CN111147821A - Intelligent monitoring method and device for locomotive-mounted video - Google Patents
Intelligent monitoring method and device for locomotive-mounted video Download PDFInfo
- Publication number
- CN111147821A CN111147821A CN202010001231.XA CN202010001231A CN111147821A CN 111147821 A CN111147821 A CN 111147821A CN 202010001231 A CN202010001231 A CN 202010001231A CN 111147821 A CN111147821 A CN 111147821A
- Authority
- CN
- China
- Prior art keywords
- video
- crew
- monitoring
- target
- standard
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention relates to a locomotive-mounted video intelligent monitoring method, which comprises the steps of obtaining a monitoring video collected by a locomotive-mounted camera device; calculating the difference degree between the monitoring video and a standard frame; the standard frame is a video frame for a crew member to carry out standard operation; and sending an alarm prompt when the difference degree is greater than a preset threshold value. In the locomotive-mounted video intelligent monitoring method, by means of online video real-time monitoring, an analyst does not need to monitor all videos, the processing range is reduced, the processing efficiency is improved, the workload of the analyst is effectively saved, the processing resources are reduced, and the safety management of a locomotive service section is realized. In addition, the mode of comparing the monitoring video with the standard frame can more accurately judge the operation of the crew member, improve the monitoring precision and realize effective butt joint, comprehensive coverage and real-time management between the manager and the managed person.
Description
Technical Field
The invention relates to a railway train operation technology, in particular to a locomotive vehicle-mounted video intelligent monitoring method, a locomotive vehicle-mounted video intelligent monitoring device and a computer readable storage medium.
Background
Along with the development of railways in China, the railway transportation safety is more and more emphasized, and the problem of the railway transportation safety is the subject of the constant and unchangeable modern traffic. The locomotive crew member plays a central role in the operation of the locomotive, and the crew member directly determines whether the train can normally operate, accidents occur and the like, so the safety management of the locomotive crew member is important. In the aspect of safety management of locomotive crew members, standardized requirements are made aiming at operation standards of safety key points in the process of the crew member value taking, safety nodes are listed by analyzing a one-time riding standard operation program of the crew member according to a method of system science, for example, operation behavior requirements such as manual more visual inspection and calling response are required before passing through a signal machine and passing through a split phase, window opening is required to confirm before shunting, and the driving safety is ensured by the implementation of the operation behaviors in the daily value taking process. At present, each locomotive crew record pen and locomotive video monitoring are equipped in each locomotive crew department, a management method is formulated, an analysis team is established, and the LKJ special person analysis is combined to supervise the crew to implement the daily operation standard. However, the video monitoring and recording pen device records the video and audio data continuously, namely how long the crew is driving and how long the crew is recording, so that the workload of ground audio and video analysis personnel is huge after dumping, hundreds of crew members exist in each crew section every day, and thousands of crew members take value online to generate massive audio and video data.
However, the analysts all judge whether the current crew operation is standard or not according to experience, and due to long-time monitoring, deviation exists in the crew operation judgment easily, full coverage analysis of all the crews cannot be achieved, operations of some crews are easily omitted, and the crews cannot be prompted timely. Moreover, the monitoring videos are managed afterwards, and the fact is already formed when the problems are found, and even the accidents cannot be recovered. Therefore, the technology for effectively and comprehensively standardizing the driving standardized operation of the crew is provided.
Disclosure of Invention
Based on this, it is necessary to provide a locomotive-mounted video intelligent monitoring method, a locomotive-mounted video intelligent monitoring device and a computer readable storage medium for solving the problem of how to monitor the standardized operation of locomotive crew members.
A locomotive vehicle-mounted video intelligent monitoring method comprises the following steps:
acquiring a monitoring video acquired by a locomotive-mounted camera device;
calculating the difference degree between the monitoring video and a standard frame; the standard frame is a video frame for a crew member to carry out standard operation;
and sending an alarm prompt when the difference degree is greater than a preset threshold value.
The utility model provides a locomotive vehicle-mounted video intelligence monitoring device, includes acquisition module, calculation module and alarm module.
The acquisition module is used for acquiring a monitoring video acquired by the locomotive-mounted camera device; the calculation module is used for calculating the difference degree between the monitoring video and a standard frame; the standard frame is a video frame for a crew member to carry out standard operation; the alarm module is used for sending out an alarm prompt when the difference degree is larger than a preset threshold value.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of the above-mentioned embodiments.
According to the intelligent monitoring method for the locomotive vehicle-mounted video, around a key node for safety operation standardization in the process of locomotive crew taking, the difference degree between the monitoring video and a standard frame is calculated, and when the difference degree is larger than a preset threshold value, an alarm prompt is sent out so as to remind the crew in the current carriage to correct the current error operation on line in real time. Therefore, by means of online video real-time monitoring, an analyst does not need to monitor all videos, the processing range is reduced, the processing efficiency is improved, the workload of the analyst is effectively saved, the processing resources are reduced, and the safety management of a locomotive depot is realized. In addition, the mode of comparing the monitoring video with the standard frame can more accurately judge the operation of the crew member, improve the monitoring precision and realize effective butt joint, comprehensive coverage and real-time management between the manager and the managed person.
Drawings
FIG. 1 is a flow chart of a locomotive onboard video intelligent monitoring method of the present invention in one embodiment thereof;
FIG. 2 is a flow diagram of sub-steps of a locomotive on-board video intelligent monitoring method of the present invention in one embodiment;
FIG. 3 is a flow diagram of sub-steps of a locomotive on-board video intelligent monitoring method of the present invention in one embodiment;
FIG. 4 is a flow diagram of sub-steps of a locomotive on-board video intelligent monitoring method of the present invention in one embodiment;
FIG. 5 is a flow diagram of sub-steps of a locomotive on-board video intelligent monitoring method of the present invention in one embodiment;
FIG. 6 is a block diagram of an on-board video monitoring system for a locomotive in accordance with one embodiment of the present invention;
FIG. 7 is a block diagram of an on-board video intelligent monitoring apparatus for a locomotive in accordance with one embodiment of the present invention;
FIG. 8 is a block diagram of an on-board video intelligent monitoring apparatus for a locomotive of the present invention in one embodiment thereof;
fig. 9 is a structural diagram of the locomotive-mounted video intelligent monitoring device in one embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail by the following embodiments, which are taken in conjunction with the accompanying drawings.
The invention provides an intelligent monitoring method for locomotive-mounted videos. As shown in fig. 1, the locomotive-mounted video intelligent monitoring method includes:
and step S12, acquiring a monitoring video acquired by the locomotive-mounted camera device.
The monitoring video is collected by an on-board camera mounted on the locomotive, and the monitoring video is collected within a preset time period, for example, during the period from the preparation of the locomotive to the starting of the locomotive, the current operation of the crew member is collected by the on-board camera of each locomotive. And the monitoring video collected by the vehicle-mounted camera device is transmitted to the ground monitoring center through the transmission module. The ground monitoring center controls the vehicle-mounted control equipment through the client, and sends monitoring videos collected on the locomotive to the ground in real time through a wireless network channel so that ground analysis personnel can monitor and command temporarily. In one embodiment, a camera of the camera device is connected with the data dump device, and the dump device provides power to complete the monitoring video acquisition in the range of the locomotive. In another embodiment, the camera device further comprises an optical compensation module, and since the ambient light changes rapidly during the high-speed running of the train, the optical compensation module is used for switching the camera or compensating the brightness of the camera at black and white night according to the sensed brightness change of the external light.
Step S14, calculating the difference between the monitoring video and the standard frame. The standard frame is a video frame for a crew member to perform a normative operation.
The standard frame is a video frame for a crew member to perform standard operation, and specifically consists of a plurality of frames of video images for the crew member to demonstrate standard actions. The specific standard operation is determined by 'standard for one-time operation of locomotive crew' operation ', railway locomotive operation rule', railway technical management journey ', railway safety management regulation' and the like, and during the demonstration, the crew operates according to the standard operation in the file and is shot by a camera device or an additional camera device on the locomotive. The monitoring video is compared with the standard frame by calling the standard frame, and then the difference degree between the monitoring video and the standard frame is calculated by the existing algorithm.
Referring to fig. 2, in one embodiment, the difference between the monitoring video and the standard frame can be obtained by the following steps:
step S142, calculating the single-frame difference between each frame of the surveillance video and the standard frame.
Since the video is a group of pictures composed of multiple frames of still pictures, the comparison between the surveillance video and the standard frame can be converted into the comparison between the single-frame surveillance video and the single-frame standard frame, for example, comparing the pixel point of each frame of the surveillance video with the pixel point of the corresponding position in the standard frame, and obtaining the pixel point value of each frame of the surveillance video different from the pixel point of the corresponding position in the standard frame, so as to obtain the single-frame difference.
In a specific embodiment, the monitoring video is first converted into a group of multiple still pictures, and each still picture is preprocessed, for example, the size of each still picture, the pixel point data, and the like are standardized to make the picture meet the input requirement. And then carrying out graying processing on the static picture group of the monitoring video to obtain a plurality of frames of monitoring gray pictures. The gray scale of each frame of the monitoring gray scale picture can be divided into a plurality of gray scale levels so as to distinguish brightness of each pixel point in the picture, and the higher the brightness is, the higher the level is, that is, the pixel points in the monitoring gray scale picture correspond to different gray scale levels due to brightness difference. And sequentially judging whether each pixel point in each frame of monitoring gray level picture is the same as the pixel point at the corresponding position of the standard frame of gray level picture, if so, calculating the number of the pixel points in the frame of monitoring gray level picture, and thus obtaining the difference degree of a single frame.
Step S144, calculating the difference mean value of all frames in the monitoring video according to the difference of the single frame, and determining the difference of the monitoring video and the standard frame.
After the single-frame difference degrees of all the frames of the monitoring video are obtained, the difference degree mean value of the monitoring video is calculated to determine the difference degree of the monitoring video and the standard frame. Specifically, in all frames of the monitored video, the pixels with different gray levels from those of the standard frame are Q1, Q2, Q3 and … … qn in sequence, and the average value of the difference is Q (Q1+ Q2+ Q3+ … … + qn)/n, so that the difference between the monitored video and the standard frame as a whole is obtained.
And step S16, when the difference degree is larger than a preset threshold value, sending out an alarm prompt.
And after the difference degree between the monitoring video and the whole standard frame is obtained, further judging whether the difference degree is greater than a preset threshold value. The preset threshold value is a tolerance deviation value between any operation and standard operation of a crew, and if the difference degree is greater than the preset threshold value, an alarm prompt is sent out; if the difference degree is smaller than the preset threshold value, no alarm prompt is sent out. The specific threshold value can be set to different preset threshold values according to the actual operation of the crew member. For example, in a standard frame, the crew member demonstrates a normative operation in a full-scale inspection project of the locomotive, such as detecting whether the electrical room components are functioning well, the door latch is functioning well, etc., respectively. If the current crew monitoring the video does not do the above operation, the difference between the detected video and the standard frame is large.
The alarm prompt comprises one or more of a character prompt, an alarm bell prompt and a voice prompt.
In one embodiment, the alarm prompt is used for reminding the monitoring personnel of the current abnormal operation of the crew member, so that the monitoring personnel can give an alarm prompt to the crew member of the train through the transmission module. The alarm prompt can be sent by an alarm device arranged in the monitoring center, such as one or more of a buzzer, an audible and visual alarm and a voice alarm.
In another embodiment, the alarm prompt is used to alert a crew member of the locomotive that the current operation is not in specification. The warning prompt may be issued by a warning device mounted on the locomotive, such as one or more of a buzzer, an audible and visual alarm, and a voice alarm. When the crew member on the locomotive receives the alarm prompt, the current operation is corrected in time.
According to the intelligent monitoring method for the locomotive vehicle-mounted video, around a key node for safety operation standardization in the process of locomotive crew taking, the difference degree between the monitoring video and a standard frame is calculated, and when the difference degree is larger than a preset threshold value, an alarm prompt is sent out so as to remind the crew in the current carriage to correct the current error operation on line in real time. Therefore, by means of online video real-time monitoring, an analyst does not need to monitor all videos, the processing range is reduced, the processing efficiency is improved, the workload of the analyst is effectively saved, the processing resources are reduced, and the safety management of a locomotive depot is realized. In addition, the mode of comparing the monitoring video with the standard frame can more accurately judge the operation of the crew member, improve the monitoring precision and realize effective butt joint, comprehensive coverage and real-time management between the manager and the managed person.
Referring to fig. 3, in an embodiment, before acquiring the monitoring video collected by the camera device on board the locomotive, the method further includes:
and step S112, acquiring an original video for the crew to perform the standard operation.
Video of the crew's operations according to the locomotive crew specifications is captured to obtain raw video, which is then further processed.
Step S114, separates the crew target from the original video.
After the raw video is input, the crew targets are separated using existing algorithms.
In one embodiment, the background image in the original video is extracted by a background reconstruction method, and the crew target is separated by a gaussian background difference algorithm. Specifically, after inputting the frame sequence of the original video, a background reconstruction algorithm, such as a gaussian background reconstruction algorithm or a mixed gaussian background model extraction algorithm, is used to extract a background image from the original video. And then carrying out difference operation on the extracted background image and the original video through a Gaussian background difference algorithm so as to separate out the crew target in the original video.
And step S116, determining standard target information corresponding to the crew target in each frame of original video. Wherein the standard object information comprises temporal information and spatial information of the occurrence of the crew object in the original video.
Wherein, the standard target information and the crew target have a one-to-one correspondence relationship.
The time information in the standard object information includes the time of occurrence, the length of time of occurrence, of the crew object in the original video, which is used to locate the position in the original video where the crew object occurs.
The spatial information in the standard object information includes the proportional size of the crew object in the original video image, and the position of the characteristic objects (e.g., hand features, head features) in the crew object in the original video image, which are used to determine the type of current operation of the crew object, such as checking the operation of the electrical room components and their door latch functions, checking the operation of the machine room components and their door latch functions, and the like.
After the crew target is separated, the temporal information and the spatial information of the crew target appearing in the original video are correlated to determine the standard target information corresponding to the crew target.
And step S118, fusing multi-frame crew targets and corresponding standard target information to obtain standard frames.
And fusing the crew target and the corresponding standard target information in each frame of original video to obtain a standard frame consisting of video images of multiple frames of crew demonstration standard actions.
In one embodiment, a plurality of frames of the crew target and corresponding standard target information are fused via a scalable image fusion technique.
The scalable image fusion technology is used for fusing the multi-frame separated crew target and the corresponding standard target information. Specifically, the scalable image fusion technology establishes target objects for the crew targets in each frame, each crew target object contains standard target information of the crew target, and then fusion of the crew targets separated by multiple frames is realized through an object-oriented program to obtain multiple frame standard frames with complete information.
In one embodiment, after step S118, the method further includes the following steps:
the crew target, standard target information corresponding to the crew target, and standard frames are stored.
For different types of crew operation specifications, standard frames corresponding to different types may be established. The crew target and the corresponding standard target information are stored in an index file or database table mode, and can be stored in the storage device of the monitoring center or the cloud.
Referring to fig. 4, in one embodiment, after the step S12 obtains the surveillance video collected by the locomotive-mounted camera device, before the step S14 calculates the difference between the surveillance video and the standard frame, the method further includes the following steps:
step S132, judging whether the crew target exists in the monitoring video by adopting a preset classification detector.
In step S134, if yes, the crew target is separated from the monitoring video.
In step S136, the crew target and the monitoring target information corresponding to the crew target are determined. The monitoring target information comprises time information and space information of the appearance of the crew target in the monitoring video.
The monitoring target information and the crew targets in the monitoring video have a one-to-one correspondence relationship.
The time information of the monitoring target information comprises the time when the crew target appears in the monitoring video and the time length of the appearance, and is used for positioning the position where the crew target appears in the monitoring video.
The spatial information in the monitoring target information includes the proportion of the crew target in the monitoring video image, and the position of the characteristic target (such as hand characteristics and head characteristics) in the crew target in the monitoring video image, which is used to determine the type of current operation of the crew target, such as checking operation of the electrical room components and their door lock functions, checking operation of the machine room components and their door lock functions, and the like.
After the crew target is separated, the temporal information and the spatial information of the crew target appearing in the original video are correlated to determine the standard target information corresponding to the crew target.
Step S134 is carried out by judging whether the crew target exists in the monitoring video or not and judging whether the crew target exists in the monitoring video; and when the condition that no crew target exists in the monitoring video is judged, the comparison operation is not carried out. Therefore, processing steps are reduced, and processing resources are saved.
Referring to fig. 5, in one embodiment, the step S132 of determining whether the crew target exists in the monitoring video by using a preset classification detector includes the following steps:
step S1322 is to extract a histogram of oriented gradient HOG feature from the positive and negative samples of each type of object.
In step S1324, the HOG feature of the crew target is extracted from the input video frame of the crew target.
And S1326, putting the HOG features of the obtained positive and negative samples into a Support Vector Machine (SVM) for training to obtain a feature template of each crew target.
And step S1328, matching the obtained feature template with the extracted HOG feature of the crew target, and determining the type of the detected target according to a preset matching degree threshold. For example, when the degree of matching between the separated detection target and the characteristic template of the crew target reaches or exceeds 85%, the type of the detection target is determined as the crew target.
The operation type of the current crew target is judged through the monitoring target information of the monitoring video and is compared with the corresponding standard frames, so that the steps of comparing the current detection video with the standard frames of different types in sequence can be reduced, the processing steps can be further reduced, and the processing resources are saved.
Referring to fig. 6, the present invention further provides an intelligent locomotive-mounted video monitoring apparatus 100, which includes an obtaining module 10, a calculating module 20 and an alarm module 30.
The acquisition module 10 is used for acquiring a monitoring video acquired by a locomotive-mounted camera device. The calculating module 20 is configured to calculate a difference between the monitoring video and the standard frame; the standard frame is a video frame for a crew member to perform a normative operation. The alarm module 30 is configured to send an alarm prompt when the difference degree is greater than a preset threshold value.
For specific limitations of the locomotive onboard video intelligent monitoring device 100, reference may be made to the above limitations of the locomotive onboard video intelligent monitoring method, which are not described herein again. All or part of the modules in the locomotive-mounted video intelligent monitoring device 100 can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Referring to fig. 7, in one embodiment, the calculation module 20 includes a first calculation unit 21 and a second calculation unit 22.
The first calculation unit 21 is used for calculating the single-frame difference degree between the crew target in each monitoring video frame and the crew target in the standard frame. The second calculating unit 22 is configured to calculate a mean difference between all frames in the monitored video according to the difference between the single frame and the standard frame, and determine the difference between the monitored video and the standard frame.
Referring to fig. 8, in one embodiment, the obtaining module 10 includes a obtaining unit 11, a separating unit 12, a determining unit 13, and a fusing unit 14.
The acquisition unit 11 is used for acquiring an original video of a crew member performing a normative operation. The separation unit 12 is used to separate the crew objects from the original video. The determination unit 13 is used to determine a crew goal and standard goal information corresponding to the crew goal. Wherein the standard object information comprises temporal information and spatial information of the occurrence of the crew object in the original video. The fusion unit 14 is configured to fuse multiple frames of crew targets and corresponding standard target information to obtain a standard frame.
In one embodiment, the vehicle-mounted video intelligent monitoring device 100 further comprises a storage unit for storing the crew target, the standard target information corresponding to the crew target, and the standard frame.
In one embodiment, the fusion unit 14 fuses the multiple frames of crew targets and corresponding standard target information via scalable image fusion techniques.
Referring to fig. 9, in one embodiment, the obtaining module 10 further includes a determining unit 15.
The judging unit 15 is used for judging whether the crew target exists in the monitoring video by adopting a preset classification detector. The separation unit 12 is further configured to separate the crew target from the monitoring video if the determination unit determines that the crew target exists in the monitoring video. The determination unit 13 is also used to determine a crew objective and monitoring objective information corresponding to the crew objective. The monitoring target information comprises time information and space information of the appearance of the crew target in the monitoring video.
In a specific embodiment, the locomotive-mounted camera device comprises a camera, a CCD image sensor, a storage module, a DSP coding module, a power module and a transmission module. The camera is used for collecting a field image and transmitting the field image to the CCD image sensor. After the CCD image sensor receives a field image, the image is converted into a digital signal required by the DSP coding module, the DSP coding module collects, compresses and stores video data into a built-in storage module, the background center sends out an instruction, and the DSP coding module is used for collecting, compressing and sending the video data to the transmission module. If the background center sends voice data for controlling field operation, the DSP coding module decodes the voice data and outputs the decoded voice data to the loudspeaker, and the transmission module is responsible for transmitting the video data to the background center server through a wireless network, receiving voice information for controlling the field operation by the background center and transmitting the voice information to the DSP coding module. And the power supply module is connected with the modules.
The power supply module is a SD card for converting Direct Current (DC) 110V into Direct Current (DC) 12V. The transmission module adopts a multimode parallel transmission mode. The background center comprises a system management module, a real-time streaming media service module, a control service module, a log service module, a digital matrix service module, an alarm forwarding service module, a centralized storage service module, a database service module and a network management service module. The system comprises a system management module, a storage module for scheduling camera shooting, a centralized storage service module of a background center and user configuration information, and is used for performing unified monitoring, management and scheduling distribution; and meanwhile, when the user requests to play the video, the streaming media resources are dynamically scheduled and allocated. And the real-time streaming media service module is used for caching and distributing the video data stream transmitted by the camera to a plurality of video request terminals. When the control service module fails, the real-time streaming media service module realizes the pan-tilt control function; and the control service module is used for realizing the cloud platform control of the front-end equipment. And the log service module is used for storing user operation logs, system logs, service operation logs and the like of the whole system. The digital matrix service module is equal to the client, realizes video decoding through a hardware decoding card, does not occupy CPU resources of a computer, and realizes multi-path image output to a television wall by adopting a client control mode. And the alarm forwarding service module is used for receiving and forwarding alarm information to realize an alarm linkage function. And the centralized storage service module is used for selecting important videos from a plurality of cameras to carry out centralized digital backup work, regularly recording the videos of the lens to the centralized storage service module according to the setting of a user, and providing the videos for the client to inquire information. The database service module is used for providing a database uniform external access interface and providing uniform service for system distribution deployment; and the network management service module is responsible for managing the devices on the network, such as a DVR, an optical transceiver, system services and the like, simultaneously acquiring the working state of the devices, and displaying the working state in the forms of charts, reports and the like. And the alarm forwarding service module is used for automatically checking and playing back videos of the configured user in a linkage manner according to the configuration of the user after the alarm is triggered, and supports the short message sending function. The background center can express the image information acquired by the video transmission equipment in various forms according to the needs, such as outputting the image information to a computer client, a tablet computer, handheld equipment, a mobile phone and the like, so that the leader can conveniently conduct in real time at the background.
The present invention also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
and step S12, acquiring a monitoring video acquired by the locomotive-mounted camera device.
Step S14, calculating the difference between the monitoring video and the standard frame. The standard frame is a video frame for a crew member to perform a normative operation.
And step S16, when the difference degree is larger than a preset threshold value, sending out an alarm prompt.
In one of the embodiments, the computer program, when being executed by the processor, further realizes the steps of the control method in all the other described embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (11)
1. The locomotive vehicle-mounted video intelligent monitoring method is characterized by comprising the following steps:
acquiring a monitoring video acquired by a locomotive-mounted camera device;
calculating the difference degree between the monitoring video and a standard frame; the standard frame is a video frame for a crew member to carry out standard operation;
and sending an alarm prompt when the difference degree is greater than a preset threshold value.
2. The locomotive on-board video intelligent monitoring method according to claim 1, wherein the calculating the difference degree between the monitoring video and the standard frame comprises:
calculating the single-frame difference degree of each frame of the monitoring video and the standard frame;
and calculating the difference mean value of all frames in the monitoring video according to the difference of the single frame, and determining the difference of the monitoring video and the standard frame.
3. The intelligent locomotive video monitoring method according to claim 1, wherein before the acquiring of the monitoring video collected by the locomotive onboard camera device, the method further comprises:
acquiring an original video for a crew to perform standard operation;
separating a crew target from the original video, and determining standard target information corresponding to the crew target in each frame of the original video; wherein the standard target information comprises temporal and spatial information of the occurrence of the crew target in the original video;
and fusing a plurality of frames of the crew targets and the corresponding standard target information to obtain the standard frame.
4. The locomotive on-board video intelligent monitoring method according to claim 3, wherein a plurality of frames of the crew targets and the corresponding standard target information are fused by a scalable image fusion technique.
5. The intelligent locomotive video monitoring method according to claim 3, wherein after the monitoring video collected by the locomotive onboard camera device is obtained, before calculating the difference between the monitoring video and the standard frame, the method further comprises:
judging whether a crew target exists in the monitoring video or not by adopting a preset classification detector;
if yes, separating the crew target from the monitoring video;
determining monitoring target information corresponding to the crew target in each frame of the monitoring video; wherein the monitoring target information includes temporal information and spatial information of the occurrence of the crew target in the monitoring video.
6. The utility model provides a locomotive vehicle-mounted video intelligence monitoring device which characterized in that includes:
the acquisition module is used for acquiring a monitoring video acquired by the locomotive-mounted camera device;
the calculation module is used for calculating the difference degree between the monitoring video and a standard frame; the standard frame is a video frame for a crew member to carry out standard operation;
and the alarm module is used for sending out an alarm prompt when the difference degree is greater than a preset threshold value.
7. The locomotive on-board video intelligent monitoring device according to claim 6, wherein the computing module comprises:
the first calculation unit is used for calculating the single-frame difference degree of the crew target in each frame of the monitoring video and the crew target in the standard frame;
and the second calculating unit is used for calculating the difference mean value of all frames in the monitoring video according to the difference of the single frame and determining the difference of the monitoring video and the standard frame.
8. The locomotive on-board video intelligent monitoring device according to claim 6, wherein the obtaining module comprises:
the acquisition unit is used for acquiring an original video for a crew to perform standard operation;
a separation unit for separating the crew target from the original video;
a determination unit for determining the crew target and standard target information corresponding to the crew target; wherein the standard target information comprises temporal and spatial information of the occurrence of the crew target in the original video;
and the fusion unit is used for fusing a plurality of frames of the crew targets and the corresponding standard target information to obtain the standard frames.
9. The locomotive on-board video intelligent monitoring device according to claim 8, wherein the fusion unit fuses a plurality of frames of the crew target and the corresponding standard target information through a scalable image fusion technique.
10. The locomotive on-board video intelligent monitoring device according to claim 8, wherein the obtaining module further comprises a judging unit for judging whether a crew target exists in the monitoring video by using a preset classification detector;
the separation unit is further used for separating the crew target from the monitoring video if the judgment unit judges that the crew target exists in the monitoring video;
the determining unit is also used for determining the crew target and monitoring target information corresponding to the crew target; wherein the monitoring target information includes temporal information and spatial information of the occurrence of the crew target in the monitoring video.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010001231.XA CN111147821A (en) | 2020-01-02 | 2020-01-02 | Intelligent monitoring method and device for locomotive-mounted video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010001231.XA CN111147821A (en) | 2020-01-02 | 2020-01-02 | Intelligent monitoring method and device for locomotive-mounted video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111147821A true CN111147821A (en) | 2020-05-12 |
Family
ID=70523224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010001231.XA Pending CN111147821A (en) | 2020-01-02 | 2020-01-02 | Intelligent monitoring method and device for locomotive-mounted video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111147821A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112598953A (en) * | 2020-12-30 | 2021-04-02 | 成都运达科技股份有限公司 | Evaluation system and method for crew member based on train driving simulation system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101655907A (en) * | 2009-08-28 | 2010-02-24 | 大连鑫奇辉科技有限公司 | Trainman driving state monitoring intelligent alarm system |
| CN103065121A (en) * | 2012-12-13 | 2013-04-24 | 李秋华 | Engine driver state monitoring method and device based on video face analysis |
| CN106131502A (en) * | 2016-08-16 | 2016-11-16 | 深圳英飞拓科技股份有限公司 | Video frequency monitoring method and device for piping lane tunnel |
| CN108040203A (en) * | 2017-11-30 | 2018-05-15 | 深圳云天励飞技术有限公司 | Operation displaying method, device, Intelligent mirror and computer-readable recording medium |
| CN109545027A (en) * | 2018-12-24 | 2019-03-29 | 郑州畅想高科股份有限公司 | A kind of practical traning platform, crew's simulation training method and device |
| CN110472870A (en) * | 2019-08-15 | 2019-11-19 | 成都睿晓科技有限公司 | A kind of cashier service regulation detection system based on artificial intelligence |
| CN110618635A (en) * | 2019-10-08 | 2019-12-27 | 中兴飞流信息科技有限公司 | Train cab operation specification monitoring system based on AI technology |
-
2020
- 2020-01-02 CN CN202010001231.XA patent/CN111147821A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101655907A (en) * | 2009-08-28 | 2010-02-24 | 大连鑫奇辉科技有限公司 | Trainman driving state monitoring intelligent alarm system |
| CN103065121A (en) * | 2012-12-13 | 2013-04-24 | 李秋华 | Engine driver state monitoring method and device based on video face analysis |
| CN106131502A (en) * | 2016-08-16 | 2016-11-16 | 深圳英飞拓科技股份有限公司 | Video frequency monitoring method and device for piping lane tunnel |
| CN108040203A (en) * | 2017-11-30 | 2018-05-15 | 深圳云天励飞技术有限公司 | Operation displaying method, device, Intelligent mirror and computer-readable recording medium |
| CN109545027A (en) * | 2018-12-24 | 2019-03-29 | 郑州畅想高科股份有限公司 | A kind of practical traning platform, crew's simulation training method and device |
| CN110472870A (en) * | 2019-08-15 | 2019-11-19 | 成都睿晓科技有限公司 | A kind of cashier service regulation detection system based on artificial intelligence |
| CN110618635A (en) * | 2019-10-08 | 2019-12-27 | 中兴飞流信息科技有限公司 | Train cab operation specification monitoring system based on AI technology |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112598953A (en) * | 2020-12-30 | 2021-04-02 | 成都运达科技股份有限公司 | Evaluation system and method for crew member based on train driving simulation system |
| CN112598953B (en) * | 2020-12-30 | 2022-11-29 | 成都运达科技股份有限公司 | Train driving simulation system-based crew member evaluation system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106251578B (en) | Stream of people's early warning analysis method and system based on probe | |
| EP2688296B1 (en) | Video monitoring system and method | |
| US8922659B2 (en) | Dynamically reconfigurable intelligent video surveillance system | |
| CN104200671A (en) | Method and system for managing virtual gate based on big data platform | |
| CN210691345U (en) | Cloud intelligence safety inspection auxiliary system based on degree of depth learning | |
| CN107547617B (en) | Traffic accident information collection method and device | |
| US20180098034A1 (en) | Method of Data Exchange between IP Video Camera and Server | |
| CN113011833A (en) | Safety management method and device for construction site, computer equipment and storage medium | |
| CN106529401A (en) | Vehicle anti-tracking method, vehicle anti-tracking device and vehicle anti-tracking system | |
| CN113378616A (en) | Video analysis method, video analysis management method and related equipment | |
| KR20190041704A (en) | A cctv divided management system and method it | |
| CN115880631A (en) | Power distribution station fault identification system, method and medium | |
| US20190147734A1 (en) | Collaborative media collection analysis | |
| CN111147821A (en) | Intelligent monitoring method and device for locomotive-mounted video | |
| CN110895663B (en) | Two-wheel vehicle identification method and device, electronic equipment and monitoring system | |
| CN117612060A (en) | Video early warning system, method, equipment and medium based on artificial intelligent detection | |
| CN116797993B (en) | Monitoring method, system, medium and equipment based on intelligent community scene | |
| CN113283296A (en) | Helmet wearing detection method, electronic device and storage medium | |
| CN110928305B (en) | Patrol method and system for patrol robot of railway passenger station | |
| KR20210055257A (en) | System for analyzing accident images and method for using the same | |
| CN109120896B (en) | Security video monitoring guard system | |
| CN115909161A (en) | Monitoring information integration method and system for intelligent scenic spot | |
| CN115497268A (en) | Personnel positioning management system based on intelligent construction site and application | |
| CN104767969A (en) | Intelligent operation safety monitoring system and method for railway crossing | |
| CN111382697B (en) | Image data processing method and first electronic equipment |
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: 20200512 |