CN113777622A - Method and device for identifying rail obstacle - Google Patents
Method and device for identifying rail obstacle Download PDFInfo
- Publication number
- CN113777622A CN113777622A CN202111011733.1A CN202111011733A CN113777622A CN 113777622 A CN113777622 A CN 113777622A CN 202111011733 A CN202111011733 A CN 202111011733A CN 113777622 A CN113777622 A CN 113777622A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- point cloud
- cloud data
- dimensional point
- data
- 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
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
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
-
- 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
- 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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a method and a device for identifying a rail obstacle. The method comprises the following steps: confirming whether the front rail has an obstacle or not based on the three-dimensional point cloud data; if the obstacle exists, controlling to start a camera, and acquiring image information of the obstacle through the camera; and determining obstacle early warning information based on the three-dimensional point cloud data and the image information fusion result. The method comprises the steps of scanning the front of a train to acquire data by using a laser radar, acquiring point cloud data of an obstacle, guiding a camera to acquire a visual image of the obstacle, fusing the processed point cloud three-dimensional data with the two-dimensional data of a graph, acquiring information such as the direction, distance and strength of the obstacle, and acquiring accurate early warning information of the obstacle.
Description
Technical Field
The invention relates to the technical field of rail transit control, in particular to a method and a device for identifying rail obstacles.
Background
With the rapid development of the current urbanization, urban rail transit becomes a preferred mode for people to go out due to the advantages of large passenger capacity, no blockage and the like. And the running speed of the train is continuously improved, and the requirement on the running safety of the train is higher and higher. In order to ensure the traveling safety of people, the rail obstacles with the range larger than 950m need to be identified timely and accurately, and early warning is provided to inform a running train to take corresponding protective measures.
At present, the technical scheme of track obstacle identification mainly includes:
(1) the obstacle image is collected and identified through the zoom camera, early warning is carried out according to the processed obstacle space position information and the current state information of the vehicle, and the obstacle in front of the vehicle in 300 meters can be effectively detected;
(2) the method adopts various radars and different types of cameras, and achieves the purpose of active anti-collision monitoring by acquiring a detection target through fusing acquired obstacle image data and radar data based on machine learning and gray projection algorithm.
The technical scheme (1) only depends on a single vision technology, the detection range is limited, and the requirement of the subway on the detection range of the anti-collision equipment cannot be met; the technical scheme (2) has a complex algorithm and is not easy to engineer, and meanwhile, due to the aid of various sensors, the cost caused by various hardware devices is far higher than that of a common collision avoidance system.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method and a device for identifying a track obstacle.
In a first aspect, the present invention provides a method for identifying an obstacle in a track, including:
confirming whether the front rail has an obstacle or not based on the three-dimensional point cloud data;
if the obstacle exists, controlling to start a camera, and acquiring image information of the obstacle through the camera;
and determining obstacle early warning information based on the three-dimensional point cloud data and the image information fusion result.
Optionally, the determining obstacle warning information based on the three-dimensional point cloud data and the image information fusion result includes:
acquiring two-dimensional data information of the obstacle based on the image information;
projecting the two-dimensional data information to the rasterized three-dimensional point cloud data to obtain enhanced two-dimensional point cloud data based on the spatial resolution corresponding to the image information and the spatial correspondence between the image information and the three-dimensional point cloud data;
and obtaining obstacle early warning information based on the fusion result of the three-dimensional point cloud data and the enhanced two-dimensional point cloud data.
Optionally, before determining whether there is an obstacle in the front track based on the three-dimensional point cloud data, the method includes:
acquiring first data information of a track in front of a train through a laser radar;
and performing abnormality removal processing on the first data information to obtain effective three-dimensional point cloud data.
Optionally, the method further includes:
and sending prompt information to the camera, and controlling the camera to rotate in advance to acquire the image information of the curve.
In a second aspect, the present invention provides a device for identifying a rail obstacle, including:
the confirming module is used for confirming whether the front rail has the obstacle or not based on the three-dimensional point cloud data;
the control module is used for controlling to start the camera if the obstacle exists and acquiring the image information of the obstacle through the camera;
and the fusion module is used for determining the obstacle early warning information based on the three-dimensional point cloud data and the image information fusion result.
Optionally, the fusion module is further configured to:
acquiring two-dimensional data information of the obstacle based on the image information;
projecting the two-dimensional data information to the rasterized three-dimensional point cloud data to obtain enhanced two-dimensional point cloud data based on the spatial resolution corresponding to the image information and the spatial correspondence between the image information and the three-dimensional point cloud data;
and obtaining obstacle early warning information based on the fusion result of the three-dimensional point cloud data and the enhanced two-dimensional point cloud data.
Optionally, the apparatus further includes a data processing module, configured to:
acquiring first data information of a track in front of a train through a laser radar;
and performing abnormality removal processing on the first data information to obtain effective three-dimensional point cloud data.
Optionally, the apparatus further includes a prompt module, configured to:
and sending prompt information to the camera, and controlling the camera to rotate in advance to acquire the image information of the curve.
In a third aspect, the present invention provides an electronic device comprising a processor and a memory storing a computer program, the processor implementing the steps of the method for rail obstacle recognition of the first aspect when executing the program.
In a fourth aspect, the present invention provides a processor readable storage medium having stored thereon a computer program for causing a processor to perform the steps of the method of track obstacle identification of the first aspect.
According to the method and the device for identifying the rail obstacle, the laser radar is used for scanning the front of a train to acquire data, point cloud data of the obstacle is acquired, a camera is guided to acquire a visual image of the obstacle, processed point cloud three-dimensional data and two-dimensional data of the image are fused, information such as the direction, the distance and the strength of the obstacle is acquired, and accurate obstacle early warning information is acquired.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for identifying a rail obstacle according to the present invention;
FIG. 2 is an overall flow chart of a method of rail obstacle identification provided by the present invention;
FIG. 3 is a schematic structural diagram of a rail obstacle recognition device according to the present invention;
FIG. 4 is a schematic structural diagram of an electronic device provided by the present invention;
FIG. 5 is a schematic diagram of a particular data fusion method provided by the present invention;
fig. 6 is a schematic diagram of fusion of three-dimensional point cloud data provided by the present invention and two-dimensional data information corresponding to a camera-acquired image.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. 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.
The method and apparatus for identifying a rail obstacle according to the present invention will be described with reference to fig. 1 to 6.
Fig. 1 is a schematic flow chart of a method for identifying an obstacle in a track according to the present invention, as shown in fig. 1, the method for identifying an obstacle in a track includes:
and 103, determining obstacle early warning information based on the three-dimensional point cloud data and the image information fusion result.
In particular, lidar is a radar system, which is an active sensor, and the formed data is in the form of a point cloud. The working spectrum section is between infrared and ultraviolet, and the device mainly comprises a transmitter, a receiver, a measurement control unit and a power supply. Moreover, the laser radar has incomparable advantages in the aspects of reliability, detection range, ranging precision and the like.
The main content of the measurement work of the laser radar is to collect the position information of the obstacle in the three-dimensional space and collect the distance information from the obstacle to the measurement system through laser detection; meanwhile, the encoder of the laser radar can obtain angle information of the laser radar, such as azimuth angle and pitch angle.
Generally, according to the modern lidar concept, the following are often classified:
1. according to the laser wave band, there are ultraviolet laser radar, visible laser radar and infrared laser radar.
2. According to laser media, there are gas laser radars, solid laser radars, semiconductor laser radars, diode laser pumped solid laser radars, and the like.
3. There are pulse laser radar, continuous wave laser radar, hybrid laser radar, etc. according to the laser emission waveform.
4. According to the display mode, there are analog or digital display laser radar and imaging laser radar.
5. According to the carrying platform, the system comprises a foundation fixed laser radar, a vehicle-mounted laser radar, an airborne laser radar, a ship-mounted laser radar, a satellite-mounted laser radar, a missile-mounted laser radar, a handheld laser radar and the like.
6. According to the function, there are laser distance measuring radar, laser speed measuring radar, laser angle measuring radar, tracking radar, laser imaging radar, laser target indicator and biological laser radar.
7. According to the application, the laser radar system comprises a laser range finder, a target field laser radar, a fire control laser radar, a tracking identification laser radar, a multifunctional tactical laser radar, a virus detection laser radar, a navigation laser radar, a meteorological laser radar, a virus detection and atmosphere monitoring laser radar and the like.
The laser radar adopted in the invention is not specifically limited, the laser radar is mainly used for measuring the distance, a three-dimensional position model can be generated, the angle measurement capability is strong, the measurement precision is high, the response speed is high, and the advantages of no influence of light rays are utilized, the front of the train driving direction is scanned, data acquisition is carried out, and the point cloud data of all objects in the reaching range which can be detected by the laser radar in front of the train is obtained, wherein the point cloud data is three-dimensional data. And determining whether an obstacle exists on the track in front of the train according to the acquired three-dimensional point cloud data. For example, whether there is a protrusion above the track, which hinders the train from moving, whether there is an obstacle higher than the ground of the train, which affects the train passing, etc.
Determining that an object higher than a train ground or obviously protruding above a track exists according to the three-dimensional point cloud data, judging that an obstacle exists, sending a control starting command to the camera by the train, and carrying out image acquisition on the obstacle in front of the running train after the camera receives and executes the command, so that the timeliness of image acquisition work is improved, and corresponding image information is obtained at the same time.
And fusing the three-dimensional point cloud data and image information obtained by a camera to determine more accurate information of the barrier, thereby providing early warning information for the train.
The method for identifying the rail obstacle comprises the steps of scanning the front of a train to acquire data by using a laser radar, acquiring point cloud data of the obstacle, guiding a camera to acquire a visual image of the obstacle, fusing the processed point cloud three-dimensional data with the two-dimensional data of the image, acquiring information such as the direction, distance and strength of the obstacle, and acquiring accurate early warning information of the obstacle.
Optionally, the determining obstacle warning information based on the three-dimensional point cloud data and the image information fusion result includes:
acquiring two-dimensional data information of the obstacle based on the image information;
projecting the two-dimensional data information to the rasterized three-dimensional point cloud data to obtain enhanced two-dimensional point cloud data based on the spatial resolution corresponding to the image information and the spatial correspondence between the image information and the three-dimensional point cloud data;
and obtaining obstacle early warning information based on the fusion result of the three-dimensional point cloud data and the enhanced two-dimensional point cloud data.
Specifically, image data of an obstacle in front of the train running acquired by a camera is processed to obtain two-dimensional data information of the obstacle.
And preprocessing the three-dimensional point cloud data acquired by the laser radar, and rasterizing according to the spatial resolution corresponding to the image information to obtain a point cloud raster image.
And projecting the image information to the point cloud raster image according to the spatial corresponding relation between the image information and the three-dimensional point cloud data to obtain enhanced two-dimensional point cloud data. And determining the height value of the three-dimensional point cloud data according to the three-dimensional point cloud data, and obtaining a fusion result by combining the enhanced two-dimensional point cloud data to obtain accurate obstacle early warning information.
And the two-dimensional image acquired by the camera and the three-dimensional point cloud data acquired by the laser radar have different wave bands. The two-dimensional image includes two pieces of information of an obstacle: coordinates and intensity.
A specific data fusion method is shown in fig. 5, which includes: point cloud rasterization, point cloud raster images, multispectral image spatial resolution and overlap region data interception.
1. After three-dimensional point cloud data acquired by a radar is subjected to preprocessing, such as outlier rejection, smoothing and the like, the height value of the three-dimensional point cloud data is recorded, namely when the three-dimensional point cloud data is represented in an XYZ coordinate form, a corresponding Z value is subjected to rasterization processing according to the spatial resolution of a two-dimensional image to obtain a point cloud grid image; wherein the two-dimensional image spatial resolution is determined from image information acquired by the camera.
2. And (3) projecting the preprocessed two-dimensional image data to the two-dimensional pixel level data obtained in the step (1) according to the spatial corresponding relation between the two-dimensional image data and the point cloud data, and obtaining the data of an overlapping area of the point cloud raster image obtained in the step (1), namely the two-dimensional point cloud data with enhanced intensity.
3. And (3) combining the data obtained in the step (2) with the height value of the three-dimensional point cloud data obtained by the radar, and finally fusing the corrected point cloud data, namely the three-dimensional point cloud data with enhanced intensity, wherein the data can represent the specific characteristics of the obstacle. Namely, the XY coordinates of the two-dimensional point cloud data with enhanced intensity and the height Z coordinates of the corresponding three-dimensional point cloud data are integrated to obtain a fused result, namely, the three-dimensional point cloud data with enhanced intensity.
The final result of the fusion of the three-dimensional point cloud data and the two-dimensional data information corresponding to the image acquired by the camera is shown in fig. 6.
If the pixels of the two-dimensional image are projected on the three-dimensional point cloud data, the pixels falling into the projected three-dimensional interval and the three-dimensional point cloud data have a corresponding relation, and the pixel intensity of the barrier is improved through the mode fusion.
The three-dimensional point cloud data obtained by the radar has limited wave bands, and the two-dimensional data of the image is used for projecting the three-dimensional point cloud data to supplement the pixel intensity of a smaller wave band of a corresponding coordinate. The obtained fusion result enriches the three-dimensional point cloud data, and further makes the obtained barrier more specific.
The method for identifying the rail obstacle comprises the steps of scanning the front of a train to acquire data by using a laser radar, acquiring point cloud data of the obstacle, guiding a camera to acquire a visual image of the obstacle, fusing the processed point cloud three-dimensional data with the two-dimensional data of the image, acquiring information such as the direction, distance and strength of the obstacle, and acquiring accurate early warning information of the obstacle.
Optionally, before determining whether there is an obstacle in the front track based on the three-dimensional point cloud data, the method includes:
acquiring first data information of a track in front of a train through a laser radar;
and performing abnormality removal processing on the first data information to obtain effective three-dimensional point cloud data.
Specifically, the original data information of the track in front of the train is collected by the laser radar on the train to serve as the first data information, because when the corresponding three-dimensional point cloud data information is captured, part of the data information may be invalid, for example, flying objects appear, and the invalid data information needs to be removed. There may be some information that the data information is a discrete point and does not belong to an obstacle, and at this time, the data information of the discrete point is deleted by the smoothing processing.
The method for identifying the rail obstacle comprises the steps of scanning the front of a train to acquire data by using a laser radar, acquiring point cloud data of the obstacle, guiding a camera to acquire a visual image of the obstacle, fusing the processed point cloud three-dimensional data with the two-dimensional data of the image, acquiring information such as the direction, distance and strength of the obstacle, and acquiring accurate early warning information of the obstacle.
Optionally, the method further includes:
and sending prompt information to the camera, and controlling the camera to rotate in advance to acquire the image information of the curve.
Specifically, the camera can be controlled to rotate through a signal sent by the train, and after the camera receives a rotation control instruction, the camera can rotate a certain angle in advance to acquire a graph of the train which turns from a straight line to a curve, so that a curve barrier can be identified, and a visual field blind area does not exist;
according to the method for identifying the rail obstacle, the reliable adjustment of the cross-line operation diagram is realized by providing the operation diagram adjustment algorithm standard; and the operation diagrams of different manufacturers can be adjusted according to the standard, and the requirement of complex overline application is met.
Fig. 2 is an overall flowchart of the method for identifying an obstacle in a track according to the present invention, and as shown in fig. 2, the overall steps of the method for identifying an obstacle in a track are as follows:
s201, collecting laser radar data;
and carrying out data acquisition on the front of the train through a laser radar.
S202, processing three-dimensional point cloud data;
and processing the data acquired by the laser radar, eliminating discrete points, smoothing the data, and screening to obtain effective data.
S203, determine whether an obstacle is present?
If no obstacle exists, the flow is transferred to S201 to continue the laser radar data acquisition;
if an obstacle is present, flow proceeds to S204.
S204-1, storing point cloud data if an obstacle exists;
s204-2, simultaneously controlling the camera to be started for image acquisition;
s204-3, processing image data;
and under the condition that the obstacle exists, storing the three-dimensional point cloud data acquired by the laser radar, simultaneously controlling the camera to be started, acquiring images of the obstacle in front of the train, and processing the image data acquired by the camera to obtain two-dimensional data information of the obstacle.
S205, fusing image data and point cloud data;
and fusing the two-dimensional data information of the obstacle with the previously stored three-dimensional point cloud data of the obstacle.
S206, generating early warning information;
and obtaining accurate obstacle early warning information according to the fused data.
And S207, sending to the train.
And finally, the early warning information is sent to the train to inform the train to take measures, so that the driving safety is ensured.
The following describes the device for identifying a rail obstacle according to the present invention, and the device for identifying a rail obstacle described below and the method for identifying a rail obstacle described above may be referred to in correspondence with each other.
Fig. 3 is a schematic structural diagram of a device for identifying a track obstacle according to the present invention, as shown in fig. 3, the device for identifying a track obstacle includes:
a confirming module 301, configured to confirm whether an obstacle exists in a front track based on the three-dimensional point cloud data;
the control module 302 is configured to control to start a camera if an obstacle exists, and acquire image information of the obstacle through the camera;
and the fusion module 303 is configured to determine obstacle early warning information based on the three-dimensional point cloud data and the image information fusion result.
Optionally, the fusion module 303 is further configured to:
acquiring two-dimensional data information of the obstacle based on the image information;
projecting the two-dimensional data information to the rasterized three-dimensional point cloud data to obtain enhanced two-dimensional point cloud data based on the spatial resolution corresponding to the image information and the spatial correspondence between the image information and the three-dimensional point cloud data;
and obtaining obstacle early warning information based on the fusion result of the three-dimensional point cloud data and the enhanced two-dimensional point cloud data.
Optionally, the apparatus further comprises a data processing module 304 configured to:
acquiring first data information of a track in front of a train through a laser radar;
and performing abnormality removal processing on the first data information to obtain effective three-dimensional point cloud data.
Optionally, the control module 302 is further configured to:
and sending prompt information to the camera, and controlling the camera to rotate in advance to acquire the image information of the curve.
It should be noted that the division of the unit in the present invention is schematic, and is only a logic function division, and there may be another division manner in actual implementation. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented as a software functional unit and sold or used as a stand-alone product, may be stored in a processor readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
It should be noted that, the apparatus provided in the present invention can implement all the method steps implemented by the method embodiments and achieve the same technical effects, and detailed descriptions of the same parts and beneficial effects as the method embodiments in this embodiment are omitted here.
Fig. 4 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 4: a processor (processor)410, a Communication Interface (Communication Interface)420, a memory (memory)430 and a Communication bus 440, wherein the processor 410, the Communication Interface 420 and the memory 430 are communicated with each other via the Communication bus 440.
Optionally, the processor 410 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or a Complex Programmable Logic Device (CPLD), and may also adopt a multi-core architecture.
The processor 410 may invoke computer programs in the memory 430 to perform the steps of the method of track obstacle recognition, including, for example:
confirming whether the front rail has an obstacle or not based on the three-dimensional point cloud data;
if the obstacle exists, controlling to start a camera, and acquiring image information of the obstacle through the camera;
and determining obstacle early warning information based on the three-dimensional point cloud data and the image information fusion result.
Optionally, the determining obstacle warning information based on the three-dimensional point cloud data and the image information fusion result includes:
acquiring two-dimensional data information of the obstacle based on the image information;
projecting the two-dimensional data information to the rasterized three-dimensional point cloud data to obtain enhanced two-dimensional point cloud data based on the spatial resolution corresponding to the image information and the spatial correspondence between the image information and the three-dimensional point cloud data;
and obtaining obstacle early warning information based on the fusion result of the three-dimensional point cloud data and the enhanced two-dimensional point cloud data.
Optionally, before determining whether there is an obstacle in the front track based on the three-dimensional point cloud data, the method includes:
acquiring first data information of a track in front of a train through a laser radar;
and performing abnormality removal processing on the first data information to obtain effective three-dimensional point cloud data.
Optionally, the steps further include:
and sending prompt information to the camera, and controlling the camera to rotate in advance to acquire the image information of the curve.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It should be noted that, the electronic device provided in the embodiment of the present invention can implement all the method steps implemented by the above method embodiment, and can achieve the same technical effect, and detailed descriptions of the same parts and beneficial effects as those of the method embodiment in this embodiment are not repeated herein.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the steps of the method of rail obstacle recognition provided by the above methods, for example comprising:
confirming whether the front rail has an obstacle or not based on the three-dimensional point cloud data;
if the obstacle exists, controlling to start a camera, and acquiring image information of the obstacle through the camera;
and determining obstacle early warning information based on the three-dimensional point cloud data and the image information fusion result.
On the other hand, embodiments of the present application further provide a processor-readable storage medium, where a computer program is stored, where the computer program is configured to cause the processor to perform the steps of the method for identifying a track obstacle provided in the foregoing embodiments, for example, the method includes:
confirming whether the front rail has an obstacle or not based on the three-dimensional point cloud data;
if the obstacle exists, controlling to start a camera, and acquiring image information of the obstacle through the camera;
and determining obstacle early warning information based on the three-dimensional point cloud data and the image information fusion result.
The processor-readable storage medium can be any available medium or data storage device that can be accessed by a processor, including, but not limited to, magnetic memory (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical memory (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor memory (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND FLASH), Solid State Disks (SSDs)), etc.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method of rail obstacle identification, comprising:
confirming whether the front rail has an obstacle or not based on the three-dimensional point cloud data;
if the obstacle exists, controlling to start a camera, and acquiring image information of the obstacle through the camera;
and determining obstacle early warning information based on the three-dimensional point cloud data and the image information fusion result.
2. The method for identifying the rail obstacle according to claim 1, wherein the determining obstacle warning information based on the three-dimensional point cloud data and the image information fusion result comprises:
acquiring two-dimensional data information of the obstacle based on the image information;
projecting the two-dimensional data information to the rasterized three-dimensional point cloud data to obtain enhanced two-dimensional point cloud data based on the spatial resolution corresponding to the image information and the spatial correspondence between the image information and the three-dimensional point cloud data;
and obtaining obstacle early warning information based on the fusion result of the three-dimensional point cloud data and the enhanced two-dimensional point cloud data.
3. The method for identifying rail obstacles according to claim 1, wherein the determining whether there is an obstacle in the front rail based on the three-dimensional point cloud data comprises:
acquiring first data information of a track in front of a train through a laser radar;
and performing abnormality removal processing on the first data information to obtain effective three-dimensional point cloud data.
4. The method of rail obstacle recognition according to claim 1, further comprising:
and sending prompt information to the camera, and controlling the camera to rotate in advance to acquire the image information of the curve.
5. An apparatus for rail obstacle identification, comprising:
the confirming module is used for confirming whether the front rail has the obstacle or not based on the three-dimensional point cloud data;
the control module is used for controlling to start the camera if the obstacle exists and acquiring the image information of the obstacle through the camera;
and the fusion module is used for determining the obstacle early warning information based on the three-dimensional point cloud data and the image information fusion result.
6. The apparatus of rail obstacle recognition according to claim 5, wherein the fusion module is further configured to:
acquiring two-dimensional data information of the obstacle based on the image information;
projecting the two-dimensional data information to the rasterized three-dimensional point cloud data to obtain enhanced two-dimensional point cloud data based on the spatial resolution corresponding to the image information and the spatial correspondence between the image information and the three-dimensional point cloud data;
and obtaining obstacle early warning information based on the fusion result of the three-dimensional point cloud data and the enhanced two-dimensional point cloud data.
7. The apparatus for rail obstacle recognition according to claim 5, further comprising a data processing module for:
acquiring first data information of a track in front of a train through a laser radar;
and performing abnormality removal processing on the first data information to obtain effective three-dimensional point cloud data.
8. The apparatus of claim 5, further comprising a prompt module to:
and sending prompt information to the camera, and controlling the camera to rotate in advance to acquire the image information of the curve.
9. An electronic device comprising a processor and a memory storing a computer program, wherein the steps of the method of track obstacle recognition according to any one of claims 1 to 4 are implemented when the computer program is executed by the processor.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of track obstacle recognition according to any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111011733.1A CN113777622B (en) | 2021-08-31 | 2021-08-31 | Rail obstacle identification method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111011733.1A CN113777622B (en) | 2021-08-31 | 2021-08-31 | Rail obstacle identification method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113777622A true CN113777622A (en) | 2021-12-10 |
CN113777622B CN113777622B (en) | 2023-10-20 |
Family
ID=78840602
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111011733.1A Active CN113777622B (en) | 2021-08-31 | 2021-08-31 | Rail obstacle identification method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113777622B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113777622B (en) * | 2021-08-31 | 2023-10-20 | 通号城市轨道交通技术有限公司 | Rail obstacle identification method and device |
CN116922448A (en) * | 2023-09-06 | 2023-10-24 | 湖南大学无锡智能控制研究院 | Environment sensing method, device and system for high-speed railway body-in-white transfer robot |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109298415A (en) * | 2018-11-20 | 2019-02-01 | 中车株洲电力机车有限公司 | A kind of track and road barricade object detecting method |
CN109814112A (en) * | 2019-01-15 | 2019-05-28 | 北京百度网讯科技有限公司 | A kind of ultrasonic radar and laser radar information fusion method and system |
CN110239592A (en) * | 2019-07-03 | 2019-09-17 | 中铁轨道交通装备有限公司 | A kind of active barrier of rail vehicle and derailing detection system |
CN110481601A (en) * | 2019-09-04 | 2019-11-22 | 深圳市镭神智能***有限公司 | A kind of rail detection system |
CN111257882A (en) * | 2020-03-19 | 2020-06-09 | 北京三快在线科技有限公司 | Data fusion method and device, unmanned equipment and readable storage medium |
CN112101092A (en) * | 2020-07-31 | 2020-12-18 | 北京智行者科技有限公司 | Automatic driving environment sensing method and system |
CN112327326A (en) * | 2020-10-15 | 2021-02-05 | 深圳华芯信息技术股份有限公司 | Two-dimensional map generation method, system and terminal with three-dimensional information of obstacles |
CN113192091A (en) * | 2021-05-11 | 2021-07-30 | 紫清智行科技(北京)有限公司 | Long-distance target sensing method based on laser radar and camera fusion |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113777622B (en) * | 2021-08-31 | 2023-10-20 | 通号城市轨道交通技术有限公司 | Rail obstacle identification method and device |
-
2021
- 2021-08-31 CN CN202111011733.1A patent/CN113777622B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109298415A (en) * | 2018-11-20 | 2019-02-01 | 中车株洲电力机车有限公司 | A kind of track and road barricade object detecting method |
CN109814112A (en) * | 2019-01-15 | 2019-05-28 | 北京百度网讯科技有限公司 | A kind of ultrasonic radar and laser radar information fusion method and system |
CN110239592A (en) * | 2019-07-03 | 2019-09-17 | 中铁轨道交通装备有限公司 | A kind of active barrier of rail vehicle and derailing detection system |
CN110481601A (en) * | 2019-09-04 | 2019-11-22 | 深圳市镭神智能***有限公司 | A kind of rail detection system |
CN111257882A (en) * | 2020-03-19 | 2020-06-09 | 北京三快在线科技有限公司 | Data fusion method and device, unmanned equipment and readable storage medium |
CN112101092A (en) * | 2020-07-31 | 2020-12-18 | 北京智行者科技有限公司 | Automatic driving environment sensing method and system |
CN112327326A (en) * | 2020-10-15 | 2021-02-05 | 深圳华芯信息技术股份有限公司 | Two-dimensional map generation method, system and terminal with three-dimensional information of obstacles |
CN113192091A (en) * | 2021-05-11 | 2021-07-30 | 紫清智行科技(北京)有限公司 | Long-distance target sensing method based on laser radar and camera fusion |
Non-Patent Citations (2)
Title |
---|
肖添文等: "城市轨道交通障碍物检测及列车控制技术", 兵器装备工程学报 * |
赵一兵;王荣本;李琳辉;郑可勤;张如高;: "基于多传感器信息的前方障碍物检测", 计算机工程与应用 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113777622B (en) * | 2021-08-31 | 2023-10-20 | 通号城市轨道交通技术有限公司 | Rail obstacle identification method and device |
CN116922448A (en) * | 2023-09-06 | 2023-10-24 | 湖南大学无锡智能控制研究院 | Environment sensing method, device and system for high-speed railway body-in-white transfer robot |
CN116922448B (en) * | 2023-09-06 | 2024-01-02 | 湖南大学无锡智能控制研究院 | Environment sensing method, device and system for high-speed railway body-in-white transfer robot |
Also Published As
Publication number | Publication date |
---|---|
CN113777622B (en) | 2023-10-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11915470B2 (en) | Target detection method based on fusion of vision, lidar, and millimeter wave radar | |
US20230014874A1 (en) | Obstacle detection method and apparatus, computer device, and storage medium | |
US20210124013A1 (en) | Signal processing apparatus, signal processing method, and program | |
CN108271408B (en) | Generating three-dimensional maps of scenes using passive and active measurements | |
CN111192295B (en) | Target detection and tracking method, apparatus, and computer-readable storage medium | |
CN113777622B (en) | Rail obstacle identification method and device | |
CN109946703B (en) | Sensor attitude adjusting method and device | |
CN111427374B (en) | Airplane berth guiding method, device and equipment | |
CN109213138B (en) | Obstacle avoidance method, device and system | |
EP4089660A1 (en) | Method and device for monitoring port and ship in consideration of sea level | |
KR102265980B1 (en) | Device and method for monitoring ship and port | |
JP2019191133A (en) | Position estimating device | |
KR102466804B1 (en) | Autonomous navigation method using image segmentation | |
CN111257882B (en) | Data fusion method and device, unmanned equipment and readable storage medium | |
CN110341621B (en) | Obstacle detection method and device | |
CN113646804A (en) | Object detection device | |
CN114241177A (en) | Airport pavement apparent image detection system based on linear array scanning imaging | |
KR20210090573A (en) | Method and device for monitoring harbor and ship considering sea level | |
Steinbaeck et al. | Occupancy grid fusion of low-level radar and time-of-flight sensor data | |
CN111273314A (en) | Point cloud data processing method and device and storage medium | |
CN113763262A (en) | Application method of vehicle body filtering technology in point cloud data of automatic driving mine truck | |
CN112651405B (en) | Target detection method and device | |
CN115965847A (en) | Three-dimensional target detection method and system based on multi-modal feature fusion under cross view angle | |
CN113895482B (en) | Train speed measuring method and device based on trackside equipment | |
CN115359332A (en) | Data fusion method and device based on vehicle-road cooperation, electronic equipment and system |
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 |