CN111028455A - System and method for detecting foreign matters in gap between train door and platform door - Google Patents
System and method for detecting foreign matters in gap between train door and platform door Download PDFInfo
- Publication number
- CN111028455A CN111028455A CN201911365150.1A CN201911365150A CN111028455A CN 111028455 A CN111028455 A CN 111028455A CN 201911365150 A CN201911365150 A CN 201911365150A CN 111028455 A CN111028455 A CN 111028455A
- Authority
- CN
- China
- Prior art keywords
- stack
- target data
- data set
- suspicious target
- jumping
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a system and a method for detecting foreign matters in a gap between a train door and a platform door, which comprises the following steps: the system comprises a supplementary lighting camera shooting subsystem, an intelligent video analysis system, an alarm subsystem and a client; the intelligent video analysis system is respectively in communication connection with the light supplementing camera shooting subsystem, the alarm subsystem and the client; the client is used for logging in and checking historical alarm data by a client; the intelligent video analysis system is used for video analysis and data storage; the invention solves the problems of complex installation and deployment, limited scene and high false detection alarm rate of the existing foreign matter detection system.
Description
Technical Field
The invention belongs to the field of communication, and particularly relates to a system and a method for detecting foreign matters in a gap between a train door and a platform door.
Background
At present, methods for detecting whether foreign matters exist in a gap between a train door and a platform door comprise an infrared correlation-based system, a laser detection-based system, a traditional video detection technology and the like.
The infrared correlation mode has the following problems: the energy of the light source is not concentrated and is easy to diffuse, and the penetration force of the light source is easy to be weakened by weather interference under natural weather such as rain, fog, strong light and the like, so that the operation of the product is greatly influenced; the interference of animals such as trees, birds and the like can cause the immediate attenuation of infrared emission intensity or beam deviation, and a receiving end cannot receive a complete beam, so that false alarm can be frequently caused; the installation and application places are limited, and the two receiving ends of the infrared correlation product need to completely receive infrared rays, so that the installation environment is very harsh.
The laser correlation system belongs to the active intrusion detector class, and is composed of a laser transmitter and a laser receiver. And arranging a laser emission host at the starting end of the protection area, and directly emitting the directional laser beam emitted by the laser emission host to a receiver. The received optical signal is converted into a switching value signal through the photoelectric device and the chip at the receiver, and the switching value signal is processed by the discriminator. When the signal is confirmed to be normal, the receiving host works normally and keeps a monitoring state; when the light beam is interrupted, the signal is abnormal and an alarm switch signal is output.
In practical application on railways, the laser correlation detection system has the following problems: due to ground settlement, the laser transmitter and the laser receiver are not positioned on the same horizontal plane, and the transmitted light beams cannot be transmitted to the receiver, so that the system function is failed; the installation and application places are limited, the laser transmitters and the receivers need to be extended out of the support for deployment, the support easily affects the safety of the train, and the support is made into a rocker arm type in part of stations, so that the service life of the rocker arm type support is short; the system cannot check the field environment at the alarm moment and needs the assistance of a camera; when the clearance between the train door and the shield door is large, multiple groups of laser equipment need to be deployed for improving the detection precision.
Based on the traditional video detection technology, foreign object target detection, namely whether an object moving or static relative to a background image exists or not is detected from a video data image, and the method is also called foreground extraction. The optical flow method uses the change of pixels in image data in time domain and the correlation between adjacent frames to find the corresponding relation between the previous frame and the current frame, and calculates the motion information of the object between the adjacent frames, which is greatly influenced by noise, obstruction and the like, and has complex operation and large calculation amount. The background difference method subtracts the current frame image from the background image, and then binarizes to obtain a difference image, thereby extracting a target area different from the background image. The method is simple in principle, easy to implement and high in detection speed, but the background image in the actual scene needs to be continuously updated due to dynamic changes of weather illumination and the like. The interframe difference method carries out difference operation on two adjacent frames of images in the video data images, and extracts a moving target by comparing the difference between frames. The method has simple algorithm, is insensitive to the change of light rays, has strong environment adaptability, but has larger influence on the detection result by the motion speed of the target and the time interval between the differential frames.
The video judgment system is used for judging a strategy based on a video, acquiring a light band arranged at the tail end of the platform according to a camera at the foremost end of the platform, judging whether a gap is safe according to whether the light band is complete, and outputting an alarm signal to other systems when the light band is incomplete. The disadvantages of this method are as follows: the principle of the inspection technology is similar to laser correlation, the inspection range is a line segment between a camera and a light band, and the inspection range is small; the method is influenced by factors such as illumination, shadow and the like, and has more false alarms; when small foreign matters exist between the gaps, the visual channel between the camera and the optical band is not shielded, and the missing report is easy to occur.
Disclosure of Invention
Aiming at the defects in the prior art, the system and the method for detecting the foreign matters in the gap between the train door and the platform door provided by the invention solve the problems of large calculation amount and high detection error rate of the conventional foreign matter detection system.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that: a system for detecting a foreign object in a gap between a train door and a platform door comprising: the system comprises a supplementary lighting camera shooting subsystem, an intelligent video analysis system, an alarm subsystem and a client;
the intelligent video analysis system is respectively in communication connection with the light supplementing camera shooting subsystem, the alarm subsystem and the client;
the client is used for logging in and checking historical alarm data by a client;
the intelligent video analysis system is used for video analysis and data storage;
the light supplementing camera shooting subsystem is used for acquiring image data between a vehicle door and a platform gap;
and the alarm subsystem is used for receiving the foreign matter alarm signal sent by the intelligent video analysis system and giving an alarm.
Further: the light supplementing camera shooting subsystem comprises a plurality of groups of light supplementing lamps and cameras, and each camera is matched with one group of light supplementing lamps; the camera is disposed directly above the gap between the door and the platform, and the camera probe looks down to the front and extends toward the gap.
A method of detecting a foreign object in a gap between a train door and a platform door, comprising the steps of:
s1, opening a memory space in the intelligent video analysis system, establishing a background stack, a foreign matter stack and a suspicious target stack, prestoring complete video image data without foreign matters at the gap between a train door and a platform door of one frame in the background stack, and setting the suspicious target stack and the foreign matter stack to be empty;
s2, capturing video images at the gap between the train door and the platform door through the light supplementing camera shooting subsystem to obtain a high-definition video stream, and transmitting the high-definition video stream to the intelligent video analysis system;
s3, establishing a video analysis processing model by adopting a YOLOv2 algorithm and a ResNets residual neural network, and processing a high-definition video stream through an intelligent video analysis system according to the video analysis processing model to obtain a detection target data set;
s4, calculating the overlapping degree of the detection target data set with the data stored in the background stack and the data stored in the suspicious target stack respectively to obtain the overlapping degree of the detection target data set with the background stack and the overlapping degree of the detection target data set with the suspicious target stack;
s5, judging whether the overlapping degree of the detection target data set and the background stack is larger than a background overlapping degree threshold value, if so, jumping to the step S6, and if not, jumping to the step S7;
s6, judging that the detection target data set is background data, discarding the data, and jumping to the step S2;
s7, judging whether the overlapping degree of the detection target data set and the suspicious target stack is larger than the threshold value of the overlapping degree of the suspicious target, if so, jumping to the step S9, and if not, jumping to the step S8;
s8, recording the target data set as historical suspicious target data, storing the historical suspicious target data into a suspicious target stack, recording the time of the storage moment, and jumping to the step S2;
s9, judging that the detection target data set is suspicious target data, detecting whether historical suspicious target data which are the same as suspected foreign matters shown by the suspicious target data exist in a suspicious target stack, if so, jumping to S11, and if not, jumping to S10;
s10, recording the suspicious target data set as historical suspicious target data, storing the historical suspicious target data into a suspicious target stack, recording the time of the storage moment, and jumping to the step S2;
s11, calculating the difference value between the time of the historical suspicious target data stored in the stack and the current time, and judging whether the difference value exceeds a static time threshold value, if so, jumping to the step S12, and if not, jumping to the step S2;
s12, filtering the class value of the historical suspicious target data, judging that the historical suspicious target data are foreign matter data, storing the historical suspicious target data into a foreign matter stack, and transmitting a foreign matter signal to an alarm subsystem and a client through an intelligent video analysis system;
s13, judging whether the foreign matter data disappear, if so, tracking and timing the time when the foreign matter disappears, and jumping to the step S14, otherwise, jumping to the step S2;
s14, judging whether the tracking and timing time exceeds a disappearance time threshold value, if so, deleting historical suspicious target data corresponding to the foreign object data in the foreign object stack, removing the foreign object, and sending a foreign object signal removal signal to the client through the intelligent video analysis system; if not, the process goes to step S2.
Further: in step S2, the communication protocol between the supplementary lighting camera subsystem and the intelligent video analysis system is the RTSP protocol.
Further: the calculation formula for obtaining the overlapping degree of the detection target data set and the background stack in step S4 is
Wherein, the IOU(X,Y)For detecting the targetThe degree of overlap of the data set with the background stack,for detecting the ith object X of the object data setiThe area of (a) is,for the jth target Y in the background stackjThe area of (a).
Further: in step S4, the calculation formula for the overlap degree between the detection target data set and the data stored in the suspicious target stack is:
wherein, the IOU(X,Z)To detect the degree of overlap of the target data set with the suspect target stack,for detecting the ith object X of the object data setiThe area of (a) is,for the kth target Z in the suspicious target stackkThe area of (a).
The invention has the beneficial effects that: the system acquires a video image through the camera, processes a target data set on the video image, overcomes the problem that an infrared correlation mode and an installation scene of a laser correlation system are limited, calculates the overlapping degree of the target data set with a background stack and a suspicious target stack, judges whether a target in the target data set belongs to a background, a suspicious target or a new suspicious target, and reduces the calculation difficulty; if in a certain time quantum, the suspicious target that appears continuously, then classify as the foreign matter, reduced the error rate that detects to the time to the foreign matter disappearance is made the track, in time feeds back the foreign matter condition in train door and platform door clearance department, prevents unexpected the emergence.
Drawings
FIG. 1 is a block diagram of a system for detecting a foreign object in a gap between a train door and a platform door;
FIG. 2 is a flow chart of a method for detecting a foreign object in a gap between a train door and a platform door.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
As shown in fig. 1, a system for detecting a foreign object in a gap between a train door and a platform door includes: the system comprises a supplementary lighting camera shooting subsystem, an intelligent video analysis system, an alarm subsystem and a client;
the intelligent video analysis system is respectively in communication connection with the light supplementing camera shooting subsystem, the alarm subsystem and the client;
the client is used for logging in and checking historical alarm data by a client;
the intelligent video analysis system is used for video analysis and data storage;
the light supplementing camera shooting subsystem is used for acquiring image data between a vehicle door and a platform gap;
and the alarm subsystem is used for receiving the foreign matter alarm signal sent by the intelligent video analysis system and giving an alarm.
The light supplementing camera shooting subsystem comprises a plurality of groups of light supplementing lamps and cameras, and each camera is matched with one group of light supplementing lamps; the camera is disposed directly above the gap between the door and the platform, and the camera probe looks down to the front and extends toward the gap.
As shown in fig. 2, a method for detecting a foreign object in a gap between a train door and a platform door, includes the steps of:
s1, opening a memory space in the intelligent video analysis system, establishing a background stack, a foreign matter stack and a suspicious target stack, prestoring complete video image data without foreign matters at the gap between a train door and a platform door of one frame in the background stack, and setting the suspicious target stack and the foreign matter stack to be empty;
s2, capturing video images at the gap between the train door and the platform door through the light supplementing camera shooting subsystem to obtain a high-definition video stream, and transmitting the high-definition video stream to the intelligent video analysis system;
s3, establishing a video analysis processing model by adopting a YOLOv2 algorithm and a ResNets residual neural network, and processing a high-definition video stream through an intelligent video analysis system according to the video analysis processing model to obtain a detection target data set;
s4, calculating the overlapping degree of the detection target data set with the data stored in the background stack and the data stored in the suspicious target stack respectively to obtain the overlapping degree of the detection target data set with the background stack and the overlapping degree of the detection target data set with the suspicious target stack;
s5, judging whether the overlapping degree of the detection target data set and the background stack is larger than a background overlapping degree threshold value, if so, jumping to the step S6, and if not, jumping to the step S7;
s6, judging that the detection target data set is background data, discarding the data, and jumping to the step S2;
s7, judging whether the overlapping degree of the detection target data set and the suspicious target stack is larger than the threshold value of the overlapping degree of the suspicious target, if so, jumping to the step S9, and if not, jumping to the step S8;
s8, recording the target data set as historical suspicious target data, storing the historical suspicious target data into a suspicious target stack, recording the time of the storage moment, and jumping to the step S2;
s9, judging that the detection target data set is suspicious target data, detecting whether historical suspicious target data which are the same as suspected foreign matters shown by the suspicious target data exist in a suspicious target stack, if so, jumping to S11, and if not, jumping to S10;
s10, recording the suspicious target data set as historical suspicious target data, storing the historical suspicious target data into a suspicious target stack, recording the time of the storage moment, and jumping to the step S2;
s11, calculating the difference value between the time of the historical suspicious target data stored in the stack and the current time, and judging whether the difference value exceeds a static time threshold value, if so, jumping to the step S12, and if not, jumping to the step S2;
s12, filtering the class value of the historical suspicious target data, judging that the historical suspicious target data are foreign matter data, storing the historical suspicious target data into a foreign matter stack, and transmitting a foreign matter signal to an alarm subsystem and a client through an intelligent video analysis system;
s13, judging whether the foreign matter data disappear, if so, tracking and timing the time when the foreign matter disappears, and jumping to the step S14, otherwise, jumping to the step S2;
s14, judging whether the tracking and timing time exceeds a disappearance time threshold value, if so, deleting historical suspicious target data corresponding to the foreign object data in the foreign object stack, removing the foreign object, and sending a foreign object signal removal signal to the client through the intelligent video analysis system; if not, the process goes to step S2.
In step S2, the communication protocol between the supplementary lighting camera subsystem and the intelligent video analysis system is the RTSP protocol.
The calculation formula for obtaining the overlapping degree of the detection target data set and the background stack in step S4 is
Wherein, the IOU(X,Y)To detect the degree of overlap of the target data set with the background stack,for detecting the ith object X of the object data setiThe area of (a) is,for the jth target Y in the background stackjThe area of (a).
In step S4, the calculation formula for the overlap degree between the detection target data set and the data stored in the suspicious target stack is:
wherein, the IOU(X,Z)To detect the degree of overlap of the target data set with the suspect target stack,for detecting the ith object X of the object data setiThe area of (a) is,for the kth target Z in the suspicious target stackkThe area of (a).
The invention has the beneficial effects that: the system acquires a video image through the camera, processes a target data set on the video image, overcomes the problem that an infrared correlation mode and an installation scene of a laser correlation system are limited, calculates the overlapping degree of the target data set with a background stack and a suspicious target stack, judges whether a target in the target data set belongs to a background, a suspicious target or a new suspicious target, and reduces the calculation difficulty; if in a certain time quantum, the suspicious target that appears continuously, then classify as the foreign matter, reduced the error rate that detects to the time to the foreign matter disappearance is made the track, in time feeds back the foreign matter condition in train door and platform door clearance department, prevents unexpected the emergence.
Claims (6)
1. A system for detecting a foreign object in a gap between a train door and a platform door, comprising: the system comprises a supplementary lighting camera shooting subsystem, an intelligent video analysis system, an alarm subsystem and a client;
the intelligent video analysis system is respectively in communication connection with the light supplementing camera shooting subsystem, the alarm subsystem and the client;
the client is used for logging in and checking historical alarm data by a client;
the intelligent video analysis system is used for video analysis and data storage;
the light supplementing camera shooting subsystem is used for acquiring image data between a vehicle door and a platform gap;
and the alarm subsystem is used for receiving the foreign matter alarm signal sent by the intelligent video analysis system and giving an alarm.
2. The system according to claim 1, wherein the fill-in light camera subsystem comprises a plurality of fill-in lights and cameras, each camera being associated with a set of fill-in lights; the camera is disposed directly above the gap between the door and the platform, and the camera probe looks down to the front and extends toward the gap.
3. A method of detecting a foreign object in a gap between a train door and a platform door, comprising the steps of:
s1, opening a memory space in the intelligent video analysis system, establishing a background stack, a foreign matter stack and a suspicious target stack, prestoring complete video image data without foreign matters at the gap between a train door and a platform door of one frame in the background stack, and setting the suspicious target stack and the foreign matter stack to be empty;
s2, capturing video images at the gap between the train door and the platform door through the light supplementing camera shooting subsystem to obtain a high-definition video stream, and transmitting the high-definition video stream to the intelligent video analysis system;
s3, establishing a video analysis processing model by adopting a YOLOv2 algorithm and a ResNets residual neural network, and processing a high-definition video stream through an intelligent video analysis system according to the video analysis processing model to obtain a detection target data set;
s4, calculating the overlapping degree of the detection target data set with the data stored in the background stack and the data stored in the suspicious target stack respectively to obtain the overlapping degree of the detection target data set with the background stack and the overlapping degree of the detection target data set with the suspicious target stack;
s5, judging whether the overlapping degree of the detection target data set and the background stack is larger than a background overlapping degree threshold value, if so, jumping to the step S6, and if not, jumping to the step S7;
s6, judging that the detection target data set is background data, discarding the data, and jumping to the step S2;
s7, judging whether the overlapping degree of the detection target data set and the suspicious target stack is larger than the threshold value of the overlapping degree of the suspicious target, if so, jumping to the step S9, and if not, jumping to the step S8;
s8, recording the target data set as historical suspicious target data, storing the historical suspicious target data into a suspicious target stack, recording the time of the storage moment, and jumping to the step S2;
s9, judging that the detection target data set is suspicious target data, detecting whether historical suspicious target data which are the same as suspected foreign matters shown by the suspicious target data exist in a suspicious target stack, if so, jumping to S11, and if not, jumping to S10;
s10, recording the suspicious target data set as historical suspicious target data, storing the historical suspicious target data into a suspicious target stack, recording the time of the storage moment, and jumping to the step S2;
s11, calculating the difference value between the time of the historical suspicious target data stored in the stack and the current time, and judging whether the difference value exceeds a static time threshold value, if so, jumping to the step S12, and if not, jumping to the step S2;
s12, filtering the class value of the historical suspicious target data, judging that the historical suspicious target data are foreign matter data, storing the historical suspicious target data into a foreign matter stack, and transmitting a foreign matter signal to an alarm subsystem and a client through an intelligent video analysis system;
s13, judging whether the foreign matter data disappear, if so, tracking and timing the time when the foreign matter disappears, and jumping to the step S14, otherwise, jumping to the step S2;
s14, judging whether the tracking and timing time exceeds a disappearance time threshold value, if so, deleting historical suspicious target data corresponding to the foreign object data in the foreign object stack, removing the foreign object, and sending a foreign object signal removal signal to the client through the intelligent video analysis system; if not, the process goes to step S2.
4. The method as claimed in claim 3, wherein the communication protocol between the supplementary lighting camera subsystem and the intelligent video analysis system in step S2 is RTSP.
5. The method according to claim 3, wherein the overlap degree of the detection target data set and the background stack obtained in step S4 is calculated by
6. The method according to claim 3, wherein the overlap between the detection target data set and the data stored in the suspicious target stack in step S4 is calculated by the following formula:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911365150.1A CN111028455A (en) | 2019-12-26 | 2019-12-26 | System and method for detecting foreign matters in gap between train door and platform door |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911365150.1A CN111028455A (en) | 2019-12-26 | 2019-12-26 | System and method for detecting foreign matters in gap between train door and platform door |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111028455A true CN111028455A (en) | 2020-04-17 |
Family
ID=70214605
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911365150.1A Pending CN111028455A (en) | 2019-12-26 | 2019-12-26 | System and method for detecting foreign matters in gap between train door and platform door |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111028455A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104049281A (en) * | 2014-07-02 | 2014-09-17 | 广州市地下铁道总公司 | Device and method for automatically detecting foreign matter between screen door of curve subway platform and train |
CN104691559A (en) * | 2015-03-24 | 2015-06-10 | 江苏科技大学 | Auxiliary system for monitoring safety of region between platform safety door and vehicle door and realization method of auxiliary system |
CN104777521A (en) * | 2015-03-24 | 2015-07-15 | 广州市地下铁道总公司 | Binocular-vision-based detection system for foreign matter between train door and platform shield gate, as well as detection method for detection system |
CN107527009A (en) * | 2017-07-11 | 2017-12-29 | 浙江汉凡软件科技有限公司 | A kind of remnant object detection method based on YOLO target detections |
CN109398370A (en) * | 2018-10-22 | 2019-03-01 | 广州佳都信息技术研发有限公司 | Foreign matter based reminding method, device, equipment, storage medium and system |
CN109447090A (en) * | 2018-10-17 | 2019-03-08 | 宁波中车时代传感技术有限公司 | A kind of shield door obstacle detection method and detection system |
CN109816909A (en) * | 2019-02-26 | 2019-05-28 | 北京疯马科技有限公司 | One kind being based on video identification subway shield door security protection early warning system |
US20190332897A1 (en) * | 2018-04-26 | 2019-10-31 | Qualcomm Incorporated | Systems and methods for object detection |
-
2019
- 2019-12-26 CN CN201911365150.1A patent/CN111028455A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104049281A (en) * | 2014-07-02 | 2014-09-17 | 广州市地下铁道总公司 | Device and method for automatically detecting foreign matter between screen door of curve subway platform and train |
CN104691559A (en) * | 2015-03-24 | 2015-06-10 | 江苏科技大学 | Auxiliary system for monitoring safety of region between platform safety door and vehicle door and realization method of auxiliary system |
CN104777521A (en) * | 2015-03-24 | 2015-07-15 | 广州市地下铁道总公司 | Binocular-vision-based detection system for foreign matter between train door and platform shield gate, as well as detection method for detection system |
CN107527009A (en) * | 2017-07-11 | 2017-12-29 | 浙江汉凡软件科技有限公司 | A kind of remnant object detection method based on YOLO target detections |
US20190332897A1 (en) * | 2018-04-26 | 2019-10-31 | Qualcomm Incorporated | Systems and methods for object detection |
CN109447090A (en) * | 2018-10-17 | 2019-03-08 | 宁波中车时代传感技术有限公司 | A kind of shield door obstacle detection method and detection system |
CN109398370A (en) * | 2018-10-22 | 2019-03-01 | 广州佳都信息技术研发有限公司 | Foreign matter based reminding method, device, equipment, storage medium and system |
CN109816909A (en) * | 2019-02-26 | 2019-05-28 | 北京疯马科技有限公司 | One kind being based on video identification subway shield door security protection early warning system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9984559B2 (en) | Intrusion detection with motion sensing | |
JP3965614B2 (en) | Fire detection device | |
CN102117484B (en) | Processing system, processing method and image classification method using image color information | |
CN104971458A (en) | Multi-fire-source identification method based on automatic tracking and positioning jet fire extinguishing device | |
CN113011252B (en) | Rail foreign matter intrusion detection system and method | |
WO2023221425A1 (en) | Ship lockage safety detection method | |
KR101893875B1 (en) | Behavior Detection System Of Discards Garbage And Behavior Detection Method Of Discards Garbage | |
CN114283544B (en) | Railway platform intrusion monitoring system and method based on artificial intelligence | |
CN106353763A (en) | Laser radar with railway rail surface foreign matter scanning function | |
DE60212991D1 (en) | SAFETY SYSTEM AND WARNING METHOD WITH ROLL RECOGNITION OF AN IMAGE SIGNAL | |
JP4025007B2 (en) | Railroad crossing obstacle detection device | |
CN111028455A (en) | System and method for detecting foreign matters in gap between train door and platform door | |
CN104766422A (en) | Perimeter intruder monitoring system and method | |
KR102507540B1 (en) | Integrated fire monitoring system based on artificial intelligence | |
CN111460949B (en) | Real-time monitoring method and system for preventing external damage of power transmission line | |
CN110481600B (en) | Unmanned autonomous comprehensive alarm system | |
KR101798756B1 (en) | Intrusion Detection System And Method Using Retro Reflector | |
CN105338304A (en) | Tunnel operation safety incident detection system based on video recognition | |
KR20200106810A (en) | System for sensing and control unexpected situation using data fusion | |
CN110633625A (en) | Identification method and system | |
JP4467254B2 (en) | Monitoring device | |
JPH0337356B2 (en) | ||
JP3830616B2 (en) | Image processing device for monitoring | |
KR101596015B1 (en) | Independent building Intrusion Prevention system using Multiple camera | |
CN108986371A (en) | A kind of circumference security protection aware communications method and communication 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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200417 |