correction of the binocular camera is to perform parallel correction and horizontal equal height correction on the optical axes of two cameras of the stereo camera, and is the basis for realizing stereo vision. Images obtained by the cameras are information sources of subsequent calculation, and only the cameras which are strictly corrected can obtain accurate information of the target object, so that correction of the stereo cameras is very important. Stereo matching is a process of matching left and right images photographed by a binocular camera, which is a necessary premise for calculating parallax. Only when the corresponding points of the target object in the left and right images are found, the parallax of the corresponding points can be calculated, and further the position information of the corresponding points can be calculated. The parallax calculation is based on the previous work, and the image position difference calculation of the matching points is carried out and then converted into three-dimensional space position information. By this, the spatial position information of the target object is obtained.
2) Target detection
The target detection comprises the detection of signal lamps, the detection of locomotives, the detection of objects (people, vehicles, roadblocks and the like) in front of the locomotives, and relates to technical points such as color detection, shape contour detection, template matching and the like.
In the identification of locomotives, the identification of specific roadblocks and the identification of signals of signal lights, color detection methods are used to identify and locate these objects, since their color characteristics are very pronounced. The color space has many choices, the method adopts the YCbCr space to carry out color detection, and because the YCbCr space has the characteristic of separating the chroma from the brightness, the method can reduce the influence of different illumination on the color detection effect to a certain extent; and Y, Cb and Cr can be obtained by linear transformation of the three primary colors R, G, B, so that the calculation efficiency is high, and the singularity of a nonlinear space is avoided.
When the front camera of the locomotive detects whether a front object appears, the normal imaging condition of the locomotive when no object appears under four conditions of straight running, left turning, right turning and intersection is estimated in advance, and then the normal imaging condition is compared with the current real-time detected image. In the comparison process, the area where the track is located is determined, and the difference in the area is taken as the result of object detection. Thereafter, if further determinations of the detected objects are needed, it may be determined whether other locomotives, particular roadblocks, and people are present based on the color and shape profile characteristics. If not, the detected object is considered to be an unexpected object or an obstacle.
In the pantograph state detection, geometric parameters such as an angle and a height of an object in an image need to be estimated. First, it is necessary to determine the position of the pantograph and the position of the transmission line in the image and perform segmentation, and then measure the angle between the upper frame and the lower wall rod of the pantograph and the height of the transmission line based on the result of the segmentation.
3) Character recognition
After the locomotive is present in the shooting range of the camera and is identified, the identification of the mark on the locomotive body is needed, and the character identification technology is needed. The template matching is adopted to realize character recognition, and unified and standard characters are utilized to carry out numbering and marking on different vehicles, so that good conditions are provided for template matching.
The rail locomotive control method based on visual analysis breaks through the idea of traditional control, adopts algorithms such as a stereoscopic vision principle, target detection, character recognition and the like to replace the control means of the traditional method, and realizes the automation of a locomotive system by using computer vision. The non-contact intuitive control method not only saves manpower from the underground mine, but also is beneficial to a central control center to observe the underground mine situation in real time and perform operation control. Conventional video and image capturing is limited to the expression of plane information, and can only provide plane position information of a captured object, which is limited in many practical applications. The invention has the main innovation points that a binocular camera system is introduced based on computer vision, the traditional two-dimensional monitoring is expanded to a three-dimensional space, the three-dimensional position information of a target is obtained by utilizing a stereoscopic vision parallax principle, and the functions which cannot be finished by the traditional plane camera system, such as running positioning, target detection, distance estimation and the like of a rail locomotive, are realized by utilizing the information.
Claims (1)
1. A rail car control method based on visual analysis, comprising:
step 1, positioning locomotive operation
(1) In an underground mine, cameras are arranged at intervals along a locomotive running track, and whether a locomotive runs through or not is detected at fixed points; the distance interval for installing the cameras is determined by the effective shooting distance of the cameras so as to ensure that the locomotive is always within the operation range of the camera system;
(2) yellow rectangular marks are arranged on the side face and the back face of the locomotive, and the serial numbers of the locomotive are marked on the marks by using a uniform serial number rule, so that different locomotives can be effectively identified during detection;
(3) when the camera identifies the mark on the locomotive body, the locomotive target is considered to appear, and at the moment, the serial number on the mark is identified by character identification to determine the serial number information of the current vehicle;
(4) calculating the distance between the target locomotive and the camera by using a binocular vision principle, and positioning the running positions of different locomotives by combining the installation position information of the camera system;
step 2, signal lamp identification
(1) A binocular camera is arranged at the front end of the locomotive for identifying signal lamps and other objects;
(2) judging the distance between the locomotive and a track intersection or the position of a set signal lamp by using the position information feedback function of the locomotive, and starting the signal lamp identification function of the locomotive when the distance reaches a certain range;
(3) identifying the color displayed by a signal lamp in front of the locomotive by using color detection, and then feeding back to the locomotive to control the running state of the locomotive;
step 3, detection of other objects such as people, vehicles, roadblocks and the like
Detecting people, vehicles, roadblocks and other objects in front of the running locomotive by using a binocular camera at the front end of the locomotive; the running tracks of the locomotive are relatively fixed, the running state of the locomotive basically comprises four conditions of straight running, left turning, right turning and intersection, and for each condition, barrier-free normal running track imaging in a video shot by a binocular camera at the front end of the locomotive can be estimated, so that the normal running track imaging and the current track imaging under different conditions are compared to obtain whether an object appears in the current imaging;
step 4, character recognition of locomotive number
(1) A special mark is arranged at the rear part of the locomotive body, and whether other locomotives exist in front or not is detected according to the color detection or the characteristic matching of the mark;
(2) determining whether the front detection object is a person using the edge features;
(3) for a specially-arranged roadblock, the specially-arranged roadblock is set as an identifier with a special color, and judgment is carried out according to the set color or characteristics; and for other cases, the appearance of other objects is considered;
step 5, judging the state of the pantograph
Installing a camera at a position equivalent to the horizontal height of the transmission line to detect whether the pantograph is successfully contacted with the transmission line; because the angle between the upper frame and the lower wall rod is different when the pantograph is lifted and lowered, and the height of the transmission line is obviously changed when the transmission line is in contact with or not in contact with the pantograph, the geometric parameters are calculated by using video data to judge the working state of the pantograph, whether an abnormity occurs or not is checked,
in the signal lamp identification and the detection of other objects such as people, vehicles, roadblocks and the like, the processing of different targets is carried out by utilizing the three-dimensional video and image processing technology and integrating various characteristics such as colors, shapes, templates and the like,
in the state judgment of the pantograph, the position of the pantograph and the position of the transmission line are determined by utilizing image detection and segmentation, and then geometric parameters such as the angle of the pantograph and the height of the transmission line are estimated to judge the working state of the pantograph.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810762547.3A CN109101887B (en) | 2018-07-12 | 2018-07-12 | Rail locomotive control method based on visual analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810762547.3A CN109101887B (en) | 2018-07-12 | 2018-07-12 | Rail locomotive control method based on visual analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109101887A CN109101887A (en) | 2018-12-28 |
| CN109101887B true CN109101887B (en) | 2022-03-15 |
Family
ID=64846177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810762547.3A Active CN109101887B (en) | 2018-07-12 | 2018-07-12 | Rail locomotive control method based on visual analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109101887B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109740526B (en) * | 2018-12-29 | 2023-06-20 | 清华大学苏州汽车研究院（吴江） | Signal lamp identification method, device, equipment and medium |
| CN111666947B (en) * | 2020-05-26 | 2023-08-04 | 成都唐源电气股份有限公司 | Pantograph head offset measuring method and system based on 3D imaging |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201825066U (en) * | 2010-10-20 | 2011-05-11 | 成都可益轨道技术有限公司 | Automatic locomotive ground signal and obstacle recognition system |
| CN102507601A (en) * | 2011-11-08 | 2012-06-20 | 南京大学 | Online abrasion detection method and system for pantograph of electric locomotive |
| CN205059645U (en) * | 2015-10-21 | 2016-03-02 | 武汉钢铁(集团)公司 | Railway freight car license number automatic identification system |
| CN105718902A (en) * | 2016-01-25 | 2016-06-29 | 成都国铁电气设备有限公司 | Contact net pantograph stagger value overrun defect recognition method and system |
| CN106909152A (en) * | 2017-03-17 | 2017-06-30 | 奇瑞汽车股份有限公司 | A kind of automobile-used context aware systems and automobile |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5659013B2 (en) * | 2007-08-06 | 2015-01-28 | オーリゾン オペレイションズ リミテッド | System for monitoring pantograph damage and wear |
-
2018
- 2018-07-12 CN CN201810762547.3A patent/CN109101887B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201825066U (en) * | 2010-10-20 | 2011-05-11 | 成都可益轨道技术有限公司 | Automatic locomotive ground signal and obstacle recognition system |
| CN102507601A (en) * | 2011-11-08 | 2012-06-20 | 南京大学 | Online abrasion detection method and system for pantograph of electric locomotive |
| CN205059645U (en) * | 2015-10-21 | 2016-03-02 | 武汉钢铁(集团)公司 | Railway freight car license number automatic identification system |
| CN105718902A (en) * | 2016-01-25 | 2016-06-29 | 成都国铁电气设备有限公司 | Contact net pantograph stagger value overrun defect recognition method and system |
| CN106909152A (en) * | 2017-03-17 | 2017-06-30 | 奇瑞汽车股份有限公司 | A kind of automobile-used context aware systems and automobile |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109101887A (en) | 2018-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103522970B (en) | Based on vehicle driving safety method of inspection and the system of machine vision | |
| EP1981748B1 (en) | System for measuring speed of a train | |
| US20170372160A1 (en) | Environment recognition device and environment recognition method | |
| CN104243935B (en) | Airport field prison aims of systems monitoring method based on video identification | |
| US9349070B2 (en) | Vehicle external environment recognition device | |
| CN106218492B (en) | A kind of night running light automatic switching control equipment and switching method | |
| CN110088802B (en) | Object detection device | |
| US8855367B2 (en) | Environment recognition device and environment recognition method | |
| US8989439B2 (en) | Environment recognition device and environment recognition method | |
| US20120269391A1 (en) | Environment recognition device and environment recognition method | |
| WO2005029441A1 (en) | Device for detecting road traveling lane | |
| CN108037505A (en) | A kind of night front vehicles detection method and system | |
| CN104506800A (en) | Scene synthesis and comprehensive monitoring method and device for electronic police cameras in multiple directions | |
| CN107344696A (en) | Tire crane anti-collision based on real time video image identification hits early warning system and its method | |
| CN104392224A (en) | Crack detection method for road surface | |
| CN106970581B (en) | A kind of train pantograph real-time intelligent monitoring method and system based on the three-dimensional full visual angle of unmanned aerial vehicle group | |
| CN110001703B (en) | Train even hangs auxiliary guidance method and even hangs integrity of train monitoring method | |
| CN109101887B (en) | Rail locomotive control method based on visual analysis | |
| JP2012168592A (en) | Environment recognition device | |
| KR20140137577A (en) | Apparatus and method for providing vehicle of circumference environment information | |
| CN105083324A (en) | Method and device for locomotive anticollision using on-board optical detection mechanism combining with auxiliary image pickup | |
| JP2010218568A (en) | Communication vehicle display device | |
| KR102004909B1 (en) | Tongue rail inspection system for detecting the close contact | |
| JP2015170240A (en) | Vehicular outside environment recognition system | |
| Wang et al. | Geometry constraints-based visual rail track extraction |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |