CN116437052A - Transmission monitoring method, device and equipment for remotely collecting expressway communication image - Google Patents
Transmission monitoring method, device and equipment for remotely collecting expressway communication image Download PDFInfo
- Publication number
- CN116437052A CN116437052A CN202310459200.2A CN202310459200A CN116437052A CN 116437052 A CN116437052 A CN 116437052A CN 202310459200 A CN202310459200 A CN 202310459200A CN 116437052 A CN116437052 A CN 116437052A
- Authority
- CN
- China
- Prior art keywords
- image
- monitoring
- frame
- images
- video data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 307
- 238000004891 communication Methods 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000005540 biological transmission Effects 0.000 title claims abstract description 23
- 238000012797 qualification Methods 0.000 claims abstract description 22
- 238000005070 sampling Methods 0.000 claims description 31
- 230000003287 optical effect Effects 0.000 claims description 26
- 238000001514 detection method Methods 0.000 claims description 25
- 238000011156 evaluation Methods 0.000 claims description 24
- 238000000605 extraction Methods 0.000 claims description 19
- 238000012360 testing method Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000010586 diagram Methods 0.000 claims description 11
- 238000013144 data compression Methods 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012806 monitoring device Methods 0.000 claims description 5
- 230000004044 response Effects 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006837 decompression Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- 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
- 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
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/008—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols involving homomorphic encryption
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
- H04N5/91—Television signal processing therefor
- H04N5/913—Television signal processing therefor for scrambling ; for copy protection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Security & Cryptography (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses a transmission monitoring method, a device and equipment for remotely collecting expressway communication images, wherein the method comprises the following steps: image acquisition is carried out on the expressway section, a communication image is generated, a background image without a running vehicle and a running image with the running vehicle are obtained, a running video stream of the monitored expressway section in the target background image is generated, if the image distortion rate is smaller than a set distortion rate threshold value, monitoring video data is generated, the monitoring video data are sent to a monitoring storage module, the monitoring video data are decompressed through the monitoring storage module, the image fidelity of a plurality of frames of monitoring images is determined, and if the image qualification rate in the plurality of frames of monitoring images is larger than the set qualification rate threshold value, the monitoring video data are sent to a monitoring server through a sending module. Therefore, the definition of the transmission monitoring image is improved, and the cloud server can quickly make emergency response based on the clear monitoring image.
Description
Technical Field
The invention relates to the field of data transmission, in particular to a transmission monitoring method, a device and equipment for remotely acquiring expressway communication images.
Background
With the continuous development of electronic information technology and the popularization of networks, high and new technologies such as image video monitoring and the like are applied to each field of national economy. In the existing expressway monitoring scene, the front-end equipment of the monitoring system directly transmits the collected image content back to the monitoring center, the monitoring center carries out subsequent processing, and the road condition information of the current monitored road section is known according to the processed image, so that corresponding emergency response is rapidly carried out when traffic accidents occur on the expressway, and the driving safety on the expressway is improved. However, the current monitoring equipment is affected by factors such as weather conditions, interference signals and the like, so that the situation of fuzzy distortion and the like of the monitoring image uploaded to the monitoring is easy to occur, the monitoring center cannot accurately acquire the latest accident situation on the current expressway, the accident handling efficiency is finally affected, and the safety of passengers on the expressway is even endangered.
Disclosure of Invention
Aiming at the technical problem that a remote monitoring image uploaded to a monitoring center is unclear in the prior art, the invention provides a transmission monitoring method, a transmission monitoring device and transmission monitoring equipment for remotely acquiring expressway communication images.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
in a first aspect of the embodiment of the present invention, a transmission monitoring method for remotely acquiring highway communication images is provided, where the method includes:
image acquisition is carried out on the monitored expressway section in a preset period through the remote monitoring equipment, and a multi-frame communication image is generated; classifying the multi-frame communication images according to whether a running vehicle exists in the multi-frame communication images or not to obtain multi-frame background images without the running vehicle and multi-frame running images with the running vehicle, wherein the acquisition time of the corresponding communication image is included in any running image;
performing image fusion on the multi-frame background image to generate a target background image, and performing feature extraction on vehicle data in the multi-frame driving image according to a preset vehicle feature extraction algorithm to generate a multi-frame vehicle image; generating a driving video stream of the monitoring expressway section in the target background image based on a plurality of acquisition times corresponding to the multi-frame vehicle image;
acquiring a plurality of sampling time points from the preset period according to a first preset interval time period, and extracting multi-frame video images from the driving video stream according to the plurality of sampling time points; determining the image distortion rate of the multi-frame video image through a preset first image detection model, and if the image distortion rate is smaller than a set distortion rate threshold value, performing data compression on the multi-frame video image to generate monitoring video data; the monitoring video data are sent to a monitoring storage module;
Decompressing the monitoring video data through the monitoring storage module to generate monitoring video data; sampling the monitoring video data according to a second preset interval time period to obtain multi-frame monitoring images; performing evaluation calculation on the multi-frame monitoring image through a preset evaluation formula to generate a plurality of mean square errors and a plurality of signal to noise ratios, which are in one-to-one correspondence with the multi-frame monitoring image; for a first mean square error and a first signal-to-noise ratio corresponding to any first monitoring image, weighting the first mean square error and the first signal-to-noise ratio through preset weight parameters to generate image fidelity of the first monitoring image; if the image fidelity is greater than a set threshold, determining that the first monitoring image is qualified; and under the condition that the image qualification rate in the multi-frame monitoring image is larger than a set qualification rate threshold value, the monitoring video data is sent to a monitoring server through a sending module.
Optionally, the determining the image distortion rate of the multi-frame video image by presetting a first image detection model includes:
for any first video image in the multi-frame video image, determining an optical distortion result and a TV distortion result of the first video image in a preset point-like image test card through the first image detection model;
Determining that no distortion is present in the first video image if the optical distortion result is less than an optical distortion threshold and the TV distortion result is less than a TV distortion threshold;
traversing the multi-frame video image in the mode, and determining multi-frame normal images and multi-frame distortion images from the multi-frame video image;
and determining the image distortion rate according to the first number of the multi-frame normal images and the second number of the multi-frame distorted images.
Optionally, the determining, by the first image detection model, an optical distortion result and a TV distortion result of the first video image in a preset point chart test card includes:
placing the first video image at the center of the preset point diagram test card;
determining the distortion percentage of each pixel point in the first video image in the radial direction according to the first image detection model and the preset point diagram test card;
generating the optical distortion result and the TV distortion result according to the distortion percentage.
Optionally, the performing evaluation calculation on the multiple frame monitoring images through a preset evaluation formula, generating multiple mean square errors and multiple signal-to-noise ratios corresponding to the multiple frame monitoring images one by one, includes:
For the first monitoring image in the multi-frame monitoring image, acquiring an original image corresponding to the first monitoring image from the multi-frame communication image according to the image acquisition time of the first monitoring image;
according to the preset evaluation formula, performing difference on each pixel in the original image and the first monitoring image to be horizontally placed and summed, and generating a mean square error of the first monitoring image;
and determining an energy difference between each pixel in the original image and the first monitoring image, and determining a first signal-to-noise ratio of the first monitoring image according to the energy difference;
and traversing the multi-frame monitoring image to generate the plurality of mean square errors and the plurality of signal to noise ratios.
Optionally, the determining an energy difference between each pixel in the original image and the first monitoring image includes:
determining a plurality of first RGB values in an RGB color space for each pixel in the original image; and determining a plurality of second RGB values in an RGB color space for each pixel in the first monitor image;
converting the plurality of first RGB values to a plurality of first HVS values in an HVS color space, and converting the plurality of second RGB values to a plurality of second HVS values in the HVS color space;
The plurality of first HVS values and the plurality of second HVS values are differenced to generate the energy difference.
Optionally, the sending, by the sending module, the monitoring video data to a monitoring server includes:
acquiring a public key sent by the monitoring server;
homomorphic encryption is carried out on the monitoring video data according to the public key, and the encrypted monitoring video data is generated;
and sending the encrypted monitoring video data to the monitoring server through the sending module, so that the monitoring server decrypts the encrypted monitoring video data according to the secret key to obtain the monitoring video data.
Optionally, the homomorphic encryption is performed on the surveillance video data according to the public key, and generating the encrypted surveillance video data includes:
generating homomorphic encryption data according to the public key and the monitoring video data;
and carrying out homomorphic calculation on the homomorphic encryption data in a preset data processing mode according to the public key, and generating the encrypted monitoring video data.
According to a second aspect of embodiments of the present disclosure, there is provided a transmission monitoring apparatus for remotely acquiring highway communication images, the apparatus comprising:
The processing module is used for acquiring images of the monitored expressway sections in a preset period through the remote monitoring equipment to generate multi-frame communication images; classifying the multi-frame communication images according to whether a running vehicle exists in the multi-frame communication images or not to obtain multi-frame background images without the running vehicle and multi-frame running images with the running vehicle, wherein the acquisition time of the corresponding communication image is included in any running image;
the generating module is used for carrying out image fusion on the multi-frame background image to generate a target background image, and carrying out feature extraction on vehicle data in the multi-frame driving image according to a preset vehicle feature extraction algorithm to generate a multi-frame vehicle image; generating a driving video stream of the monitoring expressway section in the target background image based on a plurality of acquisition times corresponding to the multi-frame vehicle image;
the first sending module is used for obtaining a plurality of sampling time points from the preset period according to a first preset interval time period, and extracting multi-frame video images from the driving video stream according to the plurality of sampling time points; determining the image distortion rate of the multi-frame video image through a preset first image detection model, and if the image distortion rate is smaller than a set distortion rate threshold value, performing data compression on the multi-frame video image to generate monitoring video data; the monitoring video data are sent to a monitoring storage module;
The second sending module is used for decompressing the monitoring video data through the monitoring storage module to generate monitoring video data; sampling the monitoring video data according to a second preset interval time period to obtain multi-frame monitoring images; performing evaluation calculation on the multi-frame monitoring image through a preset evaluation formula to generate a plurality of mean square errors and a plurality of signal to noise ratios, which are in one-to-one correspondence with the multi-frame monitoring image; for a first mean square error and a first signal-to-noise ratio corresponding to any first monitoring image, weighting the first mean square error and the first signal-to-noise ratio through preset weight parameters to generate image fidelity of the first monitoring image; if the image fidelity is greater than a set threshold, determining that the first monitoring image is qualified; and under the condition that the image qualification rate in the multi-frame monitoring image is larger than a set qualification rate threshold value, the monitoring video data is sent to a monitoring server through a sending module.
Optionally, the first sending module includes:
the first determining submodule is used for determining an optical distortion result and a TV distortion result of any first video image in the multi-frame video image in a preset point-like image test card through the first image detection model;
A second determining sub-module configured to determine that no distortion exists in the first video image if the optical distortion result is less than an optical distortion threshold and the TV distortion result is less than a TV distortion threshold;
the third determining submodule is used for traversing the multi-frame video image in the mode and determining multi-frame normal images and multi-frame distortion images from the multi-frame video image;
and the generating submodule is used for determining the image distortion rate according to the first number of the multi-frame normal images and the second number of the multi-frame distorted images.
According to a third aspect of embodiments of the present disclosure, there is provided an electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the transmission monitoring method for remotely collecting highway communication images according to any one of the first aspect of the present disclosure.
The invention provides a transmission monitoring method, a device and equipment for remotely acquiring expressway communication images. Compared with the prior art, the method has the following beneficial effects:
by the method, image acquisition is carried out on the monitored expressway section to generate a plurality of frames of communication images, a plurality of frames of background images without running vehicles and a plurality of frames of running images with running vehicles are obtained, wherein for any running image, the acquisition time of the corresponding communication image is included, image fusion is carried out on the plurality of frames of background images to generate a target background image, and according to a preset vehicle feature extraction algorithm, feature extraction is carried out on vehicle data in the plurality of frames of running images to generate a plurality of frames of vehicle images; based on a plurality of acquisition times corresponding to the multi-frame vehicle images, generating a driving video stream for monitoring the expressway section in the target background image; acquiring a plurality of sampling time points from a preset period according to a first preset interval period, and extracting multi-frame video images from a driving video stream according to the plurality of sampling time points; determining the image distortion rate of the multi-frame video image by presetting a first image detection model, and if the image distortion rate is smaller than a set distortion rate threshold value, performing data compression on the multi-frame video image to generate monitoring video data; transmitting the monitoring video data to a monitoring storage module; decompressing the monitoring video data through the monitoring storage module to generate the monitoring video data; sampling the monitoring video data according to a second preset interval time period to obtain multi-frame monitoring images; evaluating and calculating the multi-frame monitoring image through a preset evaluation formula to generate a plurality of mean square errors and a plurality of signal to noise ratios, which are in one-to-one correspondence with the multi-frame monitoring image; for a first mean square error and a first signal to noise ratio corresponding to any first monitoring image, weighting the first mean square error and the first signal to noise ratio through preset weight parameters to generate image fidelity of the first monitoring image; if the image fidelity is greater than the set threshold, determining that the first monitoring image is qualified; and under the condition that the image qualification rate in the multi-frame monitoring image is larger than the set qualification rate threshold value, the monitoring video data is sent to the monitoring server through the sending module. The communication images are screened and processed, after the video stream is generated, the video stream is randomly sampled to determine the distortion rate of the video stream, so that the condition that the video stream transmitted to the monitoring server is free from blurring is ensured, the definition of the monitoring image is improved, and the cloud server can quickly make emergency response based on the clear monitoring image.
Drawings
Fig. 1 is a flow chart illustrating a transmission monitoring method for remotely acquiring highway communication images according to an exemplary embodiment.
Fig. 2 is a flowchart illustrating a method of determining an image distortion rate according to an exemplary embodiment.
Fig. 3 is a flow chart illustrating a method of generating a mean error and a signal-to-noise ratio in accordance with an exemplary embodiment.
Fig. 4 is a block diagram illustrating a transmission monitoring apparatus for remotely acquiring highway communication images according to an exemplary embodiment.
Description of the embodiments
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Fig. 1 is a flowchart illustrating a transmission monitoring method of remotely collecting highway communication images according to an exemplary embodiment, which is applied to a remote monitoring apparatus as shown in fig. 1, the method including the steps of.
In step S101, image acquisition is performed on the monitored expressway section to generate a multi-frame communication image, and a multi-frame background image in which no running vehicle exists and a multi-frame running image in which a running vehicle exists are obtained.
The embodiment is applied to remote monitoring equipment, which is fixed on a highway and is used for acquiring images of a fixed road section of the highway. Image acquisition is carried out on the monitored expressway section in a preset period through the remote monitoring equipment, and a multi-frame communication image is generated; classifying the multi-frame communication images according to whether a running vehicle exists in the multi-frame communication images or not to obtain multi-frame background images without the running vehicle and multi-frame running images with the running vehicle, wherein the acquisition time of the corresponding communication image is included in any running image.
In step S102, image fusion is performed on the multi-frame background image to generate a target background image, feature extraction is performed on vehicle data in the multi-frame driving image to generate a multi-frame vehicle image, and driving video streams of the monitored expressway section in the target background image are generated based on a plurality of acquisition times corresponding to the multi-frame vehicle image.
By way of example, in this embodiment, because the remote monitoring device is fixed, the corresponding monitoring view angle does not change, and when no running vehicle exists in the monitoring view angle, the images acquired by the remote monitoring device are the same, so that multiple frame images of the running vehicle does not exist can be fused to generate the target background image. And sampling the image with the running vehicle according to a preset sampling time period, generating a running video stream with the running vehicle image only, and merging the running video stream into the target background image, thereby generating the running video stream which can represent the monitoring image of the time period.
In this embodiment, the multi-frame background image is subjected to image fusion to generate a target background image, and the vehicle data in the multi-frame driving image is subjected to feature extraction according to a preset vehicle feature extraction algorithm to generate a multi-frame vehicle image; and generating a driving video stream of the monitoring expressway section in the target background image based on a plurality of acquisition times corresponding to the multi-frame vehicle image.
In step S103, according to a plurality of sampling time points, extracting a plurality of frames of video images from the driving video stream, determining an image distortion rate of the plurality of frames of video images, if the image distortion rate is smaller than a set distortion rate threshold, performing data compression on the plurality of frames of video images to generate monitoring video data, and transmitting the monitoring video data to the monitoring storage module.
For example, in this embodiment, a plurality of sampling time points are obtained from the preset period according to a first preset interval period, and a multi-frame video image is extracted from the driving video stream according to the plurality of sampling time points; determining the image distortion rate of the multi-frame video image through a preset first image detection model, and if the image distortion rate is smaller than a set distortion rate threshold value, performing data compression on the multi-frame video image to generate monitoring video data; and sending the monitoring video data to a monitoring storage module.
In step S104, monitoring video data is generated, the monitoring video data is sampled to obtain multi-frame monitoring images, image fidelity of the multi-frame monitoring images is generated, and if the image qualification rate in the multi-frame monitoring images is greater than a set qualification rate threshold, the monitoring video data is sent to a monitoring server through a sending module.
For example, in this embodiment, the monitoring video data is decompressed by the monitoring storage module to generate the monitoring video data; sampling the monitoring video data according to a second preset interval time period to obtain multi-frame monitoring images; evaluating and calculating the multi-frame monitoring image through a preset evaluation formula to generate a plurality of mean square errors and a plurality of signal to noise ratios, which are in one-to-one correspondence with the multi-frame monitoring image; for a first mean square error and a first signal to noise ratio corresponding to any first monitoring image, weighting the first mean square error and the first signal to noise ratio through preset weight parameters to generate image fidelity of the first monitoring image; if the image fidelity is greater than the set threshold, determining that the first monitoring image is qualified; and under the condition that the image qualification rate in the multi-frame monitoring image is larger than the set qualification rate threshold value, the monitoring video data is sent to the monitoring server through the sending module.
Alternatively, in another embodiment, the step of "transmitting the monitoring video data to the monitoring server through the transmitting module" includes the following steps.
Acquiring a public key sent by the monitoring server;
homomorphic encryption is carried out on the monitoring video data according to the public key, and the encrypted monitoring video data is generated;
and sending the encrypted monitoring video data to the monitoring server through the sending module, so that the monitoring server decrypts the encrypted monitoring video data according to the secret key to obtain the monitoring video data.
For example, in this embodiment, the monitoring image of the expressway belongs to confidential data of the expressway supervision department, so in order to avoid information leakage, in this embodiment, the monitoring image is encrypted by homomorphic encryption, so as to avoid the problem of monitoring data leakage.
Optionally, in another embodiment, the step of homomorphic encrypting the surveillance video data according to the public key to generate encrypted surveillance video data includes:
generating homomorphic encryption data according to the public key and the monitoring video data;
And carrying out homomorphic calculation on the homomorphic encryption data in a preset data processing mode according to the public key, and generating the encrypted monitoring video data.
By the method, image acquisition is carried out on the monitored expressway section to generate a plurality of frames of communication images, a plurality of frames of background images without running vehicles and a plurality of frames of running images with running vehicles are obtained, wherein for any running image, the acquisition time of the corresponding communication image is included, image fusion is carried out on the plurality of frames of background images to generate a target background image, and according to a preset vehicle feature extraction algorithm, feature extraction is carried out on vehicle data in the plurality of frames of running images to generate a plurality of frames of vehicle images; based on a plurality of acquisition times corresponding to the multi-frame vehicle images, generating a driving video stream for monitoring the expressway section in the target background image; acquiring a plurality of sampling time points from a preset period according to a first preset interval period, and extracting multi-frame video images from a driving video stream according to the plurality of sampling time points; determining the image distortion rate of the multi-frame video image by presetting a first image detection model, and if the image distortion rate is smaller than a set distortion rate threshold value, performing data compression on the multi-frame video image to generate monitoring video data; transmitting the monitoring video data to a monitoring storage module; decompressing the monitoring video data through the monitoring storage module to generate the monitoring video data; sampling the monitoring video data according to a second preset interval time period to obtain multi-frame monitoring images; evaluating and calculating the multi-frame monitoring image through a preset evaluation formula to generate a plurality of mean square errors and a plurality of signal to noise ratios, which are in one-to-one correspondence with the multi-frame monitoring image; for a first mean square error and a first signal to noise ratio corresponding to any first monitoring image, weighting the first mean square error and the first signal to noise ratio through preset weight parameters to generate image fidelity of the first monitoring image; if the image fidelity is greater than the set threshold, determining that the first monitoring image is qualified; and under the condition that the image qualification rate in the multi-frame monitoring image is larger than the set qualification rate threshold value, the monitoring video data is sent to the monitoring server through the sending module. The communication images are screened and processed, after the video stream is generated, the video stream is randomly sampled to determine the distortion rate of the video stream, so that the condition that the video stream transmitted to the monitoring server is free from blurring is ensured, the definition of the monitoring image is improved, and the cloud server can quickly make emergency response based on the clear monitoring image.
Fig. 2 is a flowchart illustrating a method for determining an image distortion rate according to an exemplary embodiment, and the step of determining an image distortion rate of the multi-frame video image by presetting a first image detection model as described above includes the following steps as shown in fig. 2.
In step S201, for any first video image in the multi-frame video image, determining, by the first image detection model, an optical distortion result and a TV distortion result of the first video image in a preset point chart test card.
Optionally, in one embodiment, the step S201 includes:
placing the first video image at the center of the preset point diagram test card;
determining the distortion percentage of each pixel point in the first video image in the radial direction according to the first image detection model and the preset point diagram test card;
generating the optical distortion result and the TV distortion result according to the distortion percentage.
In step S202, in a case where the optical distortion result is smaller than the optical distortion threshold and the TV distortion result is smaller than the TV distortion threshold, it is determined that there is no distortion in the first video image.
In step S203, the multi-frame video image is traversed in the above-described manner, and the multi-frame normal image and the multi-frame distorted image are determined from among the multi-frame video images.
In step S204, an image distortion ratio is determined from the first number of normal images of the plurality of frames and the second number of distorted images of the plurality of frames.
By the method, sampling is carried out from the video stream, the optical distortion result and the TV distortion result of each video image are determined, whether the distortion result exceeds a threshold value is determined, whether the video image is distorted is determined, the distortion rate of the image is determined according to the distortion, and the distortion rate determination of the video stream is more accurate.
Fig. 3 is a flowchart of a method for generating average error and signal-to-noise ratio according to an exemplary embodiment, where, as shown in fig. 3, the step of performing evaluation calculation on the multi-frame monitored image by using a preset evaluation formula, generating a plurality of mean square errors and a plurality of signal-to-noise ratios corresponding to the multi-frame monitored image one to one includes:
in step S301, for the first monitoring image in the multiple frames of monitoring images, an original image corresponding to the first monitoring image is acquired from the multiple frames of communication images according to an image acquisition time of the first monitoring image.
In step S302, according to the preset evaluation formula, differences are made between the original image and each pixel in the first monitoring image to be horizontally summed, so as to generate a mean square error of the first monitoring image.
In step S303, an energy difference between each pixel in the original image and the first monitoring image is determined, and a first signal-to-noise ratio of the first monitoring image is determined according to the energy difference.
Optionally, in an embodiment, the step of determining an energy difference between each pixel in the original image and the first monitored image includes:
determining a plurality of first RGB values in an RGB color space for each pixel in the original image; and determining a plurality of second RGB values in an RGB color space for each pixel in the first monitor image;
converting the plurality of first RGB values to a plurality of first HVS values in an HVS color space, and converting the plurality of second RGB values to a plurality of second HVS values in the HVS color space;
the plurality of first HVS values and the plurality of second HVS values are differenced to generate the energy difference.
In step S304, the multi-frame monitoring image is traversed, and the plurality of mean square errors and the plurality of signal-to-noise ratios are generated.
By the method, the monitoring image is compared with the original image, the mean square error and the signal to noise ratio between the two images are determined, and whether the monitoring image has distortion in the decompression process is determined according to the mean square error and the signal to noise ratio.
Fig. 4 is a block diagram illustrating a transmission monitoring apparatus for remotely acquiring an expressway communication image according to an exemplary embodiment, and as shown in fig. 4, the apparatus 100 includes a processing module 110, a generating module 120, a first transmitting module 130, and a second transmitting module 140.
The processing module 110 is configured to perform image acquisition on a monitored highway segment in a preset period by using the remote monitoring device, so as to generate a multi-frame communication image; classifying the multi-frame communication images according to whether a running vehicle exists in the multi-frame communication images or not to obtain multi-frame background images without the running vehicle and multi-frame running images with the running vehicle, wherein the acquisition time of the corresponding communication image is included in any running image;
the generating module 120 is configured to perform image fusion on the multiple frames of background images to generate a target background image, and perform feature extraction on vehicle data in the multiple frames of driving images according to a preset vehicle feature extraction algorithm to generate multiple frames of vehicle images; generating a driving video stream of the monitoring expressway section in the target background image based on a plurality of acquisition times corresponding to the multi-frame vehicle image;
A first sending module 130, configured to obtain a plurality of sampling time points from the preset period according to a first preset interval period, and extract a plurality of frame video images from the driving video stream according to the plurality of sampling time points; determining the image distortion rate of the multi-frame video image through a preset first image detection model, and if the image distortion rate is smaller than a set distortion rate threshold value, performing data compression on the multi-frame video image to generate monitoring video data; the monitoring video data are sent to a monitoring storage module;
the second sending module 140 is configured to decompress the monitoring video data through the monitoring storage module, and generate monitoring video data; sampling the monitoring video data according to a second preset interval time period to obtain multi-frame monitoring images; performing evaluation calculation on the multi-frame monitoring image through a preset evaluation formula to generate a plurality of mean square errors and a plurality of signal to noise ratios, which are in one-to-one correspondence with the multi-frame monitoring image; for a first mean square error and a first signal-to-noise ratio corresponding to any first monitoring image, weighting the first mean square error and the first signal-to-noise ratio through preset weight parameters to generate image fidelity of the first monitoring image; if the image fidelity is greater than a set threshold, determining that the first monitoring image is qualified; and under the condition that the image qualification rate in the multi-frame monitoring image is larger than a set qualification rate threshold value, the monitoring video data is sent to a monitoring server through a sending module.
Optionally, the first sending module 130 includes:
the first determining submodule is used for determining an optical distortion result and a TV distortion result of any first video image in the multi-frame video image in a preset point-like image test card through the first image detection model;
a second determining sub-module configured to determine that no distortion exists in the first video image if the optical distortion result is less than an optical distortion threshold and the TV distortion result is less than a TV distortion threshold;
the third determining submodule is used for traversing the multi-frame video image in the mode and determining multi-frame normal images and multi-frame distortion images from the multi-frame video image;
and the generating submodule is used for determining the image distortion rate according to the first number of the multi-frame normal images and the second number of the multi-frame distorted images.
Optionally, the first determining submodule is configured to determine, by using the first image detection model, an optical distortion result and a TV distortion result of the first video image in a preset point-like diagram test card, where the determining includes:
placing the first video image at the center of the preset point diagram test card;
Determining the distortion percentage of each pixel point in the first video image in the radial direction according to the first image detection model and the preset point diagram test card;
generating the optical distortion result and the TV distortion result according to the distortion percentage.
Optionally, the second sending module 140 includes:
the first acquisition sub-module is used for acquiring an original image corresponding to the first monitoring image from the multi-frame communication image according to the image acquisition time of the first monitoring image for the first monitoring image in the multi-frame monitoring image;
the calculation sub-module is used for carrying out difference on each pixel in the original image and the first monitoring image to carry out flat summation according to the preset evaluation formula, so as to generate the mean square error of the first monitoring image;
a fourth determining sub-module, configured to determine an energy difference between each pixel in the original image and the first monitoring image, and determine a first signal-to-noise ratio of the first monitoring image according to the energy difference;
and the execution submodule is used for traversing the multi-frame monitoring image and generating the plurality of mean square errors and the plurality of signal to noise ratios.
Optionally, the fourth determining submodule is configured to:
determining a plurality of first RGB values in an RGB color space for each pixel in the original image; and determining a plurality of second RGB values in an RGB color space for each pixel in the first monitor image;
converting the plurality of first RGB values to a plurality of first HVS values in an HVS color space, and converting the plurality of second RGB values to a plurality of second HVS values in the HVS color space;
the plurality of first HVS values and the plurality of second HVS values are differenced to generate the energy difference.
Optionally, the second sending module 140 includes:
the second acquisition sub-module is used for acquiring the public key sent by the monitoring server;
the encryption sub-module is used for homomorphic encryption of the monitoring video data according to the public key to generate encrypted monitoring video data;
and the transmission sub-module is used for transmitting the encrypted monitoring video data to the monitoring server through the transmission module so that the monitoring server decrypts the encrypted monitoring video data according to the secret key to obtain the monitoring video data.
Optionally, the encryption sub-module is configured to:
Generating homomorphic encryption data according to the public key and the monitoring video data;
and carrying out homomorphic calculation on the homomorphic encryption data in a preset data processing mode according to the public key, and generating the encrypted monitoring video data.
By the method, image acquisition is carried out on the monitored expressway section to generate a plurality of frames of communication images, a plurality of frames of background images without running vehicles and a plurality of frames of running images with running vehicles are obtained, wherein for any running image, the acquisition time of the corresponding communication image is included, image fusion is carried out on the plurality of frames of background images to generate a target background image, and according to a preset vehicle feature extraction algorithm, feature extraction is carried out on vehicle data in the plurality of frames of running images to generate a plurality of frames of vehicle images; based on a plurality of acquisition times corresponding to the multi-frame vehicle images, generating a driving video stream for monitoring the expressway section in the target background image; acquiring a plurality of sampling time points from a preset period according to a first preset interval period, and extracting multi-frame video images from a driving video stream according to the plurality of sampling time points; determining the image distortion rate of the multi-frame video image by presetting a first image detection model, and if the image distortion rate is smaller than a set distortion rate threshold value, performing data compression on the multi-frame video image to generate monitoring video data; transmitting the monitoring video data to a monitoring storage module; decompressing the monitoring video data through the monitoring storage module to generate the monitoring video data; sampling the monitoring video data according to a second preset interval time period to obtain multi-frame monitoring images; evaluating and calculating the multi-frame monitoring image through a preset evaluation formula to generate a plurality of mean square errors and a plurality of signal to noise ratios, which are in one-to-one correspondence with the multi-frame monitoring image; for a first mean square error and a first signal to noise ratio corresponding to any first monitoring image, weighting the first mean square error and the first signal to noise ratio through preset weight parameters to generate image fidelity of the first monitoring image; if the image fidelity is greater than the set threshold, determining that the first monitoring image is qualified; and under the condition that the image qualification rate in the multi-frame monitoring image is larger than the set qualification rate threshold value, the monitoring video data is sent to the monitoring server through the sending module. The communication images are screened and processed, after the video stream is generated, the video stream is randomly sampled to determine the distortion rate of the video stream, so that the condition that the video stream transmitted to the monitoring server is free from blurring is ensured, the definition of the monitoring image is improved, and the cloud server can quickly make emergency response based on the clear monitoring image.
Based on the same inventive concept, the present embodiment provides an electronic device including:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the transmission monitoring method for remotely collecting highway communication images according to any one of the first aspect of the present disclosure.
With the above-described preferred embodiments according to the present application as a teaching, the related workers can make various changes and modifications without departing from the scope of the technical idea of the present application. The technical scope of the present application is not limited to the contents of the specification, and must be determined according to the scope of claims.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A transmission monitoring method for remotely acquiring highway communication images, the method comprising:
Image acquisition is carried out on the monitored expressway section in a preset period through remote monitoring equipment, and a multi-frame communication image is generated; classifying the multi-frame communication images according to whether a running vehicle exists in the multi-frame communication images or not to obtain multi-frame background images without the running vehicle and multi-frame driving images with the running vehicle, wherein the driving images comprise the acquisition time of the corresponding communication images;
performing image fusion on the multi-frame background image to generate a target background image, and performing feature extraction on vehicle data in the multi-frame driving image according to a preset vehicle feature extraction algorithm to generate a multi-frame vehicle image; generating a driving video stream of the monitoring expressway section in the target background image based on a plurality of acquisition times corresponding to the multi-frame vehicle image;
acquiring a plurality of sampling time points from the preset period according to a first preset interval time period, and extracting multi-frame video images from the driving video stream according to the plurality of sampling time points; determining the image distortion rate of the multi-frame video image through a preset first image detection model, and if the image distortion rate is smaller than a set distortion rate threshold value, performing data compression on the multi-frame video image to generate monitoring video data; the monitoring video data are sent to a monitoring storage module;
Decompressing the monitoring video data through the monitoring storage module to generate monitoring video data; sampling the monitoring video data according to a second preset interval time period to obtain multi-frame monitoring images; performing evaluation calculation on the multi-frame monitoring image through a preset evaluation formula to generate a plurality of mean square errors and a plurality of signal to noise ratios, which are in one-to-one correspondence with the multi-frame monitoring image; for a first mean square error and a first signal-to-noise ratio corresponding to any first monitoring image, weighting the first mean square error and the first signal-to-noise ratio through preset weight parameters to generate image fidelity of the first monitoring image; if the image fidelity is greater than a set threshold, determining that the first monitoring image is qualified; and under the condition that the image qualification rate in the multi-frame monitoring image is larger than a set qualification rate threshold value, the monitoring video data is sent to a monitoring server through a sending module.
2. The method according to claim 1, wherein determining the image distortion rate of the multi-frame video image by presetting a first image detection model comprises:
for any first video image in the multi-frame video image, determining an optical distortion result and a TV distortion result of the first video image in a preset point-like image test card through the first image detection model;
Determining that no distortion is present in the first video image if the optical distortion result is less than an optical distortion threshold and the TV distortion result is less than a TV distortion threshold;
traversing the multi-frame video image in the mode, and determining multi-frame normal images and multi-frame distortion images from the multi-frame video image;
and determining the image distortion rate according to the first number of the multi-frame normal images and the second number of the multi-frame distorted images.
3. The method of claim 2, wherein determining, by the first image detection model, an optical distortion result and a TV distortion result of the first video image in a preset point chart test card comprises:
placing the first video image at the center of the preset point diagram test card;
determining the distortion percentage of each pixel point in the first video image in the radial direction according to the first image detection model and the preset point diagram test card;
generating the optical distortion result and the TV distortion result according to the distortion percentage.
4. The method according to claim 1, wherein the performing evaluation calculation on the multi-frame monitoring image by a preset evaluation formula to generate a plurality of mean square errors and a plurality of signal-to-noise ratios corresponding to the multi-frame monitoring image one to one includes:
For the first monitoring image in the multi-frame monitoring image, acquiring an original image corresponding to the first monitoring image from the multi-frame communication image according to the image acquisition time of the first monitoring image;
according to the preset evaluation formula, performing difference on each pixel in the original image and the first monitoring image to be horizontally placed and summed, and generating a mean square error of the first monitoring image;
and determining an energy difference between each pixel in the original image and the first monitoring image, and determining a first signal-to-noise ratio of the first monitoring image according to the energy difference;
and traversing the multi-frame monitoring image to generate the plurality of mean square errors and the plurality of signal to noise ratios.
5. The method of claim 4, wherein the determining the energy difference between each pixel in the original image and the first monitor image comprises:
determining a plurality of first RGB values in an RGB color space for each pixel in the original image; and determining a plurality of second RGB values in an RGB color space for each pixel in the first monitor image;
converting the plurality of first RGB values to a plurality of first HVS values in an HVS color space, and converting the plurality of second RGB values to a plurality of second HVS values in the HVS color space;
The plurality of first HVS values and the plurality of second HVS values are differenced to generate the energy difference.
6. The method according to any one of claims 1-5, wherein the transmitting the surveillance video data to a surveillance server by a transmitting module comprises:
acquiring a public key sent by the monitoring server;
homomorphic encryption is carried out on the monitoring video data according to the public key, and the encrypted monitoring video data is generated;
and sending the encrypted monitoring video data to the monitoring server through the sending module, so that the monitoring server decrypts the encrypted monitoring video data according to the secret key to obtain the monitoring video data.
7. The method of claim 6, wherein homomorphic encrypting the surveillance video data according to the public key generates encrypted surveillance video data, comprising:
generating homomorphic encryption data according to the public key and the monitoring video data;
and carrying out homomorphic calculation on the homomorphic encryption data in a preset data processing mode according to the public key, and generating the encrypted monitoring video data.
8. A transmission monitoring device for remotely acquiring highway communication images, the device comprising:
the processing module is used for acquiring images of the monitored expressway sections in a preset period through the remote monitoring equipment to generate multi-frame communication images; classifying the multi-frame communication images according to whether a running vehicle exists in the multi-frame communication images or not to obtain multi-frame background images without the running vehicle and multi-frame driving images with the running vehicle, wherein the driving images comprise the acquisition time of the corresponding communication images;
the generating module is used for carrying out image fusion on the multi-frame background image to generate a target background image, and carrying out feature extraction on vehicle data in the multi-frame driving image according to a preset vehicle feature extraction algorithm to generate a multi-frame vehicle image; generating a driving video stream of the monitoring expressway section in the target background image based on a plurality of acquisition times corresponding to the multi-frame vehicle image;
the first sending module is used for obtaining a plurality of sampling time points from the preset period according to a first preset interval time period, and extracting multi-frame video images from the driving video stream according to the plurality of sampling time points; determining the image distortion rate of the multi-frame video image through a preset first image detection model, and if the image distortion rate is smaller than a set distortion rate threshold value, performing data compression on the multi-frame video image to generate monitoring video data; the monitoring video data are sent to a monitoring storage module;
The second sending module is used for decompressing the monitoring video data through the monitoring storage module to generate monitoring video data; sampling the monitoring video data according to a second preset interval time period to obtain multi-frame monitoring images; performing evaluation calculation on the multi-frame monitoring image through a preset evaluation formula to generate a plurality of mean square errors and a plurality of signal to noise ratios, which are in one-to-one correspondence with the multi-frame monitoring image; for a first mean square error and a first signal-to-noise ratio corresponding to any first monitoring image, weighting the first mean square error and the first signal-to-noise ratio through preset weight parameters to generate image fidelity of the first monitoring image; if the image fidelity is greater than a set threshold, determining that the first monitoring image is qualified; and under the condition that the image qualification rate in the multi-frame monitoring image is larger than a set qualification rate threshold value, the monitoring video data is sent to a monitoring server through a sending module.
9. The apparatus of claim 8, wherein the first transmitting module comprises:
the first determining submodule is used for determining an optical distortion result and a TV distortion result of any first video image in the multi-frame video image in a preset point-like image test card through the first image detection model;
A second determining sub-module configured to determine that no distortion exists in the first video image if the optical distortion result is less than an optical distortion threshold and the TV distortion result is less than a TV distortion threshold;
the third determining submodule is used for traversing the multi-frame video image in the mode and determining multi-frame normal images and multi-frame distortion images from the multi-frame video image;
and the generating submodule is used for determining the image distortion rate according to the first number of the multi-frame normal images and the second number of the multi-frame distorted images.
10. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing said computer program in said memory to implement the steps of the transmission monitoring method for remotely capturing highway communication images according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310459200.2A CN116437052A (en) | 2023-04-26 | 2023-04-26 | Transmission monitoring method, device and equipment for remotely collecting expressway communication image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310459200.2A CN116437052A (en) | 2023-04-26 | 2023-04-26 | Transmission monitoring method, device and equipment for remotely collecting expressway communication image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116437052A true CN116437052A (en) | 2023-07-14 |
Family
ID=87092615
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310459200.2A Withdrawn CN116437052A (en) | 2023-04-26 | 2023-04-26 | Transmission monitoring method, device and equipment for remotely collecting expressway communication image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116437052A (en) |
-
2023
- 2023-04-26 CN CN202310459200.2A patent/CN116437052A/en not_active Withdrawn
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111928888B (en) | Intelligent monitoring and analyzing method and system for water pollution | |
CN107729850B (en) | Internet of things outdoor advertisement monitoring and broadcasting system | |
KR20080049063A (en) | Motion detection device | |
CN106781436A (en) | Traffic accident treatment method and device | |
US20060008118A1 (en) | Image processing apparatus and image monitoring system | |
CN107959885B (en) | Motion detection method of encrypted video | |
CN111050022B (en) | High-security image transmission system and method | |
WO2022078353A1 (en) | Vehicle driving state determination method and apparatus, and computer device and storage medium | |
CN113887412A (en) | Detection method, detection terminal, monitoring system and storage medium for pollution emission | |
CN113822814A (en) | Environment identification system and method using big data storage | |
CN110659627A (en) | Intelligent video monitoring method based on video segmentation | |
CN210955484U (en) | Traffic condition monitor | |
CN117768610A (en) | High-speed railway perimeter intrusion risk monitoring method and system based on multi-target recognition | |
CN116437052A (en) | Transmission monitoring method, device and equipment for remotely collecting expressway communication image | |
CN109547777B (en) | Method for rapidly detecting video noise of complex scene | |
CN115766297B (en) | Information data safety protection method based on Internet of things | |
CN115359391A (en) | Inspection image detection method, inspection image detection device, electronic device and medium | |
CN104735409A (en) | Single-optical-path surveillance video watermark physical hiding device and digital detection method thereof | |
CN114140724A (en) | Video monitoring system and method for transformer substation | |
CN102196259B (en) | Moving object detection system and method suitable for compression domain | |
CN111275027A (en) | Method for realizing detection and early warning processing of expressway in foggy days | |
CN117061711B (en) | Video monitoring safety management method and system based on Internet of things | |
CN111353477B (en) | Gait recognition system and method | |
CN115830806B (en) | Natural disaster condition analysis system based on high-resolution remote sensing | |
KR101890883B1 (en) | Manless a park and stop regulation system using map |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230714 |