CN116456061B - Intelligent community monitoring management method, system and medium based on dynamic target detection - Google Patents
Intelligent community monitoring management method, system and medium based on dynamic target detection Download PDFInfo
- Publication number
- CN116456061B CN116456061B CN202310710895.7A CN202310710895A CN116456061B CN 116456061 B CN116456061 B CN 116456061B CN 202310710895 A CN202310710895 A CN 202310710895A CN 116456061 B CN116456061 B CN 116456061B
- Authority
- CN
- China
- Prior art keywords
- dynamic
- monitoring
- dynamic target
- data
- intelligent community
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 160
- 238000001514 detection method Methods 0.000 title claims abstract description 58
- 238000007726 management method Methods 0.000 title claims abstract description 26
- 230000005540 biological transmission Effects 0.000 claims abstract description 56
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 241001465754 Metazoa Species 0.000 claims description 21
- 239000013598 vector Substances 0.000 claims description 20
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000011897 real-time detection Methods 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 4
- 230000003190 augmentative effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 abstract description 12
- 239000002699 waste material Substances 0.000 abstract description 6
- 230000007246 mechanism Effects 0.000 abstract description 5
- 241001464837 Viridiplantae Species 0.000 description 10
- 230000001105 regulatory effect Effects 0.000 description 3
- 241000282326 Felis catus Species 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013144 data compression Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000002203 pretreatment Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- 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
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
- H04N23/661—Transmitting camera control signals through networks, e.g. control via the Internet
-
- 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
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/70—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in livestock or poultry
Abstract
The invention discloses an intelligent community monitoring management method, system and medium based on dynamic target detection; the method comprises the steps of acquiring monitoring data of an intelligent community and preprocessing the monitoring data; detecting a dynamic target based on the preprocessed monitoring data, and judging the dynamic amplitude level of the monitoring data with the dynamic target; adjusting monitoring video acquisition parameters and monitoring video transmission modes of the intelligent community according to the dynamic target detection result and the dynamic amplitude level judgment result; the invention improves on the basis of the existing method, adjusts the monitoring video acquisition parameters and the monitoring video transmission modes of the intelligent community based on the dynamic target detection result and the dynamic amplitude level judgment result, and solves the problem of insufficient broadband efficiency by using a more intelligent data sampling rate control mechanism to regulate and control the data sampling rate according to the content of monitoring data in order to avoid broadband waste and data redundancy caused by unreasonable data sampling rate of equipment.
Description
Technical Field
The invention relates to the technical field of intelligent communities, in particular to an intelligent community monitoring management method, system and medium based on dynamic target detection.
Background
The intelligent community security framework is a security precaution measure framework based on the Internet of things technology and intelligent security equipment, and aims to improve the intelligent degree of community security management and service; the intelligent management and control system has the main functions of video monitoring, access control, personnel detection and the like, and can realize the intelligent management and control of community access personnel through technical means such as face recognition, identity authentication and the like.
The community security design framework needs a quite large broadband, for example, a high-resolution camera and more personnel and equipment data need to be uploaded, and a certain pressure is caused on broadband resources; aiming at the problem of insufficient broadband efficiency existing in the current community security design framework, the prior art adopts the following methods to solve the problems: higher speed broadband schemes such as gigabit networks or fiber optic networks may be employed; optimizing a data compression algorithm: the community security design framework needs to upload and store a large amount of data such as video images, and in order to reduce the bandwidth occupied by data transmission and storage, the data volume can be reduced to the minimum by adopting a more efficient data compression algorithm; optimizing data upload polling mechanisms, etc.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: the invention aims to provide an intelligent community monitoring management method, system and medium based on dynamic target detection, which are improved based on the existing method, adjust monitoring video acquisition parameters and monitoring video transmission modes of an intelligent community based on dynamic target detection results and dynamic amplitude level judgment results, and solve the problem of insufficient broadband efficiency by using a more intelligent data sampling rate control mechanism and regulating and controlling the data sampling rate according to the content of monitoring data in order to avoid broadband waste and data redundancy caused by unreasonable data sampling rate of equipment.
The invention is realized by the following technical scheme:
the scheme provides an intelligent community monitoring management method based on dynamic target detection, which comprises the following steps:
acquiring monitoring data of an intelligent community and preprocessing the monitoring data;
detecting a dynamic target based on the preprocessed monitoring data, and judging the dynamic amplitude level of the monitoring data with the dynamic target;
and adjusting the monitoring video acquisition parameters and the monitoring video transmission modes of the intelligent community according to the dynamic target detection result and the dynamic amplitude level judgment result.
The working principle of the scheme is as follows: the intelligent community monitoring management method, system and medium based on dynamic target detection are improved on the basis of the existing method, and the monitoring video acquisition parameters and the monitoring video transmission mode of the intelligent community are adjusted based on the dynamic target detection result and the dynamic amplitude level judgment result; in order to avoid broadband waste and data redundancy caused by unreasonable data sampling rate of video equipment, the broadband efficiency deficiency is solved by a more intelligent video equipment data sampling rate control mechanism: the problem of insufficient broadband efficiency is solved by regulating the data sampling rate according to the content of the monitoring data.
The traditional monitoring video transmission is characterized in that no matter how the pedestrian condition of the monitored scene is, the camera device transmits a uniform acquisition mode and transmission mode, so that waste of a large amount of transmission broadband is easily caused when no pedestrian or fewer pedestrians exist, and the invention judges the dynamic amplitude level of the monitoring data with the dynamic target according to the situation; and the monitoring video acquisition parameters and the monitoring video transmission modes of the intelligent community are adjusted based on the dynamic target detection result and the dynamic amplitude level judgment result, so that the shot video data are more meaningful, and the camera device selects acquisition modes and transmission modes with different qualities according to different dynamic amplitude levels, so that the network flow consumed by transmission is reduced to the greatest extent fundamentally.
The pretreatment method comprises the following steps of:
acquiring image data of the monitoring data;
dividing a background area and a foreground area of the image data, and classifying a stationary point and a moving point of the image data from two adjacent frames of image data based on an inter-frame difference method; taking a stationary point as a background pixel point and a motion point as a foreground pixel point;
candidate background pixel points are extracted from background pixel points based on a Bayesian decision method, and candidate foreground pixel points are extracted from foreground pixel points. Respectively acquiring posterior probability of the background and posterior probability of the foreground based on a Bayesian decision method; extracting feature vectors from foreground targets and background targets of the image data, and acquiring feature vector probabilities; and respectively associating the background area and the foreground area in the image with the feature vectors, and dividing candidate background pixel points and candidate foreground pixel points according to the probability of the feature vectors.
In a further optimized scheme, the method for detecting the dynamic target comprises the following steps:
s1, weighting calculation is carried out on candidate pixel points: according toCalculating the weight vector of each pixel point; wherein u represents the pixel factor of the pixel point, and w represents the weight;
s2, setting the weight vector of the pixel point i as a diagonal element to establish a diagonal matrixAnd sets the weight vector of each pixel point as a diagonal matrix +.>Obtaining a weight matrix B of the video sequence through the arrangement of the column vectors;
s3, byEstimating a gesture area of a dynamic target in image data for a detection model; wherein n represents the total number of candidate pixel points, alpha is the attitude parameter of the dynamic target, and +.>E and C are respectively low-rank components and sparse components of a weight matrix B, and Z is a possible gesture parameter of a dynamic target; />Represents the core norm of E;represents an L1 norm;
s4, solving a convex optimization problem of the detection model to obtain a real-time detection result of the dynamic target, and outputting the real-time detection result and a gesture area of the dynamic target;
according to the scheme, the global view of the picture data is established through the multi-layer paradigm, the global view is set as an initial value for real-time detection of the target gesture, and the gesture detection precision of the dynamic target is improved through further segmentation. And the weight matrix B is used for inhibiting the background information in the dynamic target, so that the distinguishing performance of the dynamic target and the background area is improved, and the foreground in the area is more prominent.
In a further optimized scheme, the step S4 comprises the following substeps:
s41, calculating an extended Lagrangian function of the detection model:
wherein y is Lagrangian multiplier, and beta is penalty parameter; />Representing the Frobenius norm;
s42, iteratively solving the multivariable optimization problem of the augmented Lagrangian function of the detection model until a convergence condition is met to obtain a real-time detection result of the dynamic target, wherein the convergence condition is that，/>Representing the L0 norm.
The further optimization scheme is that the dynamic amplitude level judging method comprises the following steps:
when the real-time detection result of the monitoring data is that the dynamic target exists, calculating the average area ratio of the attitude area of the dynamic target;
judging whether the average area occupation ratio belongs to an area threshold range, and when the average area occupation ratio belongs to the area threshold range and the dynamic target is a pedestrian; judging the dynamic amplitude level of the current monitoring data as a first level;
when the average area occupation ratio is within the area threshold range and the dynamic target is a living animal; judging the dynamic amplitude level of the current monitoring data as a second level;
otherwise, judging the dynamic amplitude level of the current monitoring data as a third level.
The further optimization scheme is that the monitoring video acquisition parameters comprise: resolution of camera, image quality, upper limit of code rate and frame rate;
taking the first resolution, the first image quality, the first code rate upper limit and the first frame rate as first-grade parameters;
taking the second resolution, the second image quality, the second code rate upper limit and the second frame rate as second-gear parameters;
taking a third resolution, a third image quality, a third code rate upper limit and a third frame rate as third-gear parameters;
taking a fourth resolution, a fourth image quality, a fourth code rate upper limit and a fourth frame rate as fourth-gear parameters;
wherein the first resolution, the second resolution, the third resolution and the fourth resolution are sequentially increased; the first image quality, the second image quality, the third image quality and the fourth image quality are sequentially increased; the first upper limit of the code rate, the second upper limit of the code rate, the third upper limit of the code rate and the fourth upper limit of the code rate are sequentially increased; the second frame rate, the third frame rate, and the fourth frame rate are all greater than the first frame rate.
The further optimization scheme is that the monitoring video acquisition parameter adjusting method comprises the following steps:
if the current monitoring data has no dynamic target, adjusting the monitoring video acquisition parameters to be first-file parameters;
if the dynamic amplitude level is the first level, adjusting the monitoring video acquisition parameter to be a fourth-gear parameter;
if the dynamic amplitude level is the second level, adjusting the monitoring video acquisition parameter to be a third-gear parameter;
and if the dynamic amplitude level is the third level, adjusting the monitoring video acquisition parameter to be the second-gear parameter.
The further optimization scheme is that the method for adjusting the transmission parameters of the monitoring video comprises the following steps:
if the current monitoring data has no dynamic target, adjusting the transmission mode of the monitoring video to be not transmitted;
if the dynamic amplitude level is the first level, adjusting the transmission mode of the monitoring video to be differential transmission;
and if the dynamic amplitude level is the second level and the third level, adjusting the transmission mode of the monitoring video to be normal transmission.
0015. For some communities with better green belts, the green plants shake along with wind in extreme weather, and a dynamic target exists in a monitoring area at the moment, but the green plants do not need to be excessively shot, so that the infrared sensing equipment can be combined to judge whether the green plants are pedestrians or animals in a gesture area, when the green plants are determined not to be pedestrians or animals in the gesture area, the green plants are judged to be of a third grade, and the monitoring video acquisition parameters and the monitoring video transmission modes of the intelligent community are adjusted according to the third grade;
for a community with a good green belt, more wild animals such as wild cats and birds exist, certain dynamic performance exists for the wild animals, in order to avoid excessive shooting of the wild animals, whether pedestrians are in a gesture area or not is detected according to a pedestrian detection method when the pedestrians are determined to be in the gesture area, if the pedestrians are pedestrians, the first grade is determined, and monitoring video acquisition parameters and monitoring video transmission modes of the intelligent community are adjusted according to the first grade; and judging the animals as a second grade, adjusting monitoring video acquisition parameters and monitoring video transmission modes of the intelligent community according to the second grade, acquiring video data of pedestrians with optimal acquisition quality, acquiring video data of wild animals with suboptimal acquisition quality, acquiring natural video data with final-stage acquisition quality, and respectively transmitting the video data with different transmission modes to different grades.
The scheme also provides an intelligent community monitoring management system based on dynamic target detection, which is used for realizing the intelligent community monitoring management system based on dynamic target detection and comprises the following components:
the acquisition module is used for acquiring monitoring data of the intelligent community and preprocessing the monitoring data;
the detection module is used for detecting the dynamic target based on the preprocessed monitoring data and judging the dynamic amplitude level of the monitoring data with the dynamic target;
and the adjusting module is used for adjusting the monitoring video acquisition parameters and the monitoring video transmission modes of the intelligent community based on the dynamic target detection result and the dynamic amplitude level judgment result.
The present solution also provides a computer readable medium having stored thereon a computer program to be executed by a processor to implement the intelligent community monitoring management method based on dynamic object detection as described above.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the invention provides an intelligent community monitoring management method, system and medium based on dynamic target detection; the method is improved on the basis of the existing method, the monitoring video acquisition parameters and the monitoring video transmission modes of the intelligent community are adjusted based on the dynamic target detection result and the dynamic amplitude level judgment result, so that broadband waste and data redundancy caused by unreasonable equipment data sampling rate are avoided, the data sampling rate is regulated and controlled according to the content of monitoring data by a more intelligent data sampling rate control mechanism, and the problem of broadband efficiency deficiency is solved. The invention carries out dynamic amplitude grade judgment on the monitoring data with the dynamic target; and the monitoring video acquisition parameters and the monitoring video transmission modes of the intelligent community are adjusted based on the dynamic target detection result and the dynamic amplitude level judgment result, so that the shot video data are more meaningful, and the camera device selects acquisition modes and transmission modes with different qualities according to different dynamic amplitude levels, so that the network flow consumed by transmission is reduced to the greatest extent fundamentally.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings that are needed in the examples will be briefly described below, it being understood that the following drawings only illustrate some examples of the present invention and therefore should not be considered as limiting the scope, and that other related drawings may be obtained from these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a schematic flow chart of an intelligent community monitoring and management method based on dynamic target detection;
description of the embodiments
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention.
The traditional monitoring video transmission is characterized in that no matter how the pedestrian condition of the monitored scene is, the camera device transmits a uniform acquisition mode and transmission mode, so that waste of a large amount of transmission broadband is easily caused when no pedestrian or fewer pedestrians are present, and the following technical problems are solved by the following embodiments:
example 1
The embodiment provides an intelligent community monitoring management method based on dynamic target detection, as shown in fig. 1, including:
step one: acquiring monitoring data of an intelligent community and preprocessing the monitoring data;
the pretreatment method comprises the following steps:
acquiring image data of the monitoring data;
dividing a background area and a foreground area of the image data, and classifying a stationary point and a moving point of the image data from two adjacent frames of image data based on an inter-frame difference method; taking a stationary point as a background pixel point and a motion point as a foreground pixel point;
candidate background pixel points are extracted from background pixel points based on a Bayesian decision method, and candidate foreground pixel points are extracted from foreground pixel points.
Candidate background pixel points are extracted from background pixel points based on a Bayesian decision method, and candidate foreground pixel points are extracted from foreground pixel points. Respectively acquiring posterior probability of the background and posterior probability of the foreground based on a Bayesian decision method; extracting feature vectors from foreground targets and background targets of the image data, and acquiring feature vector probabilities; and respectively associating the background area and the foreground area in the image with the feature vectors, and dividing candidate background pixel points and candidate foreground pixel points according to the probability of the feature vectors.
Step two: detecting a dynamic target based on the preprocessed monitoring data, and judging the dynamic amplitude level of the monitoring data with the dynamic target;
the method for detecting the dynamic target comprises the following steps:
s1, weighting calculation is carried out on candidate pixel points: according toCalculating the weight vector of each pixel point; wherein u represents the pixel factor of the pixel point, and w represents the weight;
s2, setting the weight vector of the pixel point i as a diagonal element to establish a diagonal matrixAnd sets the weight vector of each pixel point as a diagonal matrix +.>Obtaining a weight matrix B of the video sequence through the arrangement of the column vectors;
s3, byEstimating a gesture area of a dynamic target in image data for a detection model; wherein n represents the total number of candidate pixel points, alpha is the attitude parameter of the dynamic target, and +.>E and C are respectively low-rank components and sparse components of a weight matrix B, and Z is a possible gesture parameter of a dynamic target; />Represents the core norm of E;represents an L1 norm;
s4, solving the convex optimization problem of the detection model to obtain the real-time detection result of the dynamic target, and outputting the real-time detection result and the attitude area of the dynamic target.
Step S4 comprises the following sub-steps:
s41, calculating an extended Lagrangian function of the detection model:
wherein y is Lagrangian multiplier, and beta is penalty parameter; />Representing the Frobenius norm;
s42, iteratively solving the multivariable optimization problem of the augmented Lagrangian function of the detection model until a convergence condition is met to obtain a real-time detection result of the dynamic target, wherein the convergence condition is that，/>Representing the L0 norm.
The dynamic amplitude level judging method comprises the following steps:
when the real-time detection result of the monitoring data is that the dynamic target exists, calculating the average area ratio of the attitude area of the dynamic target;
judging whether the average area occupation ratio belongs to an area threshold range, and when the average area occupation ratio belongs to the area threshold range and the dynamic target is a pedestrian; judging the dynamic amplitude level of the current monitoring data as a first level;
when the average area occupation ratio is within the area threshold range and the dynamic target is a living animal; judging the dynamic amplitude level of the current monitoring data as a second level;
otherwise, judging the dynamic amplitude level of the current monitoring data as a third level.
Whether the pedestrian or animal is in the gesture area can be judged by combining the infrared sensing equipment, when the pedestrian or animal is not in the gesture area, the third grade is judged, and the monitoring video acquisition parameters and the monitoring video transmission mode of the intelligent community are adjusted according to the third grade; when the pedestrian or animal in the gesture area is determined, detecting whether the pedestrian is in the gesture area according to a pedestrian detection method, if the pedestrian is in the gesture area, judging the pedestrian as a first grade, and adjusting the monitoring video acquisition parameters and the monitoring video transmission mode of the intelligent community according to the first grade; and judging the animals as a second grade, and adjusting the monitoring video acquisition parameters and the monitoring video transmission modes of the intelligent community according to the second grade.
Step three: and adjusting the monitoring video acquisition parameters and the monitoring video transmission modes of the intelligent community according to the dynamic target detection result and the dynamic amplitude level judgment result.
The monitoring video acquisition parameters comprise: resolution of camera, image quality, upper limit of code rate and frame rate;
taking the first resolution, the first image quality, the first code rate upper limit and the first frame rate as first-grade parameters;
taking the second resolution, the second image quality, the second code rate upper limit and the second frame rate as second-gear parameters;
taking a third resolution, a third image quality, a third code rate upper limit and a third frame rate as third-gear parameters;
taking a fourth resolution, a fourth image quality, a fourth code rate upper limit and a fourth frame rate as fourth-gear parameters;
wherein the first resolution, the second resolution, the third resolution and the fourth resolution are sequentially increased; the first image quality, the second image quality, the third image quality and the fourth image quality are sequentially increased; the first upper limit of the code rate, the second upper limit of the code rate, the third upper limit of the code rate and the fourth upper limit of the code rate are sequentially increased; the second frame rate, the third frame rate, and the fourth frame rate are all greater than the first frame rate.
The monitoring video acquisition parameter adjustment method comprises the following steps:
if the current monitoring data has no dynamic target, adjusting the monitoring video acquisition parameters to be first-file parameters;
if the dynamic amplitude level is the first level, adjusting the monitoring video acquisition parameter to be a fourth-gear parameter;
if the dynamic amplitude level is the second level, adjusting the monitoring video acquisition parameter to be a third-gear parameter;
and if the dynamic amplitude level is the third level, adjusting the monitoring video acquisition parameter to be the second-gear parameter.
The method for adjusting the transmission parameters of the monitoring video comprises the following steps:
if the current monitoring data has no dynamic target, adjusting the transmission mode of the monitoring video to be not transmitted;
if the dynamic amplitude level is the first level, adjusting the transmission mode of the monitoring video to be differential transmission;
and if the dynamic amplitude level is the second level and the third level, adjusting the transmission mode of the monitoring video to be normal transmission.
For some communities with better green belts, the green plants shake along with wind in extreme weather, and a dynamic target exists in a monitoring area at the moment, but the green plants do not need to be excessively shot, so that the infrared sensing equipment can be combined to judge whether the green plants are pedestrians or animals in a gesture area, when the green plants are determined not to be pedestrians or animals in the gesture area, the green plants are judged to be of a third grade, and the monitoring video acquisition parameters and the monitoring video transmission modes of the intelligent community are adjusted according to the third grade;
for a community with a good green belt, more wild animals such as wild cats and birds exist, certain dynamic performance exists for the wild animals, in order to avoid excessive shooting of the wild animals, whether pedestrians are in a gesture area or not is detected according to a pedestrian detection method when the pedestrians are determined to be in the gesture area, if the pedestrians are pedestrians, the first grade is determined, and monitoring video acquisition parameters and monitoring video transmission modes of the intelligent community are adjusted according to the first grade; and judging the animals as a second grade, adjusting monitoring video acquisition parameters and monitoring video transmission modes of the intelligent community according to the second grade, acquiring video data of pedestrians with optimal acquisition quality, acquiring video data of wild animals with suboptimal acquisition quality, acquiring natural video data with final-stage acquisition quality, and respectively transmitting the video data with different transmission modes to different grades.
The embodiment carries out dynamic amplitude level judgment on the monitoring data with the dynamic target; and the monitoring video acquisition parameters and the monitoring video transmission modes of the intelligent community are adjusted based on the dynamic target detection result and the dynamic amplitude level judgment result, so that the shot video data are more meaningful, and the camera device selects acquisition modes and transmission modes with different qualities according to different dynamic amplitude levels, so that the network flow consumed by transmission is reduced to the greatest extent fundamentally.
Example 2
The embodiment provides an intelligent community monitoring management system based on dynamic target detection, which is used for the intelligent community monitoring management system based on dynamic target detection described in the previous embodiment, and includes:
the acquisition module is used for acquiring monitoring data of the intelligent community and preprocessing the monitoring data;
the detection module is used for detecting the dynamic target based on the preprocessed monitoring data and judging the dynamic amplitude level of the monitoring data with the dynamic target;
and the adjusting module is used for adjusting the monitoring video acquisition parameters and the monitoring video transmission modes of the intelligent community based on the dynamic target detection result and the dynamic amplitude level judgment result.
Example 3
The present embodiment provides a computer-readable medium having stored thereon a computer program that is executed by a processor to implement the intelligent community monitoring management method based on dynamic object detection as described in embodiment 1.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (6)
1. The intelligent community monitoring management method based on dynamic target detection is characterized by comprising the following steps of:
acquiring monitoring data of an intelligent community and preprocessing the monitoring data;
detecting a dynamic target based on the preprocessed monitoring data, and judging the dynamic amplitude level of the monitoring data with the dynamic target;
the dynamic amplitude level judging method comprises the following steps:
when the real-time detection result of the monitoring data is that the dynamic target exists, calculating the average area ratio of the attitude area of the dynamic target;
judging whether the average area occupation ratio belongs to an area threshold range, and when the average area occupation ratio belongs to the area threshold range and the dynamic target is a pedestrian; judging the dynamic amplitude level of the current monitoring data as a first level;
when the average area occupation ratio is within the area threshold range and the dynamic target is a living animal; judging the dynamic amplitude level of the current monitoring data as a second level;
otherwise, judging the dynamic amplitude level of the current monitoring data to be a third level;
adjusting monitoring video acquisition parameters and monitoring video transmission modes of the intelligent community according to the dynamic target detection result and the dynamic amplitude level judgment result;
the monitoring video acquisition parameters comprise: resolution of camera, image quality, upper limit of code rate and frame rate;
taking the first resolution, the first image quality, the first code rate upper limit and the first frame rate as first-grade parameters;
taking the second resolution, the second image quality, the second code rate upper limit and the second frame rate as second-gear parameters;
taking a third resolution, a third image quality, a third code rate upper limit and a third frame rate as third-gear parameters;
taking a fourth resolution, a fourth image quality, a fourth code rate upper limit and a fourth frame rate as fourth-gear parameters;
wherein the first resolution, the second resolution, the third resolution and the fourth resolution are sequentially increased; the first image quality, the second image quality, the third image quality and the fourth image quality are sequentially increased; the first upper limit of the code rate, the second upper limit of the code rate, the third upper limit of the code rate and the fourth upper limit of the code rate are sequentially increased; the second frame rate, the third frame rate, and the fourth frame rate are all greater than the first frame rate;
the monitoring video acquisition parameter adjustment method comprises the following steps:
if the current monitoring data has no dynamic target, adjusting the monitoring video acquisition parameters to be first-file parameters;
if the dynamic amplitude level is the first level, adjusting the monitoring video acquisition parameter to be a fourth-gear parameter;
if the dynamic amplitude level is the second level, adjusting the monitoring video acquisition parameter to be a third-gear parameter;
if the dynamic amplitude level is the third level, adjusting the monitoring video acquisition parameter to be a second-gear parameter;
the method for adjusting the transmission parameters of the monitoring video comprises the following steps:
if the current monitoring data has no dynamic target, adjusting the transmission mode of the monitoring video to be not transmitted;
if the dynamic amplitude level is the first level, adjusting the transmission mode of the monitoring video to be differential transmission;
and if the dynamic amplitude level is the second level and the third level, adjusting the transmission mode of the monitoring video to be normal transmission.
2. The intelligent community monitoring management method based on dynamic target detection according to claim 1, wherein the preprocessing method comprises:
acquiring image data of the monitoring data;
dividing a background area and a foreground area of the image data, and classifying a stationary point and a moving point of the image data from two adjacent frames of image data based on an inter-frame difference method; taking a stationary point as a background pixel point and a motion point as a foreground pixel point;
candidate background pixel points are extracted from background pixel points based on a Bayesian decision method, and candidate foreground pixel points are extracted from foreground pixel points.
3. The intelligent community monitoring management method based on dynamic object detection according to claim 2, wherein the method for dynamic object detection comprises:
s1, weighting calculation is carried out on candidate pixel points: according toCalculating the weight vector of each pixel point; wherein u represents the pixel factor of the pixel point, and w represents the weight;
s2, setting the weight vector of the pixel point i as a diagonal element to establish a diagonal matrixAnd sets the weight vector of each pixel point as a diagonal matrix +.>Obtaining a weight matrix B of the video sequence through the arrangement of the column vectors;
s3, byEstimating a gesture area of a dynamic target in image data for a detection model; wherein n represents the total number of candidate pixel points, alpha is the attitude parameter of the dynamic target, and +.>E and C are respectively low-rank components and sparse components of a weight matrix B, and Z is a possible gesture parameter of a dynamic target; />Represents the core norm of E; />Represents an L1 norm;
s4, solving the convex optimization problem of the detection model to obtain the real-time detection result of the dynamic target, and outputting the real-time detection result and the attitude area of the dynamic target.
4. The intelligent community monitoring management method based on dynamic object detection according to claim 3, wherein step S4 comprises the sub-steps of:
s41, calculating an extended Lagrangian function of the detection model:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein y is Lagrangian multiplier, and beta is penalty parameter; />Representation ofFrobenius norm;
s42, iteratively solving the multivariable optimization problem of the augmented Lagrangian function of the detection model until a convergence condition is met to obtain a real-time detection result of the dynamic target, wherein the convergence condition is that，/>Representing the L0 norm.
5. The intelligent community monitoring management system based on dynamic target detection is characterized by being used for realizing the intelligent community monitoring management method based on dynamic target detection as claimed in any one of claims 1-4, and comprising the following steps:
the acquisition module is used for acquiring monitoring data of the intelligent community and preprocessing the monitoring data;
the detection module is used for detecting the dynamic target based on the preprocessed monitoring data and judging the dynamic amplitude level of the monitoring data with the dynamic target;
and the adjusting module is used for adjusting the monitoring video acquisition parameters and the monitoring video transmission modes of the intelligent community based on the dynamic target detection result and the dynamic amplitude level judgment result.
6. A computer readable medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the dynamic object detection-based intelligent community monitoring management method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310710895.7A CN116456061B (en) | 2023-06-15 | 2023-06-15 | Intelligent community monitoring management method, system and medium based on dynamic target detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310710895.7A CN116456061B (en) | 2023-06-15 | 2023-06-15 | Intelligent community monitoring management method, system and medium based on dynamic target detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116456061A CN116456061A (en) | 2023-07-18 |
| CN116456061B true CN116456061B (en) | 2023-09-08 |
Family
ID=87134095
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310710895.7A Active CN116456061B (en) | 2023-06-15 | 2023-06-15 | Intelligent community monitoring management method, system and medium based on dynamic target detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116456061B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117098282B (en) * | 2023-10-18 | 2024-01-09 | 硬创(济宁)控股有限公司 | Big data management system and method based on intelligent park |
| CN117372968B (en) * | 2023-12-07 | 2024-03-22 | 深圳市智慧城市通信有限公司 | Electric vehicle home-entering monitoring method based on Internet of things |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06152547A (en) * | 1992-11-06 | 1994-05-31 | Victor Co Of Japan Ltd | Transmitting method for audio signal |
| US6384862B1 (en) * | 1997-03-12 | 2002-05-07 | Telefoaktiebolaget L M Ericsson | Imaging system and method for interactive control of image quality |
| CN102082947A (en) * | 2009-11-26 | 2011-06-01 | 中国移动通信集团公司 | Method, system and apparatus for video monitoring |
| CN105451075A (en) * | 2014-08-27 | 2016-03-30 | 北京大学 | Video quality control method and video quality control device |
| CN105791774A (en) * | 2016-03-31 | 2016-07-20 | 北京工业大学 | Surveillance video transmission method based on video content analysis |
| CN105979210A (en) * | 2016-06-06 | 2016-09-28 | 深圳市深网视界科技有限公司 | Pedestrian identification system based on multi-ball multi-gun camera array |
| CN106056347A (en) * | 2016-05-16 | 2016-10-26 | 北京诺士诚国际工程项目管理有限公司 | Engineering project management cloud platform system based on video monitoring |
| CN110650320A (en) * | 2019-10-23 | 2020-01-03 | 海能达通信股份有限公司 | Dynamic frame rate storage method and device and monitoring equipment |
| CN112422879A (en) * | 2019-08-20 | 2021-02-26 | 华为技术有限公司 | Method and device for dynamically adjusting media capability |
| CN115988181A (en) * | 2023-03-08 | 2023-04-18 | 四川三思德科技有限公司 | Personnel monitoring system and method based on infrared image algorithm |
-
2023
- 2023-06-15 CN CN202310710895.7A patent/CN116456061B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06152547A (en) * | 1992-11-06 | 1994-05-31 | Victor Co Of Japan Ltd | Transmitting method for audio signal |
| US6384862B1 (en) * | 1997-03-12 | 2002-05-07 | Telefoaktiebolaget L M Ericsson | Imaging system and method for interactive control of image quality |
| CN102082947A (en) * | 2009-11-26 | 2011-06-01 | 中国移动通信集团公司 | Method, system and apparatus for video monitoring |
| CN105451075A (en) * | 2014-08-27 | 2016-03-30 | 北京大学 | Video quality control method and video quality control device |
| CN105791774A (en) * | 2016-03-31 | 2016-07-20 | 北京工业大学 | Surveillance video transmission method based on video content analysis |
| CN106056347A (en) * | 2016-05-16 | 2016-10-26 | 北京诺士诚国际工程项目管理有限公司 | Engineering project management cloud platform system based on video monitoring |
| CN105979210A (en) * | 2016-06-06 | 2016-09-28 | 深圳市深网视界科技有限公司 | Pedestrian identification system based on multi-ball multi-gun camera array |
| CN112422879A (en) * | 2019-08-20 | 2021-02-26 | 华为技术有限公司 | Method and device for dynamically adjusting media capability |
| CN110650320A (en) * | 2019-10-23 | 2020-01-03 | 海能达通信股份有限公司 | Dynamic frame rate storage method and device and monitoring equipment |
| CN115988181A (en) * | 2023-03-08 | 2023-04-18 | 四川三思德科技有限公司 | Personnel monitoring system and method based on infrared image algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 基于视频处理技术的运动目标姿态检测与控制;《沈阳工业大学学报》;第第45卷卷(第第1期期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116456061A (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116456061B (en) | Intelligent community monitoring management method, system and medium based on dynamic target detection | |
| WO2021088300A1 (en) | Rgb-d multi-mode fusion personnel detection method based on asymmetric double-stream network | |
| WO2020173226A1 (en) | Spatial-temporal behavior detection method | |
| CN105516720B (en) | A kind of self-adaptation control method of monitor camera code stream | |
| US10496903B2 (en) | Using image analysis algorithms for providing training data to neural networks | |
| WO2017000465A1 (en) | Method for real-time selection of key frames when mining wireless distributed video coding | |
| CN111292264A (en) | Image high dynamic range reconstruction method based on deep learning | |
| CN108960290A (en) | Image processing method, device, computer readable storage medium and electronic equipment | |
| CN109063737A (en) | Image processing method, device, storage medium and mobile terminal | |
| CN110427922A (en) | One kind is based on machine vision and convolutional neural networks pest and disease damage identifying system and method | |
| CN110022422B (en) | Video frame sequence generation method based on dense connection network | |
| CN107547898B (en) | Energy consumption-controllable sensor double-parameter distribution system with precision | |
| CN106993188B (en) | A kind of HEVC compaction coding method based on plurality of human faces saliency | |
| CN111291663B (en) | Method for quickly segmenting video target object by using space-time information | |
| CN113255464A (en) | Airplane action recognition method and system | |
| CN112435257A (en) | Smoke detection method and system based on multispectral imaging | |
| CN112200008A (en) | Face attribute recognition method in community monitoring scene | |
| CN116614705A (en) | Coal face camera regulation and control system based on multi-mode video feature analysis | |
| CN114040124B (en) | Camera self-adaptive exposure processing system and method for forest and grassland patrol unmanned aerial vehicle | |
| CN115797396A (en) | Mixed Gaussian model foreground segmentation method for overcoming illumination mutation | |
| US20210329285A1 (en) | Image processing apparatus, image processing method, and non-transitory computer-readable storage medium | |
| CN104079934A (en) | Method for extracting regions of interest in real-time video communication | |
| CN117280708A (en) | Shutter value adjustment of monitoring camera using AI-based object recognition | |
| CN112541859A (en) | Illumination self-adaptive face image enhancement method | |
| CN112752102A (en) | Video code rate distribution method based on visual saliency |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |