CN113486783A - Obstacle detection method and system for rail transit vehicle - Google Patents
Obstacle detection method and system for rail transit vehicle Download PDFInfo
- Publication number
- CN113486783A CN113486783A CN202110752812.1A CN202110752812A CN113486783A CN 113486783 A CN113486783 A CN 113486783A CN 202110752812 A CN202110752812 A CN 202110752812A CN 113486783 A CN113486783 A CN 113486783A
- Authority
- CN
- China
- Prior art keywords
- image
- vehicle
- obstacle
- distance range
- preset distance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims description 37
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000003384 imaging method Methods 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 102100029368 Cytochrome P450 2C18 Human genes 0.000 description 1
- 101000919360 Homo sapiens Cytochrome P450 2C18 Proteins 0.000 description 1
- 241000111040 Micrasema minimum Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003116 impacting effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning, or like safety means along the route or between vehicles or vehicle trains
- B61L23/04—Control, warning, or like safety means along the route or between vehicles or vehicle trains for monitoring the mechanical state of the route
- B61L23/041—Obstacle detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention discloses a method and a system for detecting obstacles in a rail transit vehicle, which are used for acquiring a first image in a first preset distance range in front of the vehicle and acquiring a second image in a second preset distance range in front of the vehicle, wherein the maximum distance from the second preset distance range to the vehicle is greater than the maximum distance from the second preset distance range to the vehicle, the minimum distance from the second preset distance range to the vehicle is less than or equal to the maximum distance from the second preset distance range to the vehicle, and the obstacles existing in a vehicle limit are detected and alarm information is sent out according to the first image and/or the second image. The invention acquires the image in the first preset distance range and the image in the second preset distance range in front of the vehicle, detects whether the obstacle exists in the vehicle limit according to the images acquired from the two distance ranges, and the second preset distance range can be a distance range far away from the vehicle.
Description
Technical Field
The invention relates to the field of machine vision application, in particular to a method and a system for detecting obstacles of a rail transit vehicle.
Background
In the rail transit industry, driving safety must be considered during train operation, wherein obstacles within train operation limits are important factors influencing driving safety. In recent years, it has often occurred that a train operation accident occurs due to a rockfall, a landslide, an abnormal state of a trackside equipment, an intrusion of a pedestrian vehicle or the like into a boundary at an intersection or a station. The obstacle detection system applied to the train observes and pre-warns obstacles in advance by means of a machine vision detection technology so as to achieve the effects of assisting driving and guaranteeing driving safety.
At present, the running speed of a train is higher and higher, the highest running speed of the train in the past urban rail transit is 80km/h, but the running speed is increased from 80km/h to 120km/h by more and more lines at present. With the increase of the running speed, the braking distance of the train is prolonged. Taking 80km/h as an example, when the braking acceleration is-1.2 m/s2The braking distance of the train is 205.8 meters. Taking 120km/h as an example, when the braking acceleration is-1.2 m/s2The braking distance of the train is 463.0 m. In order to ensure the safety of the train, the obstacle detection needs to find the obstacle in advance and send out an early warning signal outside the braking distance Number (n). It can be seen that the high speed line places new demands on the detection distance of obstacles compared to the conventional low speed line.
Disclosure of Invention
The invention aims to provide an obstacle detection method and system for a rail transit vehicle, which can detect obstacles remotely and can be used for vehicles with higher running speed.
In order to achieve the purpose, the invention provides the following technical scheme:
an obstacle detection method for a rail transit vehicle, comprising:
the method comprises the steps of obtaining a first image in a first preset distance range in front of a vehicle and obtaining a second image in a second preset distance range in front of the vehicle, wherein the maximum distance from the second preset distance range to the vehicle is larger than the maximum distance from the second preset distance range to the vehicle, and the minimum distance from the second preset distance range to the vehicle is smaller than or equal to the maximum distance from the second preset distance range to the vehicle;
and detecting an obstacle existing in the vehicle boundary and sending out warning information according to the first image and/or the second image.
Preferably, the first image is a visible light image or an infrared light image, and the second image is a visible light image or an infrared light image.
Preferably, the detecting, from the first image and/or the second image, an obstacle present within the vehicle boundary comprises:
if an object is detected to exist in front of the vehicle according to the second image, mapping the object to the first image according to the matching relation between the second image and the first image;
and according to the position of the object in the first image, if the object is judged to be in the rail running area of the vehicle, determining that an obstacle exists in the vehicle boundary.
Preferably, the detecting, from the first image and/or the second image, an obstacle present within the vehicle boundary comprises:
extracting features of an image, and processing the features of the image by using a preset model to obtain a pre-stored standard image which is most consistent with the shooting position of a camera device corresponding to the image, wherein the standard image is an image without an obstacle in front of a vehicle;
and acquiring a difference image block of the image and the standard image, and detecting the type of the object according to the acquired difference image block.
Preferably, the detecting, from the first image and/or the second image, an obstacle present within the vehicle boundary comprises: and judging whether the obstacle exists on the track according to the continuous condition of the track in the image.
Preferably, the detecting, from the first image and/or the second image, an obstacle present within the vehicle boundary comprises: the images are processed using a trained network to detect the presence of an obstacle within the vehicle boundary, the network being obtained by training images that are free of obstacles within the vehicle boundary.
An obstacle detection system of a rail transit vehicle is used for executing the obstacle detection method of the rail transit vehicle.
Preferably, the vehicle safety monitoring system comprises a first camera device, a second camera device and a processing device, wherein the first camera device is used for acquiring a first image in a first preset distance range in front of the vehicle and transmitting the acquired image to the processing device, the second camera device is used for acquiring a second image in a second preset distance range in front of the vehicle and transmitting the acquired image to the processing device, and the processing device is used for detecting an obstacle existing in a vehicle limit and giving out warning information according to the first image and/or the second image.
Preferably, the first image is a visible light image, the second image is a visible light image, the vehicle further includes a third camera device for acquiring an infrared light image in front of the vehicle, and the processing device is further configured to detect an obstacle present within a vehicle boundary from the acquired infrared light image.
Preferably, the vehicle further comprises a light source for emitting infrared light to the front of the vehicle.
According to the technical scheme, the method and the system for detecting the obstacle of the rail transit vehicle are used for acquiring the first image in the first preset distance range in front of the vehicle and acquiring the second image in the second preset distance range in front of the vehicle, the maximum distance between the second preset distance range and the vehicle is larger than the maximum distance between the second preset distance range and the vehicle, the minimum distance between the second preset distance range and the vehicle is smaller than or equal to the maximum distance between the second preset distance range and the vehicle, and the obstacle existing in the vehicle limit is detected and alarm information is sent out according to the first image and/or the second image.
The invention acquires the image in the first preset distance range in front of the vehicle and the image in the second preset distance range in front of the vehicle, and detects whether the obstacle exists in the vehicle limit according to the images acquired from the two distance ranges, wherein the second preset distance range can be a distance range far away from the vehicle.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an obstacle detection method for a rail transit vehicle according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for detecting an obstacle within a vehicle boundary based on an acquired image according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an obstacle detection system of a rail transit vehicle according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a detection system constructed in accordance with an embodiment of the present invention;
FIG. 5 is a schematic diagram of the arrangement of cameras in an embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention, and it is obvious that the described embodiment is only a part of the embodiment of the present invention, and not all 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, fig. 1 is a flowchart illustrating an obstacle detection method for a rail transit vehicle according to an embodiment of the present invention, where as shown in the figure, the obstacle detection method for a rail transit vehicle includes the following steps:
s10: the method comprises the steps of obtaining a first image in a first preset distance range in front of a vehicle and obtaining a second image in a second preset distance range in front of the vehicle.
The maximum distance from the second preset distance range to the vehicle is larger than the maximum distance from the first preset distance range to the vehicle, and the minimum distance from the second preset distance range to the vehicle is smaller than or equal to the maximum distance from the first preset distance range to the vehicle.
During the travel of the vehicle along the track, an image within a first predetermined distance range in front of the vehicle is acquired, denoted as a first image, and an image within a second predetermined distance range in front of the vehicle is acquired, denoted as a second image.
S11: and detecting an obstacle existing in the vehicle boundary and sending out warning information according to the first image and/or the second image.
The boundary line refers to a contour line which is specified by a vehicle and buildings and equipment adjacent to a route and is not allowed to be exceeded in order to ensure that the vehicle runs on the route safely and prevent the rolling stock from impacting the buildings or the equipment adjacent to the route. Obstacles present within a boundary are objects within the boundary that are potentially threatening the safe driving of the vehicle.
The method for detecting the obstacle of the rail transit vehicle acquires an image in a first preset distance range in front of the vehicle and an image in a second preset distance range in front of the vehicle, and detects whether the obstacle exists in the vehicle limit according to the images acquired from the two distance ranges, wherein the second preset distance range can be a distance range far away from the vehicle.
The obstacle detection method of the present rail transit vehicle will be described in detail below with reference to specific embodiments. Referring to fig. 1, the method for detecting an obstacle of a rail transit vehicle includes the steps of:
s10: the method comprises the steps of obtaining a first image in a first preset distance range in front of a vehicle and obtaining a second image in a second preset distance range in front of the vehicle.
Alternatively, the first image may be a visible light image or an infrared light image, and the second image may be a visible light image or an infrared light image. The sunlight is strong in the daytime environment, the obstacles can be detected by acquiring the visible light image, the infrared light image can be acquired for detection in the environment with weak sunlight, or the visible light image and the infrared light image can be acquired, and the detection is performed by combining the visible light image and the infrared light image, so that the detection accuracy is ensured.
Optionally, the specific settings of the first preset distance range and the second preset distance range may be determined according to the running condition of the vehicle in practical application. For example, the running speed of the current rail motor vehicle is improved to 120km/h from 80km/h mostly, and the braking acceleration is-1.2 m/s2The running speed is 120km/h, and the braking distance is 463.0 meters. Correspondingly, the first preset distance range can be set to be 20-250 m, and the second preset distance range can be set to be 250-500 m.
S11: and detecting an obstacle existing in the vehicle boundary and sending out warning information according to the first image and/or the second image.
Optionally, whether an obstacle exists in the vehicle clearance is detected according to the acquired image by the following method, please refer to fig. 2, where fig. 2 is a flowchart of a method for detecting an obstacle in the vehicle clearance according to the acquired image in the embodiment, and includes the following steps:
s20: and if the object in front of the vehicle is detected according to the second image, mapping the object into the first image according to the matching relation between the second image and the first image.
The second image frame acquired from the far distance is a part of the first image frame acquired from the near distance, and the object detected from the second image is mapped to the first image by finding out a part corresponding to the second image in the first image and obtaining a matching relationship between the second image and the part corresponding to the second image in the first image.
S21: and according to the position of the object in the first image, if the object is judged to be in the rail running area of the vehicle, determining that an obstacle exists in the vehicle boundary.
The rail region is defined as the projection which is delimited on the ground. And after the object is mapped to the first image, judging whether the object is in the track running area according to the position of the object in the image and the track position in the first image. If the object is within the trackbound area, it indicates that the object is within the bound, indicating that an obstacle is present within the vehicle bound.
If the second preset distance range is a distance range far away from the vehicle, when the vehicle runs on a curve section, no rail or only a part of rails may exist in an image acquired from the second preset distance range ahead, and the first preset distance range may be close to the vehicle, the field of view is large, the rails in the first image are complete, and the rail segmentation accuracy is high.
Optionally, the following method may be adopted to detect the obstacle according to the first image or the second image, and specifically includes: extracting features of an image, and processing the features of the image by using a preset model to obtain a pre-stored standard image which is most consistent with the shooting position of a camera device corresponding to the image, wherein the standard image is an image without an obstacle in front of a vehicle; and acquiring a difference image block of the image and the standard image, and then detecting the type of the object according to the acquired difference image block.
The method can be used for acquiring images of obstacles in front of the vehicle acquired by the camera device in the running process of the vehicle in advance, extracting features of the acquired video images, and establishing indexes between the image features and the camera device position when the image is acquired for modeling to obtain a preset model. And for the acquired real-time image, extracting features of the real-time image, processing the features of the real-time image by using a preset model, comparing the features of the real-time image with the preset model, finding out a standard image which is most consistent with the shooting position of the camera device corresponding to the real-time image in the preset model, and considering that the shooting position of the camera device when shooting the real-time image is the same as that when shooting the standard image. And comparing the standard image at the position with the real-time image to obtain a difference image block between the standard image and the real-time image for detection. The method can accurately detect the difference part of the real-time image.
Optionally, the difference image block may be processed and learned by a deep learning method, and the object type may be detected.
Optionally, whether an obstacle exists in the vehicle boundary is detected according to the first image or the second image, and the following method can be adopted: and judging whether the obstacle exists on the track according to the continuous condition of the track in the image. If the acquired image has continuous track, it shows that there is no obstacle on the track, if the acquired image has discontinuous break point on the track, it shows that there is object on the track to shield the track, and there is obstacle on the track to make the track discontinuous in the shot image. The method can detect the small objects existing on the track.
Optionally, whether an obstacle exists in the vehicle boundary is detected according to the first image or the second image, and the following method can be adopted: the images are processed using a trained network to detect the presence of an obstacle within the vehicle boundary, the network being obtained by training images that are free of obstacles within the vehicle boundary.
The training network can be a self-encoder, the self-encoder belongs to one of deep learning, the network adapts to the characteristics of the barrier-free image by performing encoding and decoding training on a large number of barrier-free images, when a barrier appears in the image, the encoding characteristics and the decoding image are abnormal, and whether the barrier exists or not and the position of the barrier are judged according to the abnormal appearance.
Preferably, the method of this embodiment may further include: infrared light is emitted toward the front of the vehicle. Specifically, detecting an obstacle present within the vehicle boundary from the first image and/or the second image may include: whether an obstacle exists is detected according to a light spot image formed by infrared light reflected by an object in the image. In dark light environment such as in the tunnel or under the night condition, the information that visible light image contains is limited, and this embodiment method detects the barrier through acquireing the infrared light image through initiatively replenishing the infrared light, has compensatied the not enough of visible light image, can promote formation of image and detection ability under the environment that bad weather and illumination are not good.
Correspondingly, the embodiment also provides an obstacle detection system of the rail transit vehicle, which is used for executing the obstacle detection method of the rail transit vehicle.
The obstacle detection system of the rail transit vehicle of the embodiment acquires an image in a first preset distance range in front of the vehicle and an image in a second preset distance range in front of the vehicle, and detects whether an obstacle exists in a vehicle limit according to the images acquired from the two distance ranges, wherein the second preset distance range can be a distance range far away from the vehicle, so that the system of the embodiment can remotely detect the obstacle and can be used for vehicles with high running speed.
It should be noted that, in the embodiment, for specific embodiments of acquiring the first image, acquiring the second image, and detecting the obstacle existing in the vehicle boundary according to the first image and/or the second image, reference may be made to the embodiments described in the above obstacle detection method for the rail transit vehicle, and details are not repeated herein.
Referring to fig. 3, fig. 3 is a schematic diagram of an obstacle detection system of a rail transit vehicle according to this embodiment, and as shown in the drawing, the obstacle detection system of the rail transit vehicle includes a first camera device 31, a second camera device 32 and a processing device 30, the first camera device 31 is configured to acquire a first image in a first preset distance range in front of the vehicle and transmit the acquired image to the processing device 30, the second camera device 32 is configured to acquire a second image in a second preset distance range in front of the vehicle and transmit the acquired image to the processing device 30, and the processing device 30 is configured to detect an obstacle existing within a vehicle boundary and issue warning information according to the first image and/or the second image.
Optionally, the first image is a visible light image, the second image is a visible light image, the vehicle further includes a third camera device for acquiring an infrared light image in front of the vehicle, and the processing device is further configured to detect an obstacle present within a vehicle boundary according to the acquired infrared light image.
Further preferably, the system of the present embodiment may further include a light source for emitting infrared light toward the front of the vehicle. In dark light environment such as in the tunnel or under the night condition, the information that visible light image contains is limited, and this embodiment method detects the barrier through acquireing the infrared light image through initiatively replenishing the infrared light, has compensatied the not enough of visible light image, can promote formation of image and detection ability under the environment that bad weather and illumination are not good.
In one embodiment, the track line conditions of the motor vehicle are: line correction: 800m in general and 450m in difficulty; an entrance and exit section line: typically 200 m; difficulty 150 m; the vehicle field line: 150 m. Minimum vertical curve radius: 2000 m.
The performance requirements for obstacle detection are shown in the following table:
referring to fig. 4, fig. 4 is a schematic diagram of a detection system constructed in an embodiment, the obstacle detection system constructed as shown in the figure includes an infrared light source, three cameras, namely a first visible light camera, a second visible light camera and an infrared light camera, a system host and an alarm,
The infrared light source adopts a 850nm waveband light source, the illumination distance reaches 500 meters, and the light spot divergence angle is adjustable at 5-25 degrees. The working wave band of the infrared camera is 850nm, and the focal length is 5 mm-115 mm. The first visible light camera is a near-focus camera, the second visible light camera is a far-focus camera, focal lengths are all variable between 5mm and 115mm, and the focal lengths of the first visible light camera and the second visible light camera need to be adjusted and fixed differently through different actual installation positions. The infrared camera adopts a CMOS imaging sensor, integrates a high-speed camera and a processing board card, and adopts a laser light source as an infrared light source. The combination of the infrared camera and the visible light camera can clearly image under various severe working conditions, and all-weather work is guaranteed. The alarm is an audible and visual alarm, receives an alarm signal of the system host, and generates a signal to remind a driver of paying attention to the existence of the barrier on the track.
Referring to fig. 5, fig. 5 is a schematic layout diagram of cameras according to an embodiment, in which three cameras, i.e., a first visible light camera, a second visible light camera and an infrared light camera, are integrated in an imaging unit. The imaging unit adopts a centrosymmetric hexagon design, wherein a second visible light camera (far focus camera) is arranged above the imaging unit, a first visible light camera (near focus camera) is arranged at the lower left side, and an infrared camera is arranged at the lower right side. The system host can be a self-developed CPCI plug-in box type host, has the characteristics of high storage capacity, high calculation capacity and the like, is connected with the multi-path camera through an Ethernet interface, and performs centralized processing after image data are collected.
In addition, the system host has a storage function, and the hard disk capacity is 2T. And when the storage space is completely occupied, starting an overlay mechanism, and automatically overlaying the earliest recorded video file in a first-in first-out mode. The system is also provided with a perfect log recording function, can comprehensively record the information of the working state, the fault information, the alarm information, the time and the like of the system, and provides credible original data for fault diagnosis and accident analysis of the system. The system also has a positioning function, and after the abnormal condition of the line is detected, the position information of the abnormal condition can be recorded for later check.
The method and the system for detecting the obstacle of the rail transit vehicle provided by the invention are described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (10)
1. An obstacle detection method for a rail transit vehicle, comprising:
The method comprises the steps of obtaining a first image in a first preset distance range in front of a vehicle and obtaining a second image in a second preset distance range in front of the vehicle, wherein the maximum distance from the second preset distance range to the vehicle is larger than the maximum distance from the second preset distance range to the vehicle, and the minimum distance from the second preset distance range to the vehicle is smaller than or equal to the maximum distance from the second preset distance range to the vehicle;
and detecting an obstacle existing in the vehicle boundary and sending out warning information according to the first image and/or the second image.
2. The method of claim 1, wherein the first image is a visible light image or an infrared light image and the second image is a visible light image or an infrared light image.
3. The method of claim 1, wherein detecting an obstacle present within a vehicle boundary from the first image and/or the second image comprises:
if an object is detected to exist in front of the vehicle according to the second image, mapping the object to the first image according to the matching relation between the second image and the first image;
And according to the position of the object in the first image, if the object is judged to be in the rail running area of the vehicle, determining that an obstacle exists in the vehicle boundary.
4. The method of claim 1, wherein detecting an obstacle present within a vehicle boundary from the first image and/or the second image comprises:
extracting features of an image, and processing the features of the image by using a preset model to obtain a pre-stored standard image which is most consistent with the shooting position of a camera device corresponding to the image, wherein the standard image is an image without an obstacle in front of a vehicle;
and acquiring a difference image block of the image and the standard image, and detecting the type of the object according to the acquired difference image block.
5. The method of claim 1, wherein detecting an obstacle present within a vehicle boundary from the first image and/or the second image comprises: and judging whether the obstacle exists on the track according to the continuous condition of the track in the image.
6. The method of claim 1, wherein detecting an obstacle present within a vehicle boundary from the first image and/or the second image comprises: the images are processed using a trained network to detect the presence of an obstacle within the vehicle boundary, the network being obtained by training images that are free of obstacles within the vehicle boundary.
7. An obstacle detection system for a rail transit vehicle, characterized by being configured to perform the obstacle detection method for a rail transit vehicle according to any one of claims 1 to 6.
8. The obstacle detection system of a rail transit vehicle according to claim 7, comprising a first camera device for acquiring a first image in a first preset distance range in front of the vehicle and transmitting the acquired image to a processing device, a second camera device for acquiring a second image in a second preset distance range in front of the vehicle and transmitting the acquired image to the processing device, and a processing device for detecting an obstacle existing within a vehicle boundary and issuing warning information based on the first image and/or the second image.
9. The obstacle detection system of a rail transit vehicle of claim 8, wherein the first image is a visible light image and the second image is a visible light image, further comprising a third camera device for acquiring an infrared light image in front of the vehicle, the processing device being further configured to detect an obstacle present within the vehicle boundary from the acquired infrared light image.
10. The rail transit vehicle obstacle detection system of claim 9, further comprising a light source for emitting infrared light forward of the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110752812.1A CN113486783A (en) | 2021-07-02 | 2021-07-02 | Obstacle detection method and system for rail transit vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110752812.1A CN113486783A (en) | 2021-07-02 | 2021-07-02 | Obstacle detection method and system for rail transit vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113486783A true CN113486783A (en) | 2021-10-08 |
Family
ID=77939675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110752812.1A Pending CN113486783A (en) | 2021-07-02 | 2021-07-02 | Obstacle detection method and system for rail transit vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113486783A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI804113B (en) * | 2021-12-17 | 2023-06-01 | 正修學校財團法人正修科技大學 | Intelligent railway monitoring system and method thereof |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104192174A (en) * | 2014-08-29 | 2014-12-10 | 北京交通大学 | Train early-warning system and train early-warning method |
| JP2016088183A (en) * | 2014-10-31 | 2016-05-23 | 株式会社Ihi | Obstacle detection system and railway vehicle |
| CN207345852U (en) * | 2017-10-12 | 2018-05-11 | 中车青岛四方机车车辆股份有限公司 | A kind of train Safety of Shunting Operation prevention and control system |
| CN108528478A (en) * | 2018-04-02 | 2018-09-14 | 交控科技股份有限公司 | The recognition methods of rail traffic situation and device |
| CN108583622A (en) * | 2018-04-02 | 2018-09-28 | 交控科技股份有限公司 | Recognition methods, device, equipment and the medium of rail traffic situation |
| CN108583620A (en) * | 2018-04-02 | 2018-09-28 | 交控科技股份有限公司 | The processor and early warning system of train assistance tracking early warning |
| CN109188460A (en) * | 2018-09-25 | 2019-01-11 | 北京华开领航科技有限责任公司 | Unmanned foreign matter detection system and method |
| CN110329316A (en) * | 2019-07-29 | 2019-10-15 | 江苏必得科技股份有限公司 | A kind of city rail obstacle detector and detection method |
| CN110412986A (en) * | 2019-08-19 | 2019-11-05 | 中车株洲电力机车有限公司 | A kind of vehicle barrier detection method and 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 |
| CN111198371A (en) * | 2020-03-03 | 2020-05-26 | 杭州中车数字科技有限公司 | Forward-looking obstacle detection system |
| CN111526352A (en) * | 2020-07-02 | 2020-08-11 | 北京大成国测科技有限公司 | Railway foreign matter anti-invasion three-dimensional intelligent recognition robot equipment |
| US20200307661A1 (en) * | 2016-10-20 | 2020-10-01 | Rail Vision Ltd | System and method for object and obstacle detection and classification in collision avoidance of railway applications |
| CN112351928A (en) * | 2018-07-10 | 2021-02-09 | 铁路视像有限公司 | Railway obstacle detection method and system based on track segmentation |
| CN112406960A (en) * | 2020-11-08 | 2021-02-26 | 青岛融创信为技术有限公司 | Active anti-collision system and method for fusion of multiple sensors for subway |
| CN112470456A (en) * | 2018-07-24 | 2021-03-09 | 株式会社东芝 | Camera system for railway vehicle |
-
2021
- 2021-07-02 CN CN202110752812.1A patent/CN113486783A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104192174A (en) * | 2014-08-29 | 2014-12-10 | 北京交通大学 | Train early-warning system and train early-warning method |
| JP2016088183A (en) * | 2014-10-31 | 2016-05-23 | 株式会社Ihi | Obstacle detection system and railway vehicle |
| US20200307661A1 (en) * | 2016-10-20 | 2020-10-01 | Rail Vision Ltd | System and method for object and obstacle detection and classification in collision avoidance of railway applications |
| CN207345852U (en) * | 2017-10-12 | 2018-05-11 | 中车青岛四方机车车辆股份有限公司 | A kind of train Safety of Shunting Operation prevention and control system |
| CN108528478A (en) * | 2018-04-02 | 2018-09-14 | 交控科技股份有限公司 | The recognition methods of rail traffic situation and device |
| CN108583622A (en) * | 2018-04-02 | 2018-09-28 | 交控科技股份有限公司 | Recognition methods, device, equipment and the medium of rail traffic situation |
| CN108583620A (en) * | 2018-04-02 | 2018-09-28 | 交控科技股份有限公司 | The processor and early warning system of train assistance tracking early warning |
| US20190300031A1 (en) * | 2018-04-02 | 2019-10-03 | Traffic Control Technology Co., Ltd | Processor and system for train assistance tracking and early-warning |
| CN112351928A (en) * | 2018-07-10 | 2021-02-09 | 铁路视像有限公司 | Railway obstacle detection method and system based on track segmentation |
| CN112470456A (en) * | 2018-07-24 | 2021-03-09 | 株式会社东芝 | Camera system for railway vehicle |
| CN109188460A (en) * | 2018-09-25 | 2019-01-11 | 北京华开领航科技有限责任公司 | Unmanned foreign matter detection system and method |
| CN110329316A (en) * | 2019-07-29 | 2019-10-15 | 江苏必得科技股份有限公司 | A kind of city rail obstacle detector and detection method |
| CN110412986A (en) * | 2019-08-19 | 2019-11-05 | 中车株洲电力机车有限公司 | A kind of vehicle barrier detection method and 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 |
| CN111198371A (en) * | 2020-03-03 | 2020-05-26 | 杭州中车数字科技有限公司 | Forward-looking obstacle detection system |
| CN111526352A (en) * | 2020-07-02 | 2020-08-11 | 北京大成国测科技有限公司 | Railway foreign matter anti-invasion three-dimensional intelligent recognition robot equipment |
| CN112406960A (en) * | 2020-11-08 | 2021-02-26 | 青岛融创信为技术有限公司 | Active anti-collision system and method for fusion of multiple sensors for subway |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI804113B (en) * | 2021-12-17 | 2023-06-01 | 正修學校財團法人正修科技大學 | Intelligent railway monitoring system and method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111198371A (en) | Forward-looking obstacle detection system | |
| CN100440269C (en) | Intelligent detecting prewarning method for expressway automobile running and prewaring system thereof | |
| US20210073557A1 (en) | Systems and methods for augmenting upright object detection | |
| CN102945603B (en) | Method for detecting traffic event and electronic police device | |
| CN102785661B (en) | Lane departure control system and lane departure control method | |
| JP6332384B2 (en) | Vehicle target detection system | |
| US9020747B2 (en) | Method for recognizing a turn-off maneuver | |
| CN101519981B (en) | Mine locomotive anti-collision early warning system based on monocular vision and early warning method thereof | |
| CN110497939B (en) | Rail transit anti-collision detection system and method | |
| CN102592475A (en) | Crossing traffic early warning system | |
| CN109765571B (en) | Vehicle obstacle detection system and method | |
| KR20170127036A (en) | Method and apparatus for detecting and assessing road reflections | |
| CN107336724A (en) | The high ferro anticollision gear and method that a kind of computer vision and millimeter-wave technology combine | |
| US20140002658A1 (en) | Overtaking vehicle warning system and overtaking vehicle warning method | |
| CN111717243B (en) | Rail transit monitoring system and method | |
| JP2008117073A (en) | Interruption vehicle detection device | |
| JP2018055426A (en) | Target detection system for vehicle | |
| CN108639108B (en) | Locomotive operation safety protection system | |
| CN102923000A (en) | Automobile active backing speed limiting control method based on binocular vision target detection | |
| CN113486783A (en) | Obstacle detection method and system for rail transit vehicle | |
| KR102206223B1 (en) | Method for processing data, apparatus thereof and vehicle control system | |
| CN111627131A (en) | Driving recording device and method with driver auxiliary monitoring warning function | |
| CN112927509A (en) | Road driving safety risk assessment system based on traffic conflict technology | |
| CN114119955A (en) | Method and device for detecting potential dangerous target | |
| WO2022267266A1 (en) | Vehicle control method based on visual recognition, and device |
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 |