CN114554664B - Road illumination energy-saving method, device, equipment and medium based on edge calculation - Google Patents
Road illumination energy-saving method, device, equipment and medium based on edge calculation Download PDFInfo
- Publication number
- CN114554664B CN114554664B CN202111339710.3A CN202111339710A CN114554664B CN 114554664 B CN114554664 B CN 114554664B CN 202111339710 A CN202111339710 A CN 202111339710A CN 114554664 B CN114554664 B CN 114554664B
- Authority
- CN
- China
- Prior art keywords
- street lamp
- video
- area
- value
- latest
- 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
Images
Classifications
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
- H05B47/105—Controlling the light source in response to determined parameters
- H05B47/115—Controlling the light source in response to determined parameters by determining the presence or movement of objects or living beings
- H05B47/125—Controlling the light source in response to determined parameters by determining the presence or movement of objects or living beings by using cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
- H05B47/155—Coordinated control of two or more light sources
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
- H05B47/165—Controlling the light source following a pre-assigned programmed sequence; Logic control [LC]
-
- 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
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Circuit Arrangement For Electric Light Sources In General (AREA)
Abstract
The invention provides a road illumination energy-saving method, a device, equipment and a medium based on edge calculation, wherein the method comprises the following steps: acquiring a video stream data set acquired by a video acquisition equipment set; acquiring a neural network algorithm model; reading the latest video pictures of all video stream data in the video stream data group, and inputting the latest video pictures into a neural network algorithm model to obtain the number of people and the number of vehicles in each latest video picture; according to the number of people and the number of vehicles in each latest video picture, calculating the area average thermal value of the whole target illumination area; and sending a lighting brightness output instruction to the street lamp equipment group in the target lighting area according to the calculated area average heating power value, so that the street lamp equipment group in the target lighting area is uniformly controlled. The invention has the advantages that: the overall implementation cost can be effectively reduced, and a better energy-saving effect is realized.
Description
Technical Field
The invention relates to the technical field of road illumination, in particular to an edge calculation-based road illumination energy-saving method, device, equipment and medium.
Background
Road lighting is an important component of municipal electricity consumption, and along with the development of urban construction of various countries, the electricity consumption of road lighting is also increasing year by year.
Based on the development of communication technology, with the proposal of 5G technology in recent years and the infrastructure construction of China in the communication field, the coverage and transmission capability of a communication network are greatly increased. In addition, based on the enhancement of the computing capability of the computer, the soil is provided for large-scale application of the neural network algorithm. The two factors are combined, and the concepts of the Internet of things, the smart city and the like are inoculated.
In a smart city scenario, road lighting uses smart street lamp products. On traditional street lamp basis, wisdom street lamp is because the promotion of chip own operational capability possesses output regulatory function, joins in the communication module again and makes the street lamp product can carry out information interaction with internet or LAN, in addition, establishes the unified management platform of internet high in the clouds, records the street lamp product of management registration on the network. Through the integrated management of the information, the street lamp products can be subjected to unified management control in a remote mode. At present, the energy-saving modes of the main stream of intelligent street lamps comprise:
(1) Duration fixed split mode: the lighting time at night is divided. Currently, the main stream is to divide the whole night illumination time into two sections, namely, generally adopting a 4+X mode, namely dividing the night illumination into a first half night (4 hours) and a second half night (variable free time length), wherein the first half night is 4 hours with fixed high brightness, and the second half night is X hours with preset or remotely arranged low-brightness illumination. However, the energy-saving effect of the mode depends on the matching degree of time segment segmentation and field requirements, the higher matching degree requires more time segments to be segmented, more parameters need to be set, and meanwhile, the randomness of high matching parameters can be caused due to the randomness of the installation field; therefore, the practice effect of the method is poor, and the high energy-saving effect is difficult to achieve.
(2) Adaptive adjustment mode: video monitoring and people flow identification functions are added to a single intelligent street lamp, and the brightness output of the intelligent street lamp is adjusted through statistics of people flow, for example, the application date is 2015.01.08, and the intelligent street lamp control system based on target identification is disclosed in the application number 201510007655.6. However, each intelligent street lamp is required to have the functions of video input and face recognition, so that the external equipment is complex, the requirement on the operation capability of the main control chip is high, the single intelligent street lamp is high in cost, and the additional power consumption and the chip operation power consumption of newly added equipment are caused while energy is saved; in addition, the intelligent street lamp has different output because of the angle problem of video input, and the overall lighting effect is poor.
Therefore, the energy-saving mode in the prior art has the problems of poor energy-saving effect and high cost. In view of the above, the present inventors have made intensive studies to solve the above-mentioned drawbacks of the prior art.
Disclosure of Invention
The invention aims to solve the technical problems of poor energy-saving effect and high cost in the prior art by providing an edge calculation-based road illumination energy-saving method, device, equipment and medium.
In a first aspect, the present invention provides a road lighting energy saving method based on edge calculation, the method is applied to an edge calculation gateway, and the method includes the following steps:
acquiring a video stream data group acquired by a video acquisition device group, wherein the video acquisition device group comprises at least one video acquisition device which is arranged in a target illumination area and is used for acquiring video stream data;
acquiring a neural network algorithm model, wherein the neural network algorithm model comprises a face recognition neural network model and a vehicle recognition neural network model;
reading the latest video pictures of all video stream data in the video stream data group; inputting all the read latest video pictures into a face recognition neural network model for face recognition to obtain the number of people in each latest video picture; inputting all the read latest video pictures into a vehicle identification neural network model for vehicle identification to obtain the number of vehicles in each latest video picture;
according to the number of people and the number of vehicles in each latest video picture, calculating a comprehensive thermodynamic value of the people and the vehicles corresponding to each latest video picture; calculating the area average thermal value of the whole target illumination area by utilizing the comprehensive thermal values of the vehicles corresponding to all the latest video pictures;
Transmitting illumination brightness output instructions to the street lamp equipment groups in the target illumination area according to the calculated area average thermal value, so that the street lamp equipment groups in the target illumination area are uniformly controlled; the street light equipment group comprises at least one street light equipment for illumination, which is installed in a target illumination area.
In a second aspect, the invention provides an edge calculation-based road illumination energy-saving device, which is an edge calculation gateway and comprises a video stream acquisition module, a network model acquisition module, an identification module, a thermal value calculation module and a brightness output control module;
the video stream acquisition module is used for acquiring a video stream data group acquired by a video acquisition device group, and the video acquisition device group comprises at least one video acquisition device which is arranged in a target illumination area and is used for acquiring video stream data;
the network model acquisition module is used for acquiring a neural network algorithm model, wherein the neural network algorithm model comprises a face recognition neural network model and a vehicle recognition neural network model;
the identification module is used for reading the latest video pictures of all video stream data in the video stream data group; inputting all the read latest video pictures into a face recognition neural network model for face recognition to obtain the number of people in each latest video picture; inputting all the read latest video pictures into a vehicle identification neural network model for vehicle identification to obtain the number of vehicles in each latest video picture;
The thermodynamic value calculation module is used for calculating the comprehensive thermodynamic value of the person and the vehicle corresponding to each latest video picture according to the number of the persons and the number of the vehicles in each latest video picture; calculating the area average thermal value of the whole target illumination area by utilizing the comprehensive thermal values of the vehicles corresponding to all the latest video pictures;
the brightness output control module is used for transmitting a brightness output instruction to the street lamp equipment group in the target illumination area according to the calculated area average thermal value so as to realize unified control on the street lamp equipment group in the target illumination area; the street light equipment group comprises at least one street light equipment for illumination, which is installed in a target illumination area.
In a third aspect, the invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of the first aspect when executing the program.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the method of the first aspect.
The invention adopts a regional management mode, and the video stream data acquired by each video acquisition device in the video acquisition device group is integrated by deploying the video acquisition device group and the street lamp device group in the target illumination area and by means of the high-performance edge computing gateway, so that the illumination brightness output by the street lamp device group in the target illumination area is matched with the flow of people and/or vehicles in the target illumination area; therefore, compared with the energy-saving mode of the existing street lamp, the energy-saving street lamp has at least the following beneficial technical effects:
1. Compared with the existing fixed-duration dividing mode, the method has the advantages that the illumination brightness output by the street lamp equipment set can be matched with the flow of people and/or vehicles in the target illumination area, the situation that no people or vehicles exist in the target illumination area but the street lamp equipment set is wasted due to high brightness output is avoided, the situation that people or vehicles in the target illumination area are crowded but the street lamp equipment set cannot meet illumination requirements due to low brightness output is avoided, the method has better practical effect, and the energy-saving purpose can be better achieved.
2. Compared with the existing self-adaptive adjustment mode, at least one video acquisition device is deployed in the target illumination area without adding video monitoring and people flow identification functions to each intelligent street lamp, so that the complexity of external devices of the intelligent street lamp can be greatly reduced, and the extra power consumption caused by adding the external devices can be effectively reduced; meanwhile, the high-performance edge computing gateway is utilized to directly process the video stream data acquired by each video acquisition device, so that the requirement on the operation capability of a main control chip of a single street lamp device can be greatly reduced, and the response speed of processing is higher, so that the overall realization cost can be effectively reduced, and the response efficiency is improved; in addition, under unified control, the output brightness of each street lamp equipment in the street lamp equipment group is the same, and the overall lighting effect is better.
3. The functions of the conventional monitoring center and the remote control station are realized by utilizing the edge computing gateway through the edge computing technology, and the cloud platform is only used for receiving and displaying the data uploaded by the edge computing gateway, so that the equipment cost and the manpower resource cost brought by the conventional deployment of the monitoring center and the remote control station can be saved; the street lamp equipment of the street lamp equipment group only needs to have a remote brightness adjusting function, so that the street lamp equipment is simpler to realize, and is particularly more convenient to reform aiming at some traditional street lamps.
4. In the target illumination area, only the number of people and/or vehicles is needed to be judged, and the specific track of the people and/or vehicles is not needed to be judged, so that the operation amount of a specific algorithm can be greatly reduced, the operation efficiency is improved, and the requirement on the hardware performance of equipment can be reduced.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
The invention will be further described with reference to examples of embodiments with reference to the accompanying drawings.
FIG. 1 is a block flow diagram of a road illumination energy saving method based on edge calculation in a first embodiment of the invention;
FIG. 2 is a schematic diagram of a system frame structure according to the present invention;
fig. 3 is a schematic structural diagram of a road illumination energy-saving device based on edge calculation in the second embodiment of the invention;
FIG. 4 is a schematic diagram of the installation of a video acquisition device according to the present invention;
FIG. 5 is a schematic view of the field of view of the video capture device of the present invention;
FIG. 6 is a graph showing the thermal value of a target illumination area according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention;
fig. 8 is a schematic structural diagram of a medium in a fourth embodiment of the present invention.
Detailed Description
In order to better understand the technical scheme of the present invention, the following detailed description will refer to the accompanying drawings and specific embodiments.
Before describing the specific technical scheme of the present invention, first, the system architecture of the present invention is described, referring to fig. 2, where the system architecture of the present invention mainly includes an edge computing gateway, a video acquisition device group, a street lamp device group, and a cloud platform; the video acquisition equipment group refers to a plurality of video acquisition equipment in a target illumination area, and video stream data of each video acquisition equipment is accessed to an edge computing gateway; the street lamp equipment group is a plurality of street lamp equipment in a target illumination area, each street lamp equipment is communicated with the edge computing gateway, and each street lamp equipment can carry out output brightness adjustment control through the edge computing gateway; the edge computing gateway is used for processing data of the video acquisition equipment group and the street lamp equipment group and uploading the processed data to the cloud platform; the cloud platform is a network platform which is set up in the cloud of the Internet, can acquire data from the video acquisition equipment group and the street lamp equipment group from the edge computing gateway, and is used for but not limited to display system operation data, area average thermal values and the like.
Example 1
The embodiment provides a road lighting energy-saving method based on edge calculation, as shown in fig. 1, the method is applied to an edge calculation gateway, and the method comprises the following steps:
step S1, acquiring a video stream data set acquired by a video acquisition device set, wherein the video acquisition device set comprises at least one video acquisition device which is arranged in a target illumination area and is used for acquiring video stream data; wherein the target illumination area may be a road, several roads intersecting each other, a patch, etc.;
s2, acquiring a neural network algorithm model, wherein the neural network algorithm model comprises a face recognition neural network model and a vehicle recognition neural network model; the face recognition neural network model is used for realizing face recognition, and the vehicle recognition neural network model; for effecting vehicle identification;
step S3, reading the latest video pictures of all video stream data in the video stream data group, wherein each video stream data is a section of coded video data and consists of a plurality of frames of static lens pictures, so that when the method is implemented, the latest lens picture is read out to be used for identification after decoding the video stream data; inputting all the read latest video pictures into a face recognition neural network model for face recognition to obtain the number of people in each latest video picture; inputting all the read latest video pictures into a vehicle identification neural network model for vehicle identification to obtain the number of vehicles in each latest video picture;
Step S4, calculating a comprehensive thermodynamic value of the person and the vehicle corresponding to each latest video picture according to the number of persons and the number of vehicles in each latest video picture; calculating the area average thermal value of the whole target illumination area by utilizing the comprehensive thermal values of the vehicles corresponding to all the latest video pictures;
s5, transmitting a lighting brightness output instruction to the street lamp equipment group in the target lighting area according to the calculated area average heating power value, so as to realize unified control of the street lamp equipment group in the target lighting area; the street light equipment group comprises at least one street light equipment for illumination, which is installed in a target illumination area.
The invention adopts a regional management mode, and the video stream data acquired by each video acquisition device in the video acquisition device group is integrated by deploying the video acquisition device group and the street lamp device group in the target illumination area and by means of the high-performance edge computing gateway, so that the illumination brightness output by the street lamp device group in the target illumination area is matched with the flow of people and/or vehicles in the target illumination area; therefore, compared with the energy-saving mode of the existing street lamp, the energy-saving street lamp has at least the following beneficial effects:
1. Compared with the existing fixed-duration dividing mode, the method has the advantages that the illumination brightness output by the street lamp equipment set can be matched with the flow of people and/or vehicles in the target illumination area, the situation that no people or vehicles exist in the target illumination area but the street lamp equipment set is wasted due to high brightness output is avoided, the situation that people or vehicles in the target illumination area are crowded but the street lamp equipment set cannot meet illumination requirements due to low brightness output is avoided, the method has better practical effect, and the energy-saving purpose can be better achieved.
2. Compared with the existing self-adaptive adjustment mode, at least one video acquisition device is deployed in the target illumination area without adding video monitoring and people flow identification functions to each intelligent street lamp, so that the complexity of external devices of the intelligent street lamp can be greatly reduced, and the extra power consumption caused by adding the external devices can be effectively reduced; meanwhile, the high-performance edge computing gateway is utilized to directly process the video stream data acquired by each video acquisition device, so that the requirement on the operation capability of a main control chip of a single street lamp device can be greatly reduced, and the response speed of processing is higher, so that the overall realization cost can be effectively reduced, and the response efficiency is improved; in addition, under unified control, the output brightness of each street lamp equipment in the street lamp equipment group is the same, and the overall lighting effect is better.
3. The functions of the conventional monitoring center and the remote control station are realized by utilizing the edge computing gateway through the edge computing technology, and the cloud platform is only used for receiving and displaying the data uploaded by the edge computing gateway, so that the equipment cost and the manpower resource cost brought by the conventional deployment of the monitoring center and the remote control station can be saved; the street lamp equipment of the street lamp equipment group only needs to have a remote brightness adjusting function, so that the street lamp equipment is simpler to realize, and is particularly more convenient to reform aiming at some traditional street lamps.
4. In the target illumination area, only the number of people and/or vehicles is needed to be judged, and the specific track of the people and/or vehicles is not needed to be judged, so that the operation amount of a specific algorithm can be greatly reduced, the operation efficiency is improved, and the requirement on the hardware performance of equipment can be reduced.
The core idea of the invention is to analyze the regional thermal values by means of edge calculations. The number of people and vehicles in a unit area is taken in a specified area, namely the density of people and vehicles in the area can be represented.
Therefore, in the embodiment of the present invention, in the step S4, the calculating the comprehensive thermal value of the passenger and the vehicle corresponding to each latest video frame according to the number of people and the number of vehicles in each latest video frame specifically includes:
Record the number of people in each latest video picture as NumM i Recording the number of vehicles in each latest video picture as NumC i The method comprises the steps of carrying out a first treatment on the surface of the Acquiring the road area S covered by the video acquisition equipment corresponding to each latest video picture when shooting i Wherein i represents a natural number;
calculating the density DM of people in each latest video picture i And density DC of the vehicle i ，
For example, in a firstTaking the latest video picture as an example, assume that the number NumM of people in the first latest video picture 1 The number of vehicles NumC in the first latest video frame is 30 people 1 The number of the video acquisition devices is 10, and the road area S of the video acquisition device corresponding to the first latest video picture is covered when the video acquisition device shoots 1 100m of 2 Then, the density DM of the person 1 Is 0.3 person/m 2 Density DC of vehicle 1 Is 0.1/m 2 ；
Because of the density DM of the individual i And density DC of the vehicle i It is not yet possible to accurately grasp the dense condition in the target illumination area, and therefore it is necessary to set the extreme congestion density reference value D of the person refM And an extreme congestion density reference value D of the vehicle refC The method comprises the steps of carrying out a first treatment on the surface of the Simultaneous introduction of the human crowding factor f M And a vehicle congestion factor f C ，
Wherein, when DM i ＜D refM At time f M Larger indicates that the density is closer to D refM The degree of congestion referred to is the same as DC i ＜D refC At time f C Larger indicates that the density is closer to D refC The degree of congestion referenced; while when DM i ≥D refM At time f M =1 indicates that the degree of density is not lower than D refM The degree of congestion referred to is the same as DC i ≥D refC At time f C =1 indicates that the degree of density is not lower than D refC The degree of congestion referenced;
crowding factor f M For the road area S i The thermal value of the area describing the crowding degree of the person is similar to the thermal value of the area describing the crowding degree of the person, and the crowding factor f of the vehicle is set C For the road area S i An area heating power value internally describing a degree of congestion of the vehicle;
because the crowding degree reference of the target illumination area comprises people and vehicles, two factors of people and vehicles need to be comprehensively considered, the people-vehicle importance ratio g is introduced, and the value range of g is (0, 1); calculating the comprehensive thermodynamic value f of the man and car corresponding to each latest video picture i ，
f i ＝gf M +(1-g)f C (5)
Wherein the more the value of the importance ratio g of the human-vehicle is close to 1, f is represented i The judgment of the crowding degree of people is more emphasized; the more the value of the importance ratio g of the vehicle is close to 0, the f is expressed i The judgment of the crowding degree of the vehicle is more emphasized; in the specific implementation, the importance ratio g of the man-car can be valued within the range of (0, 1) according to the actual situation.
Since in practice the illumination of people and vehicles is often equally important, it is preferred that the people to vehicles importance ratio g takes a value of 0.5.
In the present invention, in order to facilitate implementation of the algorithm, preferably, in the video capturing device group, each video capturing device includes a road area S at the time of capturing i Equal. Meanwhile, as a preferred installation mode, the installation requirements of each video acquisition device in the invention are as follows: as shown in fig. 4, the installation height is 3m to 3.5m higher than the road surface, the angle orientation is 60 degrees between the ground and the plumb line direction, the visual angle range is 50 degrees, and the front is free from shielding. Of course, in the implementation, the installation requirement can be adjusted according to the actual requirement, for example, the angle orientation can be adjusted by + -5 degrees on the basis of 60 degrees, and the view angle range can be adjusted by + -5 degrees on the basis of 50 degrees.
The comprehensive thermodynamic value f of the man-vehicle is described below i Is calculated in detail:
because the total number of people and vehicles in the target illumination area is not easy to count, the invention adopts the Monte Carlo algorithm to estimate the density of the people and the vehicles in the target illumination area, and randomly acquires any area in the target illumination area as S i I represents a natural number, and the number of people in the region is NumM i The number of vehicles is NumC i ThenFor random variable S i ，NumM i And NumC i The method comprises the following steps:
E(f i )＝f (6)
i.e. for a random sub-area, the expected man-vehicle integrated thermal value for that sub-area is the same as the area average thermal value for the whole area. And:
according to the Monte Carlo algorithm, estimating the expectation of the comprehensive human-vehicle thermodynamic value of the subarea by using the observed calculated values of a limited subarea (denoted by N) in the target illumination area; namely:
substituting the formula (1), the formula (2), the formula (3) and the formula (4) into the formula (5) to obtain the calculation of the comprehensive thermodynamic value of the human and the vehicle:
to further simplify D refM And D refC Expressed as:
wherein, numM ref Representing the area S at a reference crowded population density ref Is the population number of (a); numC ref Representing the area S under the reference of the density of the crowded vehicle ref Is a vehicle number of (a);
the method further comprises the following steps:
because the video pictures acquired by the video acquisition equipment are used for counting the quantity in the invention, namely S i The road area S included by each video acquisition device when shooting is designed in the invention i Equal, namely:
S 1 ＝S 2 ＝...＝S i ＝...S n (13)
let S ref ＝S i Representing a video picture shot by using video acquisition equipment as a reference area, and simplifying to obtain:
substituting the man-vehicle importance ratio g=0.5 into the formula (14) to obtain the final man-vehicle comprehensive thermal value f i Is defined by the specific calculation formula:
because the video picture shot by the video acquisition equipment is used as the reference area in the invention, the shot pavement area is the cross section of the pavement to the viewing cone, wherein the viewing cone is assumed to be a cone, the ground is assumed to be a plane, and the cross section is an ellipse, as shown in fig. 5:
wherein h represents the height of the installation part from the ground, a represents the real axis length of the ellipse, b represents the virtual axis length of the ellipse, θ represents the included angle between the central axis of the lens and the plumb line, and α represents the view angle of the lens;
as an embodiment of the present invention, taking h=3m,θ=60°, α=50°, giving S i ≈489.72m 2 The method comprises the steps of carrying out a first treatment on the surface of the D is taken out refM =0.5 person/m 2 And D refC =0.05 vehicle/m 2 A reference of the number of persons and a reference of the number of vehicles can be obtained, e.g. in combination with the area S above i (i.e. S i ≈489.72m 2 ) It was found that the number of people in the lens reached 245 people, which was extremely crowded (i.e., numM ref =245), when reaching 25 vehicles, is extremely crowded (i.e. NumC ref =25). Of course, the present invention is not limited thereto, and in formula (15), numM ref And NumC ref The specific number of reference values may also follow S i 、D refM And D refC And vary from one to another.
In the embodiment of the present invention, in the step S4, the area average thermal value f of the entire target illumination area is calculated as follows:
Wherein the value interval of f is [0,1]]The method comprises the steps of carrying out a first treatment on the surface of the i represents a natural number; n is n v Representing the number of video acquisition devices in the video acquisition device group that are successfully accessed; f (f) i The specific calculation formula of (2) is formula (15).
As shown in fig. 6, fig. 6 shows a schematic diagram of thermal values of a certain target illumination area, where V1, V2, V3, V4, and V5 show video capturing devices, and f1, f2, f3, and f4 show comprehensive thermal values of a person and a vehicle in four sub-areas in the target illumination area.
In the embodiment of the invention, because the road illumination is suitable for the condition of road congestion, namely the required brightness of the road illumination is proportional to the regional average thermal value f, and the regional average thermal value is directly used for carrying out factor control on the road illumination due to the fact that the value interval of f is [0,1]; therefore, the street lamp equipment group for sending the illumination brightness output command to the target illumination area according to the calculated area average thermal value specifically comprises:
the calculated average thermal value of the area is f, and the value range of f is [0,1];
setting the maximum brightness output value of each street lamp equipment in the street lamp equipment group as L high Setting the maximum brightness output value of each street lamp equipment in the street lamp equipment group as L low ；
The actual luminance output value L is calculated from the area average thermal value f,
L＝fL high +(1-f)L low (18)
For example, when the area average thermal value f of a certain target illumination area is calculated to be 0.6, the actual luminance output value l=0.6l for that target illumination area high +0.4L low 。
In an embodiment of the invention, the method further comprises: initializing a video acquisition device group and a street lamp device group;
the initialization video acquisition equipment group specifically comprises: setting a video acquisition device address list video list representing an attempted connection; reading access addresses of video acquisition devices stored in an edge computing gateway into a video list of the video acquisition device address list attempted to be connected, and creating an index for each video acquisition device access address in the video acquisition device address list attempted to be connected; taking out access addresses of video acquisition equipment one by one from an address list of the video acquisition equipment which is tried to be connected according to the created index, attempting to create a video stream instance, and determining all video acquisition equipment which is accessed successfully; in particular, the variable n can also be set v For the number of successful video acquisition devices, when each video acquisition device access address is fetched according to the index and an attempt is made to create a video stream instance, if the video stream instance is successfully created, the variable n v The value of (2) is increased by 1; if the video stream instance creation fails, variable n v The value of (2) is not increased by 1, so that after completing the entire index attempt, the variable n v The value of (1) is the number of video acquisition devices that have been successfully accessed;
the initialization street lamp equipment group specifically comprises: setting a street lamp equipment address list (LampList) for representing the attempted connection; reading access address of street lamp equipment stored in edge computing gateway to address column of street lamp equipment attempting to connectIn the table, creating an index for each street lamp equipment access address in the street lamp equipment address list which is tried to be connected; taking out the street lamp equipment access addresses one by one from the street lamp equipment address list which is tried to be connected according to the created index, attempting to create communication connection, and determining all street lamp equipment which is successful in access; in particular, the variable n can also be set l For accessing the number of successful street lamp devices, when each street lamp device access address is fetched according to the index and the creation of a communication connection is attempted, if the communication connection is successfully created, the variable n is l The value of (2) is increased by 1; if the communication connection creation fails, variable n l The value of (2) is not increased by 1, so that after completing the entire index attempt, the variable n l The value of (1) is the number of street light devices that were successfully accessed. In step S5, when the illumination output command is issued to the street lamp equipment group in the target illumination area according to the calculated area average thermal value, only the illumination output command may be issued to all street lamp equipment in the target illumination area that is successfully accessed, and the street lamp equipment that is failed to access may not issue the illumination output command.
Of course, in the practice of the invention, if the variable n v If the value of (2) is 0, it indicates that there is no video capturing device capable of capturing video stream data normally in the target illumination area, and the method can switch to the fixed duration split mode (i.e. 4+X mode) to avoid affecting normal road illumination. And if the variable n l And finally, if the value of (2) is 0, indicating that no street lamp equipment capable of being controlled normally exists in the target illumination area, and ending the whole process at the moment.
In an embodiment of the invention, the method further comprises: and uploading the processing data of the video acquisition equipment group and the data of the street lamp equipment group to a cloud platform, and displaying related data by the cloud platform, wherein the displayed content comprises, but is not limited to, area average thermal value, information of successful video acquisition equipment, information of successful street lamp equipment, information of street lamp equipment with failed access and the like. Related data are displayed on the cloud platform, so that related personnel can check the running condition of each device conveniently, and maintenance is convenient; for example, when the street lamp equipment with access failure is found, the street lamp equipment is indicated to have abnormality, and related personnel can conduct fault investigation on the street lamp equipment with access failure.
In an embodiment of the invention, the method further comprises: initializing the data storage space of the face recognition neural network model and the vehicle recognition neural network model in the high-speed read-write medium, and reading the face recognition neural network model and the vehicle recognition neural network model stored in the low-speed read-write medium into the initialized data storage space in the high-speed read-write medium for storage. The face recognition neural network model and the vehicle recognition neural network model are a group of data, and are both existing models, and are trained and saved outside the invention; the high-speed read-write medium may be a cache memory and the low-speed read-write medium may be a hard disk. The face recognition neural network model and the vehicle recognition neural network model stored in the low-speed read-write medium are read into the initialized data storage space in the high-speed read-write medium for storage, so that the face recognition neural network model and the vehicle recognition neural network model can be conveniently and quickly obtained from the high-speed read-write medium when used each time, the data reading efficiency is improved, and larger delay is avoided.
Based on the same inventive concept, the present application also provides a device corresponding to the method in the first embodiment, and details of the second embodiment are described in the following.
Example two
In this embodiment, as shown in fig. 3, the energy-saving device for road illumination based on edge calculation is an edge calculation gateway, and includes a video stream acquisition module, a network model acquisition module, an identification module, a thermal value calculation module and a brightness output control module;
the video stream acquisition module is used for acquiring a video stream data group acquired by a video acquisition device group, and the video acquisition device group comprises at least one video acquisition device which is arranged in a target illumination area and is used for acquiring video stream data;
the network model acquisition module is used for acquiring a neural network algorithm model, wherein the neural network algorithm model comprises a face recognition neural network model and a vehicle recognition neural network model;
the identification module is used for reading the latest video pictures of all video stream data in the video stream data group; inputting all the read latest video pictures into a face recognition neural network model for face recognition to obtain the number of people in each latest video picture; inputting all the read latest video pictures into a vehicle identification neural network model for vehicle identification to obtain the number of vehicles in each latest video picture;
The thermodynamic value calculation module is used for calculating the comprehensive thermodynamic value of the person and the vehicle corresponding to each latest video picture according to the number of the persons and the number of the vehicles in each latest video picture; calculating the area average thermal value of the whole target illumination area by utilizing the comprehensive thermal values of the vehicles corresponding to all the latest video pictures;
the brightness output control module is used for transmitting a brightness output instruction to the street lamp equipment group in the target illumination area according to the calculated area average thermal value so as to realize unified control on the street lamp equipment group in the target illumination area; the street light equipment group comprises at least one street light equipment for illumination, which is installed in a target illumination area.
The invention adopts a regional management mode, and the video stream data acquired by each video acquisition device in the video acquisition device group is integrated by deploying the video acquisition device group and the street lamp device group in the target illumination area and by means of the high-performance edge computing gateway, so that the illumination brightness output by the street lamp device group in the target illumination area is matched with the flow of people and/or vehicles in the target illumination area; therefore, compared with the energy-saving mode of the existing street lamp, the energy-saving street lamp has at least the following beneficial effects:
1. Compared with the existing fixed-duration dividing mode, the method has the advantages that the illumination brightness output by the street lamp equipment set can be matched with the flow of people and/or vehicles in the target illumination area, the situation that no people or vehicles exist in the target illumination area but the street lamp equipment set is wasted due to high brightness output is avoided, the situation that people or vehicles in the target illumination area are crowded but the street lamp equipment set cannot meet illumination requirements due to low brightness output is avoided, the method has better practical effect, and the energy-saving purpose can be better achieved.
2. Compared with the existing self-adaptive adjustment mode, at least one video acquisition device is deployed in the target illumination area without adding video monitoring and people flow identification functions to each intelligent street lamp, so that the complexity of external devices of the intelligent street lamp can be greatly reduced, and the extra power consumption caused by adding the external devices can be effectively reduced; meanwhile, the high-performance edge computing gateway is utilized to directly process the video stream data acquired by each video acquisition device, so that the requirement on the operation capability of a main control chip of a single street lamp device can be greatly reduced, and the response speed of processing is higher, so that the overall realization cost can be effectively reduced, and the response efficiency is improved; in addition, under unified control, the output brightness of each street lamp equipment in the street lamp equipment group is the same, and the overall lighting effect is better.
3. The functions of the conventional monitoring center and the remote control station are realized by utilizing the edge computing gateway through the edge computing technology, and the cloud platform is only used for receiving and displaying the data uploaded by the edge computing gateway, so that the equipment cost and the manpower resource cost brought by the conventional deployment of the monitoring center and the remote control station can be saved; the street lamp equipment of the street lamp equipment group only needs to have a remote brightness adjusting function, so that the street lamp equipment is simpler to realize, and is particularly more convenient to reform aiming at some traditional street lamps.
4. In the target illumination area, only the number of people and/or vehicles is needed to be judged, and the specific track of the people and/or vehicles is not needed to be judged, so that the operation amount of a specific algorithm can be greatly reduced, the operation efficiency is improved, and the requirement on the hardware performance of equipment can be reduced.
The device described in the second embodiment of the present invention is a device for implementing the method in the first embodiment of the present invention, wherein the specific functions of the video stream acquisition module, the network model acquisition module, the identification module, the thermal value calculation module and the brightness output control module are described in detail with reference to the corresponding steps in the first embodiment, so that based on the method described in the first embodiment of the present invention, a person skilled in the art can understand the specific structure and the deformation of the device, and thus will not be described herein. All devices used in the method according to the first embodiment of the present invention are within the scope of the present invention.
Based on the same inventive concept, the application provides an electronic device embodiment corresponding to the first embodiment, and the details of the third embodiment are described in detail.
Example III
The present embodiment provides an electronic device, as shown in fig. 7, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where any implementation of the first embodiment may be implemented when the processor executes the computer program.
Since the electronic device described in this embodiment is a device for implementing the method described in the first embodiment of the present application, those skilled in the art will be able to understand the specific implementation of the electronic device and various modifications thereof based on the method described in the first embodiment of the present application, so how the method described in the embodiment of the present application is implemented in this electronic device will not be described in detail herein. The apparatus used to implement the methods of the embodiments of the present application are within the scope of what is intended to be protected by the present application.
Based on the same inventive concept, the application provides a storage medium corresponding to the first embodiment, and the details of the fourth embodiment are described in detail.
Example IV
The present embodiment provides a computer readable storage medium, as shown in fig. 8, on which a computer program is stored, which when executed by a processor, can implement any implementation of the first embodiment.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus, and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that the specific embodiments described are illustrative only and not intended to limit the scope of the invention, and that equivalent modifications and variations of the invention in light of the spirit of the invention will be covered by the claims of the present invention.
Claims (9)
1. The road illumination energy-saving method based on edge calculation is characterized by comprising the following steps of: the method is applied to the edge computing gateway and comprises the following steps:
acquiring a video stream data group acquired by a video acquisition device group, wherein the video acquisition device group comprises at least one video acquisition device which is arranged in a target illumination area and is used for acquiring video stream data;
acquiring a neural network algorithm model, wherein the neural network algorithm model comprises a face recognition neural network model and a vehicle recognition neural network model;
reading the latest video pictures of all video stream data in the video stream data group; inputting all the read latest video pictures into a face recognition neural network model for face recognition to obtain the number of people in each latest video picture; inputting all the read latest video pictures into a vehicle identification neural network model for vehicle identification to obtain the number of vehicles in each latest video picture;
according to the number of people and the number of vehicles in each latest video picture, calculating a comprehensive thermodynamic value of the people and the vehicles corresponding to each latest video picture; calculating the area average thermal value of the whole target illumination area by utilizing the comprehensive thermal values of the vehicles corresponding to all the latest video pictures;
Transmitting illumination brightness output instructions to the street lamp equipment groups in the target illumination area according to the calculated area average thermal value, so that the street lamp equipment groups in the target illumination area are uniformly controlled; the street lamp equipment group comprises at least one street lamp equipment for illumination, wherein the street lamp equipment is installed in a target illumination area;
according to the number of people and the number of vehicles in each latest video picture, the calculation of the comprehensive thermodynamic value of the people and the vehicles corresponding to each latest video picture specifically comprises the following steps:
record the number of people in each latest video picture as NumM i Recording the number of vehicles in each latest video picture as NumC i The method comprises the steps of carrying out a first treatment on the surface of the Acquiring the road area S covered by the video acquisition equipment corresponding to each latest video picture when shooting i Wherein i represents a natural number;
calculating the density DM of people in each latest video picture i And density DC of the vehicle i ，
Setting an extreme congestion density reference value D of a person refM And an extreme congestion density reference value D of the vehicle refC The method comprises the steps of carrying out a first treatment on the surface of the Simultaneous introduction of the human crowding factor f M And a vehicle congestion factor f C ，
Crowding factor f M For the road area S i The thermal value of the area describing the crowding degree of the person is similar to the thermal value of the area describing the crowding degree of the person, and the crowding factor f of the vehicle is set C For the road area S i An area heating power value internally describing a degree of congestion of the vehicle;
introducing a human-vehicle importance ratio g, wherein the value range of g is (0, 1); calculating the comprehensive thermodynamic value f of the man and car corresponding to each latest video picture i ，
f i ＝gf M +(1-g)f C 。
2. The edge-calculation-based roadway lighting energy-saving method of claim 1, wherein: the street lamp equipment group which transmits the illumination brightness output instruction to the target illumination area according to the calculated area average thermal value specifically comprises:
the calculated average thermal value of the area is f, and the value range of f is [0,1];
setting the maximum brightness output value of each street lamp equipment in the street lamp equipment group as L high Setting the maximum brightness output value of each street lamp equipment in the street lamp equipment group as L low ；
The actual luminance output value L is calculated from the area average thermal value f,
L＝fL high +(1-f)L low 。
3. the edge-calculation-based roadway lighting energy-saving method of claim 1, wherein: the method further comprises the steps of: initializing a video acquisition device group and a street lamp device group;
the initialization video acquisition equipment group specifically comprises: setting an address list of video acquisition equipment for representing the attempted connection; reading access addresses of video acquisition devices stored in an edge computing gateway into an address list of the video acquisition devices which are attempted to be connected, and creating an index for each access address of the video acquisition devices in the address list of the video acquisition devices which are attempted to be connected; taking out access addresses of video acquisition equipment one by one from an address list of the video acquisition equipment which is tried to be connected according to the created index, attempting to create a video stream instance, and determining all video acquisition equipment which is accessed successfully;
The initialization street lamp equipment group specifically comprises: setting a street lamp equipment address list for representing the attempted connection; reading the street lamp equipment access addresses stored in the edge computing gateway into a street lamp equipment address list which is tried to be connected, and creating an index for each street lamp equipment access address in the street lamp equipment address list which is tried to be connected; and taking out the street lamp equipment access addresses one by one from the street lamp equipment address list which is tried to be connected according to the created index, attempting to create communication connection, and determining all street lamp equipment which is successfully accessed.
4. The edge-calculation-based roadway lighting energy-saving method of claim 1, wherein: the method further comprises the steps of: initializing the data storage space of the face recognition neural network model and the vehicle recognition neural network model in the high-speed read-write medium, and reading the face recognition neural network model and the vehicle recognition neural network model stored in the low-speed read-write medium into the initialized data storage space in the high-speed read-write medium for storage.
5. The edge-calculation-based roadway lighting energy-saving method of claim 1, wherein: in the video acquisition equipment group, the road area S included by each video acquisition equipment during shooting i Equal.
6. The edge-calculation-based roadway lighting energy-saving method of claim 1, wherein: the important ratio g of the man-car is 0.5.
7. The utility model provides a road illumination economizer based on edge calculates which characterized in that: the energy-saving device is an edge computing gateway and comprises a video stream acquisition module, a network model acquisition module, an identification module, a thermodynamic value calculation module and a brightness output control module;
the video stream acquisition module is used for acquiring a video stream data group acquired by a video acquisition device group, and the video acquisition device group comprises at least one video acquisition device which is arranged in a target illumination area and is used for acquiring video stream data;
the network model acquisition module is used for acquiring a neural network algorithm model, wherein the neural network algorithm model comprises a face recognition neural network model and a vehicle recognition neural network model;
the identification module is used for reading the latest video pictures of all video stream data in the video stream data group; inputting all the read latest video pictures into a face recognition neural network model for face recognition to obtain the number of people in each latest video picture; inputting all the read latest video pictures into a vehicle identification neural network model for vehicle identification to obtain the number of vehicles in each latest video picture;
The thermodynamic value calculation module is used for calculating the comprehensive thermodynamic value of the person and the vehicle corresponding to each latest video picture according to the number of the persons and the number of the vehicles in each latest video picture; calculating the area average thermal value of the whole target illumination area by utilizing the comprehensive thermal values of the vehicles corresponding to all the latest video pictures;
the brightness output control module is used for transmitting a brightness output instruction to the street lamp equipment group in the target illumination area according to the calculated area average thermal value so as to realize unified control on the street lamp equipment group in the target illumination area; the street lamp equipment group comprises at least one street lamp equipment for illumination, wherein the street lamp equipment is installed in a target illumination area;
according to the number of people and the number of vehicles in each latest video picture, the calculation of the comprehensive thermodynamic value of the people and the vehicles corresponding to each latest video picture specifically comprises the following steps:
record the number of people in each latest video picture as NumM i Recording the number of vehicles in each latest video picture as NumC i The method comprises the steps of carrying out a first treatment on the surface of the Acquiring the road area S covered by the video acquisition equipment corresponding to each latest video picture when shooting i Wherein i represents a natural number;
Calculating the density DM of people in each latest video picture i And density DC of the vehicle i ，
Setting an extreme congestion density reference value D of a person refM And an extreme congestion density reference value D of the vehicle refC The method comprises the steps of carrying out a first treatment on the surface of the Simultaneous introduction of the human crowding factor f M And a vehicle congestion factor f C ，
Crowding factor f M For the road area S i The thermal value of the area describing the crowding degree of the person is similar to the thermal value of the area describing the crowding degree of the person, and the crowding factor f of the vehicle is set C For the road area S i An area heating power value internally describing a degree of congestion of the vehicle;
introducing a human-vehicle importance ratio g, wherein the value range of g is (0, 1); calculating the comprehensive thermodynamic value f of the man and car corresponding to each latest video picture i ，
f i ＝gf M +(1-g)f C 。
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 6 when the program is executed by the processor.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111339710.3A CN114554664B (en) | 2021-11-12 | 2021-11-12 | Road illumination energy-saving method, device, equipment and medium based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111339710.3A CN114554664B (en) | 2021-11-12 | 2021-11-12 | Road illumination energy-saving method, device, equipment and medium based on edge calculation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114554664A CN114554664A (en) | 2022-05-27 |
| CN114554664B true CN114554664B (en) | 2023-06-16 |
Family
ID=81668714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111339710.3A Active CN114554664B (en) | 2021-11-12 | 2021-11-12 | Road illumination energy-saving method, device, equipment and medium based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114554664B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110661861A (en) * | 2019-09-19 | 2020-01-07 | 北京邮电大学 | Wisdom logistics business system |
| CN113110057A (en) * | 2021-04-20 | 2021-07-13 | 北京硕人时代科技股份有限公司 | Heating power station energy-saving control method based on artificial intelligence and intelligent decision system |
| CN113192345A (en) * | 2021-04-12 | 2021-07-30 | 武汉理工大学 | Traffic light intelligent regulation and control system for crossroad |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110312057B (en) * | 2018-03-27 | 2021-01-29 | 华为技术有限公司 | Intelligent video processing device |
-
2021
- 2021-11-12 CN CN202111339710.3A patent/CN114554664B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110661861A (en) * | 2019-09-19 | 2020-01-07 | 北京邮电大学 | Wisdom logistics business system |
| CN113192345A (en) * | 2021-04-12 | 2021-07-30 | 武汉理工大学 | Traffic light intelligent regulation and control system for crossroad |
| CN113110057A (en) * | 2021-04-20 | 2021-07-13 | 北京硕人时代科技股份有限公司 | Heating power station energy-saving control method based on artificial intelligence and intelligent decision system |
Non-Patent Citations (3)
| Title |
|---|
| 基于开放式系统架构的智慧杆塔管理平台;张雪晴;《通信企业管理》;全文 * |
| 大型公共建筑能耗预测模型与监管系统研究;秦育;《中国优秀硕士论文全文数据库 工程科技Ⅱ辑》;全文 * |
| 边缘计算应用:传感数据异常实时检测算法;张琪;胡宇鹏;嵇存;展鹏;李学庆;;计算机研究与发展(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114554664A (en) | 2022-05-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105516654B (en) | A kind of supervision of the cities video fusion method based on scene structure analysis | |
| US7424175B2 (en) | Video segmentation using statistical pixel modeling | |
| CN106845415B (en) | Pedestrian fine identification method and device based on deep learning | |
| CN102750710B (en) | Moving target statistical method and device in a kind of image | |
| WO2007126525A2 (en) | Video segmentation using statistical pixel modeling | |
| CN108416256A (en) | The family's cloud intelligent monitor system and monitoring method of feature based identification | |
| CN107945523B (en) | Road vehicle detection method, traffic parameter detection method and device | |
| CN103325259A (en) | Illegal parking detection method based on multi-core synchronization | |
| CN103268470A (en) | Method for counting video objects in real time based on any scene | |
| CN102833492A (en) | Color similarity-based video scene segmenting method | |
| CN111476710A (en) | Video face changing method and system based on mobile platform | |
| CN104463125A (en) | DSP-based automatic face detecting and tracking device and method | |
| CN109766743A (en) | A kind of intelligent bionic policing system | |
| CN115294483A (en) | Small target identification method and system for complex scene of power transmission line | |
| CN109191492A (en) | A kind of intelligent video black smoke vehicle detection method based on edge analysis | |
| CN110321378A (en) | A kind of mobile monitor image identification system and method | |
| CN114554664B (en) | Road illumination energy-saving method, device, equipment and medium based on edge calculation | |
| CN107644431A (en) | Effective method for concentration of video monitoring in the case of a kind of low-light (level) | |
| CN106682590A (en) | Processing method and server for monitoring service | |
| CN105741277A (en) | ViBe (Visual Background Extractor) algorithm and SLIC (Simple Linear Iterative Cluster) superpixel based background difference method | |
| CN108648473A (en) | Traffic signal light control device, system and method | |
| CN112258552A (en) | Pedestrian multi-target tracking method under community monitoring scene | |
| CN108510527B (en) | Moving object detection method based on frame difference method and moving point clustering | |
| CN114565597B (en) | Night road pedestrian detection method based on YOLO v3-tiny-DB and transfer learning | |
| CN114266775B (en) | Street lamp illumination control method and system for moving object detection |
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 |