CN112698352A - Obstacle recognition device for electric locomotive - Google Patents
Obstacle recognition device for electric locomotive Download PDFInfo
- Publication number
- CN112698352A CN112698352A CN202011544281.9A CN202011544281A CN112698352A CN 112698352 A CN112698352 A CN 112698352A CN 202011544281 A CN202011544281 A CN 202011544281A CN 112698352 A CN112698352 A CN 112698352A
- Authority
- CN
- China
- Prior art keywords
- data
- obstacle
- unit
- signal
- 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.)
- Granted
Links
- 230000003137 locomotive effect Effects 0.000 title claims abstract description 44
- 238000004140 cleaning Methods 0.000 claims abstract description 45
- 238000007405 data analysis Methods 0.000 claims abstract description 38
- 239000012535 impurity Substances 0.000 claims abstract description 38
- 238000013500 data storage Methods 0.000 claims abstract description 10
- 230000005540 biological transmission Effects 0.000 claims description 39
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000012790 confirmation Methods 0.000 claims description 13
- 230000004888 barrier function Effects 0.000 claims description 11
- 239000007921 spray Substances 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000000034 method Methods 0.000 claims description 7
- 238000001035 drying Methods 0.000 claims description 5
- 239000011521 glass Substances 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 claims description 4
- 239000011148 porous material Substances 0.000 claims description 4
- 238000000926 separation method Methods 0.000 claims 1
- 238000007605 air drying Methods 0.000 description 5
- 238000005507 spraying Methods 0.000 description 5
- 238000005204 segregation Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/02—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
-
- 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
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
- G01S19/50—Determining position whereby the position solution is constrained to lie upon a particular curve or surface, e.g. for locomotives on railway tracks
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Aviation & Aerospace Engineering (AREA)
- Automation & Control Theory (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention discloses an obstacle recognition device for an electric locomotive, which comprises a data acquisition unit, a data analysis unit, a data processing unit, a lens cleaning unit, a data storage unit and a driving control unit, wherein the data acquisition unit and the data analysis unit are arranged, the distance, the size and the type of an obstacle are recognized and judged by utilizing a radar and a camera, the recognition precision and the accuracy of the obstacle are improved, the safety coefficient of the electric locomotive in autonomous driving is improved, the labor intensity of manual driving is reduced, the lens cleaning unit is arranged, the data acquisition unit is used for analyzing and calculating the density of impurity points, so that the definition of a lens is determined, the lens is cleaned by utilizing the reciprocating motion of a movable block and a sponge, the definition of the lens is ensured, the quality of an image of the obstacle is improved, and the difficulty of image recognition is reduced, the recognition speed and accuracy are improved, and the reliability of the device is improved.
Description
Technical Field
The invention relates to an obstacle recognition device, in particular to an obstacle recognition device for an electric locomotive.
Background
The electric locomotive is a traction device for rail vehicle transportation, the power is to use a traction motor to drive wheels to rotate, the locomotive runs on the rail by means of the friction between the wheels and the rail surface, and the electric locomotive is often driven by a manual driver in the production and transportation process of a coal mine.
However, manual driving has many problems, because of inconsistent levels of drivers, production and transportation efficiency is unstable, and drivers drive electric locomotives in poor working environments for a long time, so that fatigue driving is easy to occur, and the obstacles appearing in the track are not timely reacted, so that accidents are often caused, and the safety of personnel and property is threatened.
Disclosure of Invention
The invention aims to provide an obstacle recognition device for an electric locomotive, which is characterized in that a data acquisition unit and a data analysis unit are arranged, a radar and a camera are used for recognizing and judging the distance, the size and the type of an obstacle, the recognition precision and the accuracy of the obstacle are improved, the safety factor of autonomous driving of the electric locomotive is improved, and the labor intensity of manual driving is reduced.
The technical problem solved by the invention is as follows:
(1) how to identify and judge the distance, the size and the type of the obstacle by using a radar and a camera by setting a data acquisition unit and a data analysis unit, and solve the problem that the electric locomotive in the prior art cannot identify the obstacle independently;
(2) how to utilize the data acquisition unit to carry out analysis calculation to the density of impurity point through setting up the clean unit of camera lens to confirm the clarity of camera lens, and utilize the reciprocating motion of movable block and sponge to clear up the camera lens, solve the camera in the course of the work problem that the camera lens pollutes the influence recognition effect.
The purpose of the invention can be realized by the following technical scheme: a barrier recognition device for an electric locomotive comprises a data acquisition unit, a data analysis unit, a data processing unit, a lens cleaning unit, a data storage unit and a drive control unit;
the data storage unit is stored with a driving circuit diagram of the electric locomotive, and is also stored with track specification data, and the track specification data represent the width and the height of a single track;
the data acquisition unit comprises a radar and a camera, the radar is used for sending radar electric waves and receiving the radar electric waves, the camera is used for shooting obstacles appearing in the vehicle driving direction, and the radar sends acquired emission time data and received time data to the data analysis unit;
the data analysis unit analyzes the existence of obstacles by transmitting time data and receiving time data, sends the obtained barrier-free signals and curve signals to the data processing unit, sends the obtained obstacle confirmation signals to the data acquisition unit, starts the camera to continuously shoot the obstacles in the driving direction after the data acquisition unit identifies the obstacle confirmation signals, generates obstacle image data, transmits the obstacle image data to the data analysis unit for obstacle feature analysis, and transmits the obtained deceleration signals, parking signals and driving signals to the data processing unit;
the data acquisition unit is also used for carrying out definition detection on the acquired obstacle image data, dividing the obstacle image data into a plurality of unit cells, recording impurity points in each unit cell and carrying out impurity point density data, wherein an impurity point density limit value is preset in the data acquisition unit, when the impurity point density data in any unit cell is greater than or equal to the impurity point density limit value, the lens glass of the camera is judged to be unclear, a cleaning signal is generated and transmitted to the data processing unit, and when the impurity point density data in any unit cell is smaller than the impurity point density limit value, no processing is carried out;
the data processing unit receives and identifies a barrier-free signal, a curve signal, a deceleration signal, a parking signal and a drive-off signal, does not perform any processing when the barrier-free signal is identified, sends a deceleration and warning instruction to the drive control unit when the curve signal is identified, sends a deceleration instruction to the drive control unit when the deceleration signal is identified, sends a brake instruction to the drive control unit when the parking signal is identified, sends a whistle instruction to the drive control unit when the drive-off signal is identified, and sends a cleaning instruction to the lens cleaning unit when the cleaning signal is identified;
the drive control unit performs downshift and deceleration when receiving a deceleration instruction, performs single whistle when receiving a warning instruction, performs braking until the speed is reduced to zero when receiving a braking instruction, and performs continuous whistle for five seconds when receiving a whistle instruction;
the lens cleaning unit is used for cleaning the lens after receiving a cleaning instruction and comprises a sleeve seat, the sleeve seat is fixedly arranged on one side of the camera, a transmission toothed ring is arranged coaxially in the sleeve seat and is rotationally connected with the sleeve seat, a plurality of transmission gears are arranged on the inner side of the transmission toothed ring at equal angles and are rotationally connected with the sleeve seat through pin shafts, the transmission gears are all meshed with the transmission toothed ring through gear teeth, one ends of the pin shafts, far away from the transmission gears, are fixedly connected with movable blocks, the movable blocks are mutually matched, a sponge is arranged on one side surface of each movable block, the side surface of the sponge is in contact with the surface of a lens of the camera, a row of alcohol spraying holes and a row of air drying holes are formed in the side surface of each movable block, and the alcohol spraying holes and the air drying holes are respectively formed in the two sides of the sponge, one side of the sleeve seat, which is far away from the transmission gear, is provided with a micro rotary cylinder, and the end part of a piston rod of the micro motor is fixedly connected with one transmission gear through a pin shaft.
The invention has further technical improvements that: the specific steps of the data analysis unit for performing obstacle existence analysis are as follows:
the method comprises the following steps: marking the transmitting time data as FTi and the receiving time data as STi, wherein i represents the serial number of the transmitting times of the radar wave, and i is 1,2,3 … … n 1;
step two: presetting a existence definition time data in the data analysis unit, marking the existence definition time data as CTs, and substituting the receiving time data and the transmitting time data into a calculation formula: the time interval data is received time data-transmission time data, and the time interval data is obtained and marked as GTi;
step three: comparing the time interval data with the existing defined time data, judging that no barrier exists in the driving direction of the electric locomotive when the time interval data is larger than the existing defined time data, generating a barrier-free signal, judging that a barrier exists in the driving direction of the electric locomotive when the time interval data is smaller than or equal to the existing defined time data, and simultaneously performing the fourth step;
step four: the data analysis unit obtains real-time position data of the electric locomotive through GPS positioning, carries out position marking in the driving route map according to the real-time position data, marks the length between the position mark of the electric locomotive in the driving route map and the upper curve and the lower curve in the driving direction as measured length data by measuring and calculating the length, and substitutes the measured length data into a calculation formula: measuring length data/a scale to obtain actual length data, and marking the actual length data as SC;
step five: the data analysis unit is preset with a curve identification distance, when the actual length data is smaller than the curve identification distance, the obstacle is judged to be the side wall of the mine road to generate a curve signal, and when the actual length data is larger than or equal to the curve identification data, the obstacle is judged to be a track obstacle to generate an obstacle confirmation signal.
The invention has further technical improvements that: the specific steps of the obstacle feature analysis are as follows:
s31: marking the received obstacle image data as TXj, wherein j represents the image reference number at each time in continuous shooting, j is 1,2,3 … … n2, acquiring the track specification data from the data storage unit, marking the track width in the track specification data as track width data KD, and marking the track height in the track width data as track height data GD;
s32: the method comprises the steps that a plurality of obstacle image data are identified, when a rail characteristic image is identified in the obstacle image data, the obstacle image data are selected, a rail is used as a reference object, the rail width data and the rail height data are substituted into an OpenCV algorithm, obstacle width data and obstacle height data of an obstacle are obtained, width limiting data and height limiting data are preset in a data analysis unit, when the obstacle width data are larger than or equal to the width limiting data or the obstacle height data are larger than or equal to the height limiting data, it is judged that an electric locomotive cannot pass smoothly, a deceleration signal is generated and the electric locomotive enters a step S33, when the obstacle width data are smaller than the width limiting data and the obstacle height data are smaller than the height limiting data, it is judged that the electric locomotive can pass smoothly, and no processing is carried out;
s33: extracting characteristic images in obstacle image data of a plurality of adjacent moments, wherein the characteristic images represent obstacle body images with environment backgrounds removed, carrying out difference comparison on the characteristic images, judging fixed obstacles of the obstacles when the characteristic images are completely the same, generating parking signals, and judging the obstacles to be movable obstacles when the characteristic images are not in the same state, and generating driving signals.
The invention has further technical improvements that: the lens cleaning unit specifically performs lens cleaning operation by:
when discerning the clearance instruction, the alcohol that the movable block side set up sprays the pore pair lens surface and carries out alcohol and spray, start miniature revolving cylinder simultaneously and carry out reciprocal rotation, thereby drive the reciprocal rotation of drive gear with miniature revolving cylinder's tailpiece of the piston rod portion fixed connection, through the meshing transmission of the teeth of a cogwheel, it takes place reciprocal rotation to drive the transmission ring gear, and then make other drive gear reciprocal rotations, drive the movable block simultaneously around round pin axle reciprocating motion, clear up the lens surface, blow off hot-blast drying of lens surface in the air-dry hole simultaneously, accomplish the clearance of camera lens, when the camera does not use, a plurality of movable block is the mutual contact cooperation state, when the camera uses, a plurality of movable block is the alternate segregation state.
Compared with the prior art, the invention has the beneficial effects that:
1. when the invention is used, a radar in a data acquisition unit sends radar electric waves and receives the radar electric waves, a camera shoots obstacles appearing in the driving direction of a vehicle, the radar sends acquired transmitting time data and receiving time data to a data analysis unit, the data analysis unit carries out obstacle existence analysis on the transmitting time data and the receiving time data, sends obtained obstacle-free signals and bend signals to a data processing unit, sends obtained obstacle confirmation signals to the data acquisition unit, after the data acquisition unit identifies the obstacle confirmation signals, the camera is started to continuously shoot the obstacles in the driving direction, obstacle image data are generated and are transmitted to the data analysis unit for obstacle feature analysis, and obtained deceleration signals, parking signals and driving signals are transmitted to the data processing unit, through setting up data acquisition unit and data analysis unit, utilize radar and camera to discern the judgement to distance, size and the type of barrier, improve the discernment precision and the accuracy to the barrier, improved the factor of safety that electric locomotive independently traveles, reduced manual driving's intensity of labour.
2. The data acquisition unit is also used for detecting the definition of the acquired image data of the obstacles, dividing the image data of the obstacles into a plurality of unit cells, recording impurity points in each unit cell and acquiring the density data of the impurity points, the data acquisition unit is preset with the density limit of the impurity points, when the density data of the impurity points in any unit cell is more than or equal to the density limit of the impurity points, judging that the lens glass of the camera is not clear, generating a cleaning signal and transmitting the cleaning signal to the data processing unit, when the density data of the impurity points in any unit cell is less than the density limit of the impurity points, the lens cleaning unit does not perform any treatment after receiving the cleaning instruction, the lens cleaning unit performs lens cleaning operation, when the cleaning instruction is identified, an alcohol spraying hole arranged on the side surface of the movable block sprays alcohol on the surface of the lens, and simultaneously the micro rotary cylinder is started to perform reciprocating rotation, so as to drive a transmission gear fixedly connected with the end part of a piston rod of the micro rotary cylinder to perform reciprocating rotation, through the meshing transmission of the teeth of a cogwheel, it takes place reciprocating rotation to drive the transmission ring gear, and then make other drive gear reciprocating rotation, drive the movable block simultaneously and around round pin axle reciprocating motion, clear up the lens surface, blow off hot-blast drying to the lens surface from air-drying downthehole simultaneously, accomplish the clearance of camera lens, through setting up the clean unit of camera lens, utilize the data acquisition unit to carry out the analysis and calculation to the density of impurity point, thereby confirm the definition of camera lens, and utilize the reciprocating motion of movable block and sponge to clear up the camera lens, the definition of camera lens has been ensured, thereby the quality of obstacle image has been improved, the degree of difficulty of image identification has been reduced, recognition speed and accuracy have been improved, thereby the reliability of device has been improved.
Drawings
In order to facilitate understanding for those skilled in the art, the present invention will be further described with reference to the accompanying drawings.
FIG. 1 is a block diagram of the system of the present invention;
FIG. 2 is a schematic view of the overall structure of the electric locomotive of the present invention;
FIG. 3 is a schematic view of the internal structure of the socket of the present invention;
FIG. 4 is a schematic view of the connection between the movable block and the lens according to the present invention;
FIG. 5 is a schematic view of the connection between the movable block and the sponge according to the present invention.
In the figure: 1. a radar; 2. a camera; 3. a sleeve seat; 4. a transmission gear ring; 5. a transmission gear; 6. a movable block; 7. a sponge.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 5, an obstacle recognition apparatus for an electric locomotive includes a data acquisition unit, a data analysis unit, a data processing unit, a lens cleaning unit, a data storage unit, and a driving control unit;
the data storage unit is stored with a driving circuit diagram of the electric locomotive, and is also stored with track specification data, and the track specification data represent the width and the height of a single track;
the data acquisition unit comprises a radar 1 and a camera 2, the radar 1 is used for sending radar electric waves and receiving the radar electric waves, the camera 2 is used for shooting obstacles appearing in the vehicle driving direction, and the radar 1 sends acquired emission time data and received time data to the data analysis unit;
the data analysis unit analyzes the existence of obstacles by transmitting time data and receiving time data, sends the obtained barrier-free signals and curve signals to the data processing unit, sends the obtained obstacle confirmation signals to the data acquisition unit, and after the data acquisition unit identifies the obstacle confirmation signals, the data acquisition unit starts the camera 2 to continuously shoot the obstacles in the driving direction, generates obstacle image data, transmits the obstacle image data to the data analysis unit for obstacle characteristic analysis, and transmits the obtained deceleration signals, parking signals and driving signals to the data processing unit;
the data acquisition unit is also used for carrying out definition detection on the acquired obstacle image data, dividing the obstacle image data into a plurality of unit cells, recording impurity points in each unit cell and recording the density data of the impurity points, the data acquisition unit is preset with an impurity point density limit value, when the density data of the impurity points in any unit cell is more than or equal to the impurity point density limit value, the lens glass of the camera 2 is judged to be unclear, a cleaning signal is generated and transmitted to the data processing unit, and when the density data of the impurity points in any unit cell is less than the impurity point density limit value, no processing is carried out;
the data processing unit receives and identifies a barrier-free signal, a curve signal, a deceleration signal, a parking signal and a drive-off signal, does not perform any processing when the barrier-free signal is identified, sends a deceleration and warning instruction to the drive control unit when the curve signal is identified, sends a deceleration instruction to the drive control unit when the deceleration signal is identified, sends a brake instruction to the drive control unit when the parking signal is identified, sends a whistle instruction to the drive control unit when the drive-off signal is identified, and sends a cleaning instruction to the lens cleaning unit when the cleaning signal is identified;
the drive control unit performs downshift and deceleration when receiving a deceleration instruction, performs single whistle when receiving a warning instruction, performs braking until the speed is reduced to zero when receiving a braking instruction, and performs continuous whistle for five seconds when receiving a whistle instruction;
the lens cleaning unit is used for cleaning lenses after receiving a cleaning instruction and comprises a sleeve seat 3, the sleeve seat 3 is fixedly installed on one side of a camera 2, a transmission gear ring 4 is coaxially arranged in the sleeve seat 3, the transmission gear ring 4 is rotatably connected with the sleeve seat 3, a plurality of transmission gears 5 are arranged on the inner side of the transmission gear ring 4 at equal angles, the transmission gears 5 are rotatably connected with the sleeve seat 3 through pin shafts, the transmission gears 5 are respectively connected with the transmission gear ring 4 through gear teeth in a meshed manner, one end of each pin shaft, far away from the transmission gear 5, is fixedly connected with a movable block 6, the movable blocks 6 are mutually matched, a sponge 7 is installed on the surface of one side of each movable block 6, the side surface of each sponge 7 is in contact with the surface of a lens of the camera 2, and the side surface of each movable block 6 is provided with a row of alcohol spraying holes and a row of air drying holes, the alcohol spraying hole and the air drying hole are respectively formed in two sides of the sponge 7, a micro rotary cylinder is arranged on one side, away from the transmission gear 5, of the sleeve seat 3, and the end portion of a piston rod of the micro motor is fixedly connected with one transmission gear 5 through a pin shaft.
The specific steps of the data analysis unit for performing obstacle existence analysis are as follows:
the method comprises the following steps: marking the transmitting time data as FTi and the receiving time data as STi, wherein i represents the serial number of the transmitting times of the radar wave, and i is 1,2,3 … … n 1;
step two: presetting a existence definition time data in the data analysis unit, marking the existence definition time data as CTs, and substituting the receiving time data and the transmitting time data into a calculation formula: the time interval data is received time data-transmission time data, and the time interval data is obtained and marked as GTi;
step three: comparing the time interval data with the existing defined time data, judging that no barrier exists in the driving direction of the electric locomotive when the time interval data is larger than the existing defined time data, generating a barrier-free signal, judging that a barrier exists in the driving direction of the electric locomotive when the time interval data is smaller than or equal to the existing defined time data, and simultaneously performing the fourth step;
step four: the data analysis unit obtains real-time position data of the electric locomotive through GPS positioning, carries out position marking in the driving route map according to the real-time position data, marks the length between the position mark of the electric locomotive in the driving route map and the upper curve and the lower curve in the driving direction as measured length data by measuring and calculating the length, and substitutes the measured length data into a calculation formula: measuring length data/a scale to obtain actual length data, and marking the actual length data as SC;
step five: the data analysis unit is preset with a curve identification distance, when the actual length data is smaller than the curve identification distance, the obstacle is judged to be the side wall of the mine road to generate a curve signal, and when the actual length data is larger than or equal to the curve identification data, the obstacle is judged to be a track obstacle to generate an obstacle confirmation signal.
The specific steps of the obstacle feature analysis are as follows:
s31: marking the received obstacle image data as TXj, wherein j represents the image reference number at each time in continuous shooting, j is 1,2,3 … … n2, acquiring the track specification data from the data storage unit, marking the track width in the track specification data as track width data KD, and marking the track height in the track width data as track height data GD;
s32: the method comprises the steps that a plurality of obstacle image data are identified, when a rail characteristic image is identified in the obstacle image data, the obstacle image data are selected, a rail is used as a reference object, the rail width data and the rail height data are substituted into an OpenCV algorithm, obstacle width data and obstacle height data of an obstacle are obtained, width limiting data and height limiting data are preset in a data analysis unit, when the obstacle width data are larger than or equal to the width limiting data or the obstacle height data are larger than or equal to the height limiting data, it is judged that an electric locomotive cannot pass smoothly, a deceleration signal is generated and the electric locomotive enters a step S33, when the obstacle width data are smaller than the width limiting data and the obstacle height data are smaller than the height limiting data, it is judged that the electric locomotive can pass smoothly, and no processing is carried out;
s33: extracting characteristic images in obstacle image data of a plurality of adjacent moments, wherein the characteristic images represent obstacle body images with environment backgrounds removed, carrying out difference comparison on the characteristic images, judging fixed obstacles of the obstacles when the characteristic images are completely the same, generating parking signals, and judging the obstacles to be movable obstacles when the characteristic images are not in the same state, and generating driving signals.
The lens cleaning unit specifically performs lens cleaning operation by:
when discerning the clearance instruction, the alcohol of the 6 side settings of movable block sprays the pore pair lens surface and carries out alcohol and spray, start miniature revolving cylinder simultaneously and carry out reciprocal rotation, thereby drive 5 reciprocal rotations of drive gear with miniature revolving cylinder's tailpiece of the piston rod portion fixed connection, through the meshing transmission of the teeth of a cogwheel, drive transmission ring gear 4 and take place reciprocal rotation, and then make other 5 reciprocal rotations of drive gear, drive movable block 6 around round pin axle reciprocating motion simultaneously, clear up the lens surface, blow off hot-blast drying to the lens surface in the air-dry hole simultaneously, accomplish the clearance of camera lens, when camera 2 does not use, a plurality of movable block 6 is the mutual contact fit state, when camera 2 uses, a plurality of movable block 6 is the alternate segregation state.
The working principle is as follows: when the invention is used, firstly, the radar 1 in the data acquisition unit sends radar electric waves and receives the radar electric waves, the camera 2 shoots obstacles appearing in the vehicle driving direction, the radar 1 sends the acquired transmitting time data and receiving time data to the data analysis unit, the data analysis unit analyzes the existence of the obstacles by the transmitting time data and the receiving time data, and the obtained barrier-free signal and the curve signal are sent to a data processing unit, the obtained barrier confirmation signal is sent to a data acquisition unit, after the data acquisition unit identifies the barrier confirmation signal, starting the camera 2 to continuously shoot the obstacles in the driving direction, generating obstacle image data, transmitting the obstacle image data to the data analysis unit for obstacle feature analysis, and transmitting the obtained deceleration signal, parking signal and driving signal to the data processing unit; the data acquisition unit is also used for carrying out definition detection on the acquired obstacle image data, dividing the obstacle image data into a plurality of unit cells, recording impurity points in each unit cell and recording the density data of the impurity points, an impurity point density limit value is preset in the data acquisition unit, when the density data of the impurity points in any unit cell is greater than or equal to the impurity point density limit value, the lens glass of the camera 2 is judged to be unclear, a cleaning signal is generated and transmitted to the data processing unit, and when the density data of the impurity points in any unit cell is smaller than the impurity point density limit value, no processing is carried out; the data processing unit receives and identifies a barrier-free signal, a curve signal, a deceleration signal, a parking signal and a drive-off signal, does not perform any processing when the barrier-free signal is identified, sends a deceleration and warning instruction to the drive control unit when the curve signal is identified, sends a deceleration instruction to the drive control unit when the deceleration signal is identified, sends a brake instruction to the drive control unit when the parking signal is identified, sends a whistle instruction to the drive control unit when the drive-off signal is identified, and sends a cleaning instruction to the lens cleaning unit when the cleaning signal is identified; when the drive control unit receives a deceleration instruction, downshifting and decelerating are carried out, when a warning instruction is received, single whistle is carried out, when a brake instruction is received, braking is carried out until the speed is reduced to zero, and when a whistle instruction is received, continuous whistle is carried out for five seconds; lens cleaning unit carries out camera lens clearance operation after receiving the clearance instruction, when discerning the clearance instruction, the alcohol that movable block 6 side set up sprays the pore pair camera lens surface and carries out alcohol and spray, start miniature revolving cylinder simultaneously and carry out reciprocal rotation, thereby drive the drive gear 5 reciprocal rotation with miniature revolving cylinder's tailpiece of the piston rod portion fixed connection, through the meshing transmission of the teeth of a cogwheel, drive transmission ring gear 4 and take place reciprocal rotation, and then make other drive gear 5 reciprocal rotations, drive movable block 6 simultaneously around round pin axle reciprocating motion, clear up the lens surface, blow off hot-blast drying to the lens surface in the air-dry hole simultaneously, accomplish the clearance of camera lens, when camera 2 does not use, a plurality of movable block 6 is the mutual contact fit state, when camera 2 uses, a plurality of movable block 6 is the alternate segregation state.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "left", "right", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation and a specific orientation configuration and operation, and thus, should not be construed as limiting the present invention. Furthermore, "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be directly connected or indirectly connected through an intermediate member, or they may be connected through two or more elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art. While one embodiment of the present invention has been described in detail, the description is only a preferred embodiment of the present invention and should not be taken as limiting the scope of the invention. All equivalent changes and modifications made within the scope of the present invention shall fall within the scope of the present invention.
Claims (4)
1. An obstacle recognition device for an electric locomotive, characterized in that: the device comprises a data acquisition unit, a data analysis unit, a data processing unit, a lens cleaning unit, a data storage unit and a drive control unit;
the data storage unit is stored with a driving circuit diagram of the electric locomotive, and is also stored with track specification data, and the track specification data represent the width and the height of a single track;
the data acquisition unit comprises a radar (1) and a camera (2), the radar (1) is used for sending radar electric waves and receiving the radar electric waves, the camera (2) is used for shooting obstacles appearing in the vehicle driving direction, and the radar (1) sends acquired transmitting time data and receiving time data to the data analysis unit;
the data analysis unit analyzes the existence of the obstacle by transmitting time data and receiving time data, sends the obtained obstacle-free signal and curve signal to the data processing unit, sends the obtained obstacle confirmation signal to the data acquisition unit, and after the data acquisition unit identifies the obstacle confirmation signal, the data acquisition unit starts a camera (2) to continuously shoot the obstacle in the driving direction, generates obstacle image data, transmits the obstacle image data to the data analysis unit for obstacle feature analysis, and transmits the obtained deceleration signal, parking signal and driving signal to the data processing unit;
the data acquisition unit is also used for carrying out definition detection on the acquired obstacle image data, dividing the obstacle image data into a plurality of unit cells, recording impurity points in each unit cell and recording the density data of the impurity points, the data acquisition unit is preset with an impurity point density limit value, when the density data of the impurity points in any unit cell is more than or equal to the impurity point density limit value, the lens glass of the camera (2) is judged to be unclear, a cleaning signal is generated and transmitted to the data processing unit, and when the density data of the impurity points in any unit cell is less than the impurity point density limit value, no processing is carried out;
the data processing unit receives and identifies a barrier-free signal, a curve signal, a deceleration signal, a parking signal and a drive-off signal, does not perform any processing when the barrier-free signal is identified, sends a deceleration and warning instruction to the drive control unit when the curve signal is identified, sends a deceleration instruction to the drive control unit when the deceleration signal is identified, sends a brake instruction to the drive control unit when the parking signal is identified, sends a whistle instruction to the drive control unit when the drive-off signal is identified, and sends a cleaning instruction to the lens cleaning unit when the cleaning signal is identified;
the drive control unit performs downshift and deceleration when receiving a deceleration instruction, performs single whistle when receiving a warning instruction, performs braking until the speed is reduced to zero when receiving a braking instruction, and performs continuous whistle for five seconds when receiving a whistle instruction;
the camera lens cleaning unit is used for carrying out camera lens cleaning operation after receiving a cleaning instruction, the camera lens cleaning unit comprises a sleeve seat (3), the sleeve seat (3) is fixedly installed on one side of a camera (2), a transmission gear ring (4) is coaxially arranged in the sleeve seat (3), the transmission gear ring (4) is rotatably connected with the sleeve seat (3), a plurality of transmission gears (5) are arranged on the inner side of the transmission gear ring (4) at equal angles, the transmission gears (5) are rotatably connected with the sleeve seat (3) through pin shafts, the transmission gears (5) are respectively connected with the transmission gear ring (4) through gear teeth meshing, one end of each pin shaft, far away from the transmission gear (5), is fixedly connected with a movable block (6), the movable blocks (6) are matched with each other, a sponge (7) is installed on the surface of one side of each movable block (6), and the side face of the sponge (7) is contacted with the surface of the lens of the camera (2), the side of movable block (6) has been seted up one row of alcohol and has been sprayed the hole and one row of air-dry hole, alcohol sprays the hole and air-dry hole sets up the both sides at sponge (7) respectively, one side that drive gear (5) were kept away from in cover seat (3) sets up miniature revolving cylinder, micro motor's piston rod tip with through round pin axle and drive gear (5) fixed connection.
2. The obstacle recognition device for an electric locomotive according to claim 1, wherein the data analysis unit performs the obstacle existence analysis by the following specific steps:
the method comprises the following steps: marking the transmitting time data as FTi and the receiving time data as STi, wherein i represents the serial number of the transmitting times of the radar wave, and i is 1,2,3 … … n 1;
step two: presetting a existence definition time data in the data analysis unit, marking the existence definition time data as CTs, and substituting the receiving time data and the transmitting time data into a calculation formula: the time interval data is received time data-transmission time data, and the time interval data is obtained and marked as GTi;
step three: comparing the time interval data with the existing defined time data, judging that no barrier exists in the driving direction of the electric locomotive when the time interval data is larger than the existing defined time data, generating a barrier-free signal, judging that a barrier exists in the driving direction of the electric locomotive when the time interval data is smaller than or equal to the existing defined time data, and simultaneously performing the fourth step;
step four: the data analysis unit obtains real-time position data of the electric locomotive through GPS positioning, carries out position marking in the driving route map according to the real-time position data, marks the length between the position mark of the electric locomotive in the driving route map and the upper curve and the lower curve in the driving direction as measured length data by measuring and calculating the length, and substitutes the measured length data into a calculation formula: measuring length data/a scale to obtain actual length data, and marking the actual length data as SC;
step five: the data analysis unit is preset with a curve identification distance, when the actual length data is smaller than the curve identification distance, the obstacle is judged to be the side wall of the mine road to generate a curve signal, and when the actual length data is larger than or equal to the curve identification data, the obstacle is judged to be a track obstacle to generate an obstacle confirmation signal.
3. The obstacle recognition device for electric locomotives according to claim 1, wherein said obstacle feature analysis comprises the following steps:
s31: marking the received obstacle image data as TXj, wherein j represents the image reference number at each time in continuous shooting, j is 1,2,3 … … n2, acquiring the track specification data from the data storage unit, marking the track width in the track specification data as track width data KD, and marking the track height in the track width data as track height data GD;
s32: the method comprises the steps that a plurality of obstacle image data are identified, when a rail characteristic image is identified in the obstacle image data, the obstacle image data are selected, a rail is used as a reference object, the rail width data and the rail height data are substituted into an OpenCV algorithm, obstacle width data and obstacle height data of an obstacle are obtained, width limiting data and height limiting data are preset in a data analysis unit, when the obstacle width data are larger than or equal to the width limiting data or the obstacle height data are larger than or equal to the height limiting data, it is judged that an electric locomotive cannot pass smoothly, a deceleration signal is generated and the electric locomotive enters a step S33, when the obstacle width data are smaller than the width limiting data and the obstacle height data are smaller than the height limiting data, it is judged that the electric locomotive can pass smoothly, and no processing is carried out;
s33: extracting characteristic images in obstacle image data of a plurality of adjacent moments, wherein the characteristic images represent obstacle body images with environment backgrounds removed, carrying out difference comparison on the characteristic images, judging fixed obstacles of the obstacles when the characteristic images are completely the same, generating parking signals, and judging the obstacles to be movable obstacles when the characteristic images are not in the same state, and generating driving signals.
4. The obstacle recognition device for an electric locomotive according to claim 1, wherein said lens cleaning unit performs lens cleaning operation specifically by:
when discerning the clearance instruction, the alcohol that movable block (6) side set up sprays the pore pair lens surface and carries out the alcohol and spray, start miniature revolving cylinder simultaneously and carry out reciprocating rotation, thereby drive gear (5) reciprocating rotation with miniature revolving cylinder's tailpiece of the piston rod portion fixed connection, through the meshing transmission of the teeth of a cogwheel, drive transmission ring gear (4) and take place reciprocating rotation, and then make other drive gear (5) reciprocating rotation, drive movable block (6) around round pin axle reciprocating motion simultaneously, clear up the lens surface, blow off hot-blast drying to the lens surface in the air-dry hole simultaneously, accomplish the clearance of camera lens, when camera (2) do not use, a plurality of movable block (6) are the mutual contact fit state, when camera (2) use, a plurality of movable block (6) are the mutual separation state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011544281.9A CN112698352B (en) | 2020-12-23 | 2020-12-23 | Obstacle recognition device for electric locomotive |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011544281.9A CN112698352B (en) | 2020-12-23 | 2020-12-23 | Obstacle recognition device for electric locomotive |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112698352A true CN112698352A (en) | 2021-04-23 |
| CN112698352B CN112698352B (en) | 2022-11-22 |
Family
ID=75509481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011544281.9A Active CN112698352B (en) | 2020-12-23 | 2020-12-23 | Obstacle recognition device for electric locomotive |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112698352B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114999157A (en) * | 2022-05-27 | 2022-09-02 | 宁波均联智行科技股份有限公司 | Parking fee automatic payment method and vehicle-mounted machine system |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090192686A1 (en) * | 2005-09-21 | 2009-07-30 | Wolfgang Niehsen | Method and Driver Assistance System for Sensor-Based Drive-Off Control of a Motor Vehicle |
| CN102616198A (en) * | 2012-04-27 | 2012-08-01 | 湖南赛格导航技术研究有限公司 | Active safety control method and device for automobile based on millimeter wave radar detection and image recognition |
| US20160152253A1 (en) * | 2013-07-31 | 2016-06-02 | Rail Safe R.S. (2015) Ltd. | System and method for utilizing an infra-red sensor by a moving train |
| EP3048559A1 (en) * | 2015-01-21 | 2016-07-27 | RindInvest AB | Method and system for detecting a rail track |
| US20170313288A1 (en) * | 2016-04-14 | 2017-11-02 | Ford Global Technologies, Llc | Exterior vehicle camera protection and cleaning mechanisms |
| WO2018077040A1 (en) * | 2016-10-31 | 2018-05-03 | 赵福林 | Motor vehicle driver assistance camera capable of self-cleaning |
| CN108416257A (en) * | 2018-01-19 | 2018-08-17 | 北京交通大学 | Merge the underground railway track obstacle detection method of vision and laser radar data feature |
| CN108482427A (en) * | 2018-02-22 | 2018-09-04 | 中车长春轨道客车股份有限公司 | A kind of contactless rail vehicle obstacle detection system and method for controlling security |
| CN109001743A (en) * | 2018-09-06 | 2018-12-14 | 中国铁道科学研究院集团有限公司通信信号研究所 | Tramcar anti-collision system |
| CN109120824A (en) * | 2018-09-19 | 2019-01-01 | 深圳市晓控通信科技有限公司 | A kind of camera with dust reduction capability based on block chain technology |
| JP2019008431A (en) * | 2017-06-22 | 2019-01-17 | 株式会社日立製作所 | Route searching apparatus and route searching method |
| CN109552366A (en) * | 2018-12-24 | 2019-04-02 | 西安思科赛德电子科技有限公司 | Locomotive vehicle-mounted railway barrier intelligent detecting alarm system and its method for early warning |
| CN110471085A (en) * | 2019-09-04 | 2019-11-19 | 深圳市镭神智能系统有限公司 | A kind of rail detection system |
| CN110705358A (en) * | 2019-09-03 | 2020-01-17 | 陕西九域通创轨道系统技术有限责任公司 | Tunnel scene control decision method of train AEB system |
| CN110789574A (en) * | 2019-11-07 | 2020-02-14 | 北京杰迈科技股份有限公司 | Train barrier detection and comprehensive early warning protection system |
-
2020
- 2020-12-23 CN CN202011544281.9A patent/CN112698352B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090192686A1 (en) * | 2005-09-21 | 2009-07-30 | Wolfgang Niehsen | Method and Driver Assistance System for Sensor-Based Drive-Off Control of a Motor Vehicle |
| CN102616198A (en) * | 2012-04-27 | 2012-08-01 | 湖南赛格导航技术研究有限公司 | Active safety control method and device for automobile based on millimeter wave radar detection and image recognition |
| US20160152253A1 (en) * | 2013-07-31 | 2016-06-02 | Rail Safe R.S. (2015) Ltd. | System and method for utilizing an infra-red sensor by a moving train |
| EP3048559A1 (en) * | 2015-01-21 | 2016-07-27 | RindInvest AB | Method and system for detecting a rail track |
| US20170313288A1 (en) * | 2016-04-14 | 2017-11-02 | Ford Global Technologies, Llc | Exterior vehicle camera protection and cleaning mechanisms |
| WO2018077040A1 (en) * | 2016-10-31 | 2018-05-03 | 赵福林 | Motor vehicle driver assistance camera capable of self-cleaning |
| JP2019008431A (en) * | 2017-06-22 | 2019-01-17 | 株式会社日立製作所 | Route searching apparatus and route searching method |
| CN108416257A (en) * | 2018-01-19 | 2018-08-17 | 北京交通大学 | Merge the underground railway track obstacle detection method of vision and laser radar data feature |
| CN108482427A (en) * | 2018-02-22 | 2018-09-04 | 中车长春轨道客车股份有限公司 | A kind of contactless rail vehicle obstacle detection system and method for controlling security |
| CN109001743A (en) * | 2018-09-06 | 2018-12-14 | 中国铁道科学研究院集团有限公司通信信号研究所 | Tramcar anti-collision system |
| CN109120824A (en) * | 2018-09-19 | 2019-01-01 | 深圳市晓控通信科技有限公司 | A kind of camera with dust reduction capability based on block chain technology |
| CN109552366A (en) * | 2018-12-24 | 2019-04-02 | 西安思科赛德电子科技有限公司 | Locomotive vehicle-mounted railway barrier intelligent detecting alarm system and its method for early warning |
| CN110705358A (en) * | 2019-09-03 | 2020-01-17 | 陕西九域通创轨道系统技术有限责任公司 | Tunnel scene control decision method of train AEB system |
| CN110471085A (en) * | 2019-09-04 | 2019-11-19 | 深圳市镭神智能系统有限公司 | A kind of rail detection system |
| CN110789574A (en) * | 2019-11-07 | 2020-02-14 | 北京杰迈科技股份有限公司 | Train barrier detection and comprehensive early warning protection system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114999157A (en) * | 2022-05-27 | 2022-09-02 | 宁波均联智行科技股份有限公司 | Parking fee automatic payment method and vehicle-mounted machine system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112698352B (en) | 2022-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105825713B (en) | The method of operation of vehicle-mounted unmanned aerial vehicle DAS (Driver Assistant System) | |
| CN103413313B (en) | The binocular vision navigation system of electrically-based robot and method | |
| CN210258411U (en) | Detection vehicle for toothed rail railway | |
| CN109910947A (en) | Carrying type track health status dynamic monitoring and wisdom analysis system and method | |
| CN111791214A (en) | Inspection robot and inspection system for inspecting construction tunnel | |
| CN105046968B (en) | A kind of motor bus identification and grasp shoot method, apparatus and system | |
| CN110471085B (en) | Track detecting system | |
| CN112319429B (en) | Control system and control method for automatically cleaning front windshield of bullet train | |
| CN112132896A (en) | Trackside equipment state detection method and system | |
| CN112698352A (en) | Obstacle recognition device for electric locomotive | |
| CN113450475A (en) | Inspection robot system and rail transit vehicle bottom detection method | |
| CN106494611B (en) | A kind of dual-purpose patrol unmanned machine of sky rail | |
| CN110955254A (en) | Intelligent inspection robot and use method thereof | |
| CN113703023A (en) | Real-time positioning method and system for railway vehicle based on environmental image recognition and correction | |
| CN112057004A (en) | Curtain wall cleaning robot obstacle identification method and control system | |
| CN111702763A (en) | Transformer substation inspection robot repositioning system and method based on Beidou system | |
| CN208765667U (en) | A kind of city rail vehicle abrasion of pantograph pan detection system based on laser ranging | |
| CN116591005A (en) | Intelligent detection and repair device for apparent diseases of asphalt pavement | |
| CN107621229B (en) | Real-time railway track width measurement system and method based on area array black-and-white camera | |
| CN113334406A (en) | Track traffic vehicle side inspection robot system and detection method | |
| CN211263774U (en) | Be used for contact net intellectual detection system device | |
| CN210879689U (en) | Intelligent robot suitable for subway vehicle train inspection work | |
| CN112025727A (en) | Novel patrol and examine track robot device | |
| CN217932084U (en) | Comprehensive train detection system | |
| CN115903779A (en) | Intelligent early warning system and method for shield tunnel electric locomotive |
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 |