CN112417978A - Vision-based method and device for detecting foreign matters between train and shield door - Google Patents
Vision-based method and device for detecting foreign matters between train and shield door Download PDFInfo
- Publication number
- CN112417978A CN112417978A CN202011156804.2A CN202011156804A CN112417978A CN 112417978 A CN112417978 A CN 112417978A CN 202011156804 A CN202011156804 A CN 202011156804A CN 112417978 A CN112417978 A CN 112417978A
- Authority
- CN
- China
- Prior art keywords
- train
- door
- characteristic
- area
- similarity
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
Abstract
The embodiment of the invention provides a method and a device for detecting foreign matters between a train and a shield door based on vision, wherein the method comprises the following steps: acquiring a real-time image of a shielded door area through a camera installed on the shielded door; performing feature extraction on the real-time image of the shielded gate area to obtain a first feature; calculating the similarity between the first characteristic and a pre-stored second characteristic, and if the similarity is greater than a preset threshold value, an obstacle exists between the train and the shielded door; and the second characteristic is obtained by extracting according to the background model when the shielding door has no obstacle. The method can automatically detect the obstacles, effectively reduce the time for a driver to perform manual detection and improve the running efficiency of the train. Meanwhile, the similarity is larger than the preset threshold, the obstacle between the train and the shielding door is judged, the judgment process is simple, the fast calculation of the processor is facilitated, and the accuracy is high.
Description
Technical Field
The invention relates to the technical field of rail transit, in particular to a method and a device for detecting foreign matters between a train and a shield door based on vision.
Background
The rail transit is an important tool for citizens to go out, and is rapidly developed in recent years. However, in the morning and evening rush hour, the density of passengers of rail trains, particularly subway trains, is huge, and accordingly a series of new traffic safety problems are generated. The most prominent one of them is due to foreign objects between the train and the screen door. A gap with a certain width is formed between the train and the shielding door, and when the train runs, safety accidents easily occur in the gap, so that huge economic loss is caused. For example, in a part of subway platforms with high traffic density, there are often accidents in which passengers get caught in their bags, passengers get caught in their luggage, and passengers get caught in their clothes and hair. Although the accidents do not cause serious life safety consequences, the accidents bring huge potential safety hazards to the traveling of passengers, and meanwhile, the safety anxiety is increased to the traveling of the passengers.
In order to avoid the accidents, most of the existing subway trains depend on train drivers to watch manually. The luminous lamp area of looking over train rear of a vehicle department is located mainly through the driver at the train locomotive, and whether complete through observing the lamp area to judge whether there is the pedestrian or whether there is the foreign matter that is pressed from both sides between train and the shield door. However, the train platform is long, and the area between the train and the platform is also long and narrow, so that it is difficult for the driver to reliably judge whether there is a foreign object; meanwhile, the driver has subjective factors such as fatigue and inattention, and the like, so that whether foreign matters exist between the train and the shield door or not is easily judged by mistake; in addition, since the train platform is not a completely straight line in a partial scene, the observation by the driver is not possible.
Based on this background, there is a need for an automatic method for detecting the intrusion of foreign objects between a platform train and a screen door, which can assist a driver in detecting foreign objects and timely discover whether pedestrians or obstacles exist between the platform train and the screen door, so as to ensure the safety of passengers when the passengers go out.
Disclosure of Invention
The embodiment of the invention provides a method and a device for detecting foreign matters between a train and a shield door based on vision, which are used for solving the problems in the prior art.
The embodiment of the invention provides a method for detecting foreign matters between a train and a shield door based on vision, which comprises the following steps: acquiring a real-time image of a shielded door area through a camera installed on the shielded door; performing feature extraction on the real-time image of the shielded gate area to obtain a first feature; calculating the similarity between the first characteristic and a pre-stored second characteristic, and if the similarity is greater than a preset threshold value, an obstacle exists between the train and the shielded door; and the second characteristic is obtained by extracting according to the background model when the shielding door has no obstacle.
According to the method for detecting the foreign matters between the train and the shield door based on the vision, before the real-time image of the shield door area is obtained, the method further comprises the following steps: determining background pixel points according to the multi-frame image of the shielding door area when no obstacle exists; and extracting the features of a background model formed by the background pixel points to obtain the second features.
According to the method for detecting the foreign matters between the train and the screen door based on the vision, the characteristic extraction is carried out on the real-time image of the area of the screen door, specifically, the characteristic extraction is carried out on the real-time image according to the background area corresponding to the background model.
According to the method for detecting the foreign matter between the train and the shielding door based on the vision, the background pixel point is determined according to the multi-frame image of the shielding door area when no obstacle exists, and the method comprises the following steps: taking a plurality of pixels in the neighborhood of each target pixel point of any frame as a sample set, and regarding a received new image frame, if the number of the pixel points in the new image frame is more than a judgment threshold value, taking the target pixel point as a background pixel point.
According to the method for detecting the foreign matter between the train and the shield door based on the vision, after the background pixel point is determined, the method further comprises the following steps: and determining a new target pixel point by using a random sampling method, judging whether the new target pixel point is a background pixel point, and updating a background model result corresponding to the background pixel point.
According to the method for detecting the foreign matter between the train and the screen door based on the vision, the similarity between the first characteristic and a pre-stored second characteristic is calculated, and specifically, the similarity between the first characteristic and the second characteristic is calculated according to the mahalanobis distance between the first characteristic and the second characteristic.
According to the method for detecting the foreign matters between the train and the shield door based on the vision, after the fact that the obstacles exist between the train and the shield door is judged, the method further comprises the step of transmitting the platform area image with the obstacles to a train cab.
The embodiment of the invention also provides a device for detecting foreign matters between a train and a shield door based on vision, which comprises: the acquisition module is used for acquiring a real-time image of a shielded door area through a camera installed on the shielded door; the extraction module is used for extracting the characteristics of the real-time image of the shielding door area to obtain first characteristics; the judging module is used for calculating the similarity between the first characteristic and a pre-stored second characteristic, and if the similarity is greater than a preset threshold value, an obstacle exists between the train and the shielding door; and the second characteristic is obtained by extracting according to the background model when the shielding door has no obstacle.
The embodiment of the invention also provides electronic equipment, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the program, the step of the method for detecting the foreign matters between the vision-based train and the screen door is realized.
Embodiments of the present invention further provide a non-transitory computer readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of any of the above-mentioned vision-based method for detecting a foreign object between a train and a screen door.
The method and the device for detecting the foreign matters between the train and the shield door based on the vision can automatically detect the obstacles, effectively reduce the time for a driver to perform manual detection and improve the running efficiency of the train. Meanwhile, the similarity is larger than the preset threshold, the obstacle between the train and the shielding door is judged, the judgment process is simple, the fast calculation of the processor is facilitated, and the accuracy is high.
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, 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 detecting a foreign object between a train and a screen door based on vision according to an embodiment of the present invention;
FIG. 2 is a schematic view of a camera installation at a single platform screen door in an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a device for detecting foreign matter between a train and a screen door based on vision according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, 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 detecting foreign objects between a vision-based train and a screen door according to an embodiment of the present invention will be described with reference to fig. 1 to 4. Fig. 1 is a schematic flow chart of a method for detecting a foreign object between a train and a shield door based on vision according to an embodiment of the present invention, and as shown in fig. 1, a method for detecting a foreign object between a train and a shield door based on vision according to an embodiment of the present invention includes:
101. and acquiring a real-time image of the shielding door area through a camera installed on the shielding door.
Two industrial cameras are installed in each screen door of a train platform, and fig. 2 is a schematic view of the installation of the cameras at a single platform screen door in the embodiment of the present invention, as shown in fig. 2. The visual angles of the cameras a and b are shot in an opposite inclined mode, the focal length of the cameras is 3mm, the frame rate of the cameras is 25fps, and the two cameras can completely cover all areas in the platform screen door. The whole train platform can contain a plurality of platform screen doors, so two industrial cameras need to be installed in each screen door, and the camera model and the camera installation visual angle in each screen door are kept consistent.
The data of each camera is transmitted to the central processing unit in real time through a network, the whole platform comprises a plurality of platform screen doors, the cameras among the screen doors are connected through a gigabit Ethernet, and finally transmitted to the central processing unit in a machine room for real-time processing. When the data in each shielding gate is output to the central processing unit, data synchronization is carried out, and the data processed subsequently is ensured to be synchronous data. That is, when data of each camera is transmitted, time stamp information of the data transmitted by each camera is recorded, and when the central processing unit processes the data, the data with the latest time stamp of each camera is screened as synchronous data.
102. And performing feature extraction on the real-time image of the shielding door area to obtain a first feature.
The method for extracting the features of the real-time image is not limited, and the extracted features can be a feature vector. Preferably, the region of the real-time image extracted features is consistent with the region of the background model when the features are extracted, so that errors caused by non-background regions are avoided.
103. And calculating the similarity between the first characteristic and a pre-stored second characteristic, and if the similarity is greater than a preset threshold value, an obstacle exists between the train and the shielded door.
Before the detection of foreign matters in the train and the shielding doors, the characteristic extraction is carried out on the image of each shielding door, and a background model of each shielding door is constructed. The background model refers to the image of the screen door area without any movable obstacles. Preferably a model of the area where no other movable objects are in the frame of the screen door. And calculating the similarity of the second characteristic and the first characteristic according to the second characteristic extracted from the background model and the first characteristic extracted from the real-time image, and if the similarity is greater than a preset threshold value, indicating that an obstacle exists between the train and the shielded gate.
The method provided by the embodiment of the invention can be used for automatically detecting the obstacles, effectively reducing the time for a driver to perform manual detection and improving the running efficiency of the train. Meanwhile, the similarity is larger than a preset threshold value, the obstacle between the train and the shielding door is judged, and the accuracy and the real-time performance are high.
Based on the content of the foregoing embodiment, as an optional embodiment, before acquiring the real-time image of the shielded gate area, the method further includes: determining background pixel points according to the multi-frame image of the shielding door area when no obstacle exists; and extracting the features of a background model formed by the background pixel points to obtain the second features.
Specifically, when no person gets on or off the vehicle, a plurality of frames of images in the area of the shielding door are obtained, and at the moment, no obstacle exists at the shielding door. However, it is considered that the acquired image captures more or less foreground images of the shield door area even if there is no obstacle at the shield door. Therefore, there is a need to accurately acquire a background model that contains only the shielded gate area. Through the multiframe images in the shielding door area when no obstacle exists, comparison is carried out, and the background pixel points are generally fixed and unchangeable, so that the background pixel points can be finally determined. And then determining a final background model, and performing feature extraction on the background model to obtain a second feature, thereby ensuring the accuracy of a judgment result.
Based on the content of the foregoing embodiment, as an optional embodiment, the feature extraction is performed on the real-time image of the shielded gate area, specifically, the feature extraction is performed on the real-time image according to a background area corresponding to a background model.
Accordingly, in order to ensure the accuracy of the result, the feature region extracted from the real-time image needs to be consistent with the background model. That is, the real-time image also extracts features in the region corresponding to the background model.
Based on the content of the foregoing embodiment, as an optional embodiment, the determining a background pixel point according to a multi-frame image of a shielding gate area when there is no obstacle includes: taking a plurality of pixels in the neighborhood of each target pixel point of any frame as a sample set, and regarding a received new image frame, if the number of the pixel points in the new image frame is more than a judgment threshold value, taking the target pixel point as a background pixel point.
In the embodiment of the invention, the background model of the area between the train and the shield door is modeled by the ViBe extractor. For each frame of image transmitted into the central server, the pixel value at pixel point x can be expressed as v (x), and the background sample set of the area between the train and the screen door can be expressed as:
M(x)＝{V1,V2,…Vn}
sample set size N, SR(Vx) And representing a region of a certain frame with the target pixel x as the center R as the radius, namely the neighborhood of the target pixel point. If SR(Vx)∩{V1,V2,…Vn}>Zmin(wherein Z isminTo determine the threshold, 50 in the embodiment of the present invention), the pixel point x is considered as a background point. Optionally, the sample set filling is performed by selecting points in 8 neighborhoods with similar spatio-temporal distributions as the values of the sample set. The method is realized based on the Vibe background model, the background model can be obtained by using a small amount of samples, the calculation efficiency is higher, and the foreign matter detection is convenient to carry out in real time.
Based on the content of the foregoing embodiment, as an optional embodiment, after the determining the background pixel point, the method further includes: and determining a new target pixel point by using a random sampling method, judging whether the new target pixel point is a background pixel point, and updating a background model result corresponding to the background pixel point.
Because the environment at the train platform changes along with the change of the light, the background model needs to be updated in order to enable the background to be continuously adapted to the change of the background light. The embodiment of the invention updates the background by using a random sub-sampling method, judges whether to update the sample by a random selection mode, and determines whether to update the neighborhood pixels by a random sampling mode. And after updating, simultaneously updating the background model result corresponding to the background pixel point. The embodiment of the invention determines the new target pixel point by using a random sampling method, judges whether the new target pixel point is a background pixel point or not, and can effectively avoid errors caused by ambient light.
Based on the content of the foregoing embodiment, as an optional embodiment, the similarity between the first feature and a pre-stored second feature is calculated, specifically, the similarity between the first feature and the second feature is calculated according to the mahalanobis distance between the first feature and the second feature.
The visual feature of the real-time image, i.e., the first feature, is denoted as F1, and the background feature, i.e., the second feature, is denoted as F2, and the similarity between the two is calculated by mahalanobis distance. One way to calculate the similarity between the real-time image data and the background is as follows:
dM(F1,F2)＝(F1-F2)T∑-1(F1-F2)
in the above formula, dM(F1, F2) represents the similarity between the live image and the background, and if the measured similarity is smaller than the set threshold (the threshold is 50 in the embodiment of the present invention), no obstacle exists between the platform screen doors, and if the measured similarity is larger than the set threshold, an obstacle exists between the platform screen doors. According to the embodiment of the invention, the Mahalanobis distance between the first feature and the second feature extracted by the background model without the obstacle is calculated, so that the similarity of two unknown sample sets can be effectively calculated.
Based on the content of the above embodiment, as an optional embodiment, after determining that an obstacle exists between the train and the screen door, the method further includes transmitting the platform area image with the obstacle to a train cab. And if the obstacle exists, transmitting the platform area image with the obstacle to a train cab, and then enabling a driver to further perform manual intervention to eliminate the obstacle.
The following describes a device for detecting foreign matter between a train and a screen door based on vision according to an embodiment of the present invention, and the device for detecting foreign matter between a train and a screen door based on vision described below and the method for detecting foreign matter between a train and a screen door based on vision described above may be referred to in correspondence to each other.
Fig. 3 is a schematic structural diagram of a device for detecting a foreign object between a train and a screen door based on vision according to an embodiment of the present invention, and as shown in fig. 3, the device for detecting a foreign object between a train and a screen door based on vision includes: an acquisition module 301, an extraction module 302 and a judgment module 303. The acquisition module 301 is configured to acquire a real-time image of a screen door area through a camera installed on the screen door; the extraction module 302 is configured to perform feature extraction on the real-time image of the shielded gate area to obtain a first feature; the judging module 303 is configured to calculate a similarity between the first feature and a pre-stored second feature, and if the similarity is greater than a preset threshold, an obstacle exists between the train and the screen door.
The device embodiment provided in the embodiments of the present invention is for implementing the above method embodiments, and for details of the process and the details, reference is made to the above method embodiments, which are not described herein again.
The device for detecting the foreign matters between the train and the shield door based on the vision, provided by the embodiment of the invention, can automatically detect the obstacles, effectively reduce the time for a driver to carry out manual detection and improve the running efficiency of the train. Meanwhile, the similarity is larger than the preset threshold, the obstacle between the train and the shielding door is judged, the judgment process is simple, the fast calculation of the processor is facilitated, and the accuracy is high.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 4, the electronic device may include: a processor (processor)401, a communication Interface (communication Interface)402, a memory (memory)403 and a communication bus 404, wherein the processor 401, the communication Interface 402 and the memory 403 complete communication with each other through the communication bus 404. Processor 401 may invoke logic instructions in memory 403 to perform a vision-based method of detecting a foreign object between a train and a screen door, the method comprising: acquiring a real-time image of a shielded door area through a camera installed on the shielded door; performing feature extraction on the real-time image of the shielded gate area to obtain a first feature; calculating the similarity between the first characteristic and a pre-stored second characteristic, and if the similarity is greater than a preset threshold value, an obstacle exists between the train and the shielded door; and the second characteristic is obtained by extracting according to the background model when the shielding door has no obstacle.
In addition, the logic instructions in the memory 403 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.
In another aspect, an embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, and when the program instructions are executed by a computer, the computer is capable of executing the method for detecting the foreign object between the vision-based train and the barrier door provided by the above-mentioned embodiments of the method, where the method includes: acquiring a real-time image of a shielded door area through a camera installed on the shielded door; performing feature extraction on the real-time image of the shielded gate area to obtain a first feature; calculating the similarity between the first characteristic and a pre-stored second characteristic, and if the similarity is greater than a preset threshold value, an obstacle exists between the train and the shielded door; and the second characteristic is obtained by extracting according to the background model when the shielding door has no obstacle.
In yet another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented by a processor to execute the method for detecting a foreign object between a vision-based train and a barrier door provided in the foregoing embodiments, and the method includes: acquiring a real-time image of a shielded door area through a camera installed on the shielded door; performing feature extraction on the real-time image of the shielded gate area to obtain a first feature; calculating the similarity between the first characteristic and a pre-stored second characteristic, and if the similarity is greater than a preset threshold value, an obstacle exists between the train and the shielded door; and the second characteristic is obtained by extracting according to the background model when the shielding door has no obstacle.
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 for detecting foreign matters between a train and a shield door based on vision is characterized by comprising the following steps:
acquiring a real-time image of a shielded door area through a camera installed on the shielded door;
performing feature extraction on the real-time image of the shielded gate area to obtain a first feature;
calculating the similarity between the first characteristic and a pre-stored second characteristic, and if the similarity is greater than a preset threshold value, an obstacle exists between the train and the shielded door;
and the second characteristic is obtained by extracting according to the background model when the shielding door has no obstacle.
2. The method of claim 1, wherein prior to obtaining the real-time image of the area of the screen door, further comprising:
determining background pixel points according to the multi-frame image of the shielding door area when no obstacle exists;
and extracting the features of a background model formed by the background pixel points to obtain the second features.
3. The method for detecting the foreign matter between the vision-based train and the screen door according to claim 1, wherein the characteristic extraction is performed on the real-time image of the area of the screen door, specifically, the characteristic extraction is performed on the real-time image according to the background area corresponding to the background model.
4. The method of claim 2, wherein determining background pixels from the multi-frame image of the barrier-free area of the screen door comprises:
taking a plurality of pixels in the neighborhood of each target pixel point of any frame as a sample set, and regarding a received new image frame, if the number of the pixel points in the new image frame is more than a judgment threshold value, taking the target pixel point as a background pixel point.
5. The method of claim 4, wherein after determining the background pixels, the method further comprises:
and determining a new target pixel point by using a random sampling method, judging whether the new target pixel point is a background pixel point, and updating a background model result corresponding to the background pixel point.
6. The method of claim 1, wherein the similarity between the first characteristic and a pre-stored second characteristic is calculated, specifically, the similarity between the first characteristic and the second characteristic is calculated according to the mahalanobis distance therebetween.
7. The vision-based method of detecting a foreign object between a train and a screen door according to claim 1, further comprising transmitting an image of a platform area having an obstacle to a train cab after determining that the obstacle is present between the train and the screen door.
8. The utility model provides a foreign matter detection device between train and shield door based on vision which characterized in that includes:
the acquisition module is used for acquiring a real-time image of a shielded door area through a camera installed on the shielded door;
the extraction module is used for extracting the characteristics of the real-time image of the shielding door area to obtain first characteristics;
the judging module is used for calculating the similarity between the first characteristic and a pre-stored second characteristic, and if the similarity is greater than a preset threshold value, an obstacle exists between the train and the shielding door;
and the second characteristic is obtained by extracting according to the background model when the shielding door has no obstacle.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method of detecting a foreign object between a vision based train and a screen door as claimed in any one of claims 1 to 7.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the method of detecting a foreign object between a vision based train and a screen door as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011156804.2A CN112417978A (en) | 2020-10-26 | 2020-10-26 | Vision-based method and device for detecting foreign matters between train and shield door |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011156804.2A CN112417978A (en) | 2020-10-26 | 2020-10-26 | Vision-based method and device for detecting foreign matters between train and shield door |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112417978A true CN112417978A (en) | 2021-02-26 |
Family
ID=74840565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011156804.2A Pending CN112417978A (en) | 2020-10-26 | 2020-10-26 | Vision-based method and device for detecting foreign matters between train and shield door |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112417978A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113422907A (en) * | 2021-06-27 | 2021-09-21 | 赣州德业电子科技有限公司 | Off-line supervision system for tower crane driver |
| CN117523318A (en) * | 2023-12-26 | 2024-02-06 | 宁波微科光电股份有限公司 | Anti-light interference subway shielding door foreign matter detection method, device and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190291754A1 (en) * | 2018-03-21 | 2019-09-26 | Traffic Control Technology Co., Ltd | Anti-pinch system and method for platform screen door and train |
| CN110348327A (en) * | 2019-06-24 | 2019-10-18 | 腾讯科技（深圳）有限公司 | Realize the method and device that Articles detecting is left in monitoring scene |
| CN110703350A (en) * | 2019-11-01 | 2020-01-17 | 深圳大学 | Train door and shield door gap foreign matter detection system and method |
| CN111626207A (en) * | 2020-05-27 | 2020-09-04 | 北京伟杰东博信息科技有限公司 | Method and system for detecting intrusion of foreign matters in front of train based on image processing |
-
2020
- 2020-10-26 CN CN202011156804.2A patent/CN112417978A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190291754A1 (en) * | 2018-03-21 | 2019-09-26 | Traffic Control Technology Co., Ltd | Anti-pinch system and method for platform screen door and train |
| CN110348327A (en) * | 2019-06-24 | 2019-10-18 | 腾讯科技（深圳）有限公司 | Realize the method and device that Articles detecting is left in monitoring scene |
| CN110703350A (en) * | 2019-11-01 | 2020-01-17 | 深圳大学 | Train door and shield door gap foreign matter detection system and method |
| CN111626207A (en) * | 2020-05-27 | 2020-09-04 | 北京伟杰东博信息科技有限公司 | Method and system for detecting intrusion of foreign matters in front of train based on image processing |
Non-Patent Citations (1)
| Title |
|---|
| 张文学等: "《大数据挖掘技术及其在医药领域的应用》", 西安：西安电子科技大学出版社, pages: 131 - 135 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113422907A (en) * | 2021-06-27 | 2021-09-21 | 赣州德业电子科技有限公司 | Off-line supervision system for tower crane driver |
| CN113422907B (en) * | 2021-06-27 | 2023-02-07 | 赣州德业电子科技有限公司 | Tower crane driver off-line supervision method and system and readable medium |
| CN117523318A (en) * | 2023-12-26 | 2024-02-06 | 宁波微科光电股份有限公司 | Anti-light interference subway shielding door foreign matter detection method, device and medium |
| CN117523318B (en) * | 2023-12-26 | 2024-04-16 | 宁波微科光电股份有限公司 | Anti-light interference subway shielding door foreign matter detection method, device and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108725440B (en) | Forward collision control method and apparatus, electronic device, program, and medium | |
| US10212397B2 (en) | Abandoned object detection apparatus and method and system | |
| US10818172B2 (en) | Method, device and system for processing startup of preceding vehicle | |
| CN112016414A (en) | Method and device for detecting high-altitude parabolic event and intelligent floor monitoring system | |
| CN110298300B (en) | Method for detecting vehicle illegal line pressing | |
| CN111652296A (en) | Deep learning-based rail wagon lower pull rod fracture fault detection method | |
| CN110458126B (en) | Pantograph state monitoring method and device | |
| CN112417978A (en) | Vision-based method and device for detecting foreign matters between train and shield door | |
| CN112528861A (en) | Foreign matter detection method and device applied to track bed in railway tunnel | |
| CN111553214B (en) | Method and system for detecting smoking behavior of driver | |
| CN112071084A (en) | Method and system for judging illegal parking by utilizing deep learning | |
| CN110309765B (en) | High-efficiency detection method for video moving target | |
| US20220366570A1 (en) | Object tracking device and object tracking method | |
| CN112364898A (en) | Image identification automatic labeling method, device, equipment and storage medium | |
| CN103400113A (en) | Method for detecting pedestrian on expressway or in tunnel based on image processing | |
| CN111079621A (en) | Method and device for detecting object, electronic equipment and storage medium | |
| CN113052047B (en) | Traffic event detection method, road side equipment, cloud control platform and system | |
| CN114445398A (en) | Method and device for monitoring state of side protection plate of hydraulic support of coal mining machine | |
| CN106803937B (en) | Double-camera video monitoring method, system and monitoring device with text log | |
| CN111597992B (en) | Scene object abnormity identification method based on video monitoring | |
| CN111582166B (en) | Method for detecting remnants based on Gaussian modeling and YoLo V3 target detection | |
| WO2023071874A1 (en) | Roadside assistance working node determining method and apparatus, electronic device, and storage medium | |
| CN116152753A (en) | Vehicle information identification method and system, storage medium and electronic device | |
| WO2022267266A1 (en) | Vehicle control method based on visual recognition, and device | |
| CN115100650A (en) | Expressway abnormal scene denoising and identifying method and device based on multiple Gaussian models |
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 |