CN112200877B - Car fills electric pile monitored control system based on artificial intelligence - Google Patents
Car fills electric pile monitored control system based on artificial intelligence Download PDFInfo
- Publication number
- CN112200877B CN112200877B CN202011073912.3A CN202011073912A CN112200877B CN 112200877 B CN112200877 B CN 112200877B CN 202011073912 A CN202011073912 A CN 202011073912A CN 112200877 B CN112200877 B CN 112200877B
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- image block
- representing
- value
- 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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 10
- 238000012544 monitoring process Methods 0.000 claims abstract description 49
- 238000012545 processing Methods 0.000 claims abstract description 23
- 230000005540 biological transmission Effects 0.000 claims abstract description 8
- 238000001514 detection method Methods 0.000 claims description 58
- 238000012216 screening Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000011161 development Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
- B60L53/60—Monitoring or controlling charging stations
- B60L53/68—Off-site monitoring or control, e.g. remote control
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/16—Information or communication technologies improving the operation of electric vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Power Engineering (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Image Processing (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The utility model provides a car fills electric pile monitored control system based on artificial intelligence, includes intelligent monitoring module, information transmission module and remote monitering terminal, intelligent monitoring module is used for gathering video image, the infrared image and the positional information that the car filled electric pile, passes through information transmission module with the image and the positional information of gathering and transmits to remote monitering terminal, remote monitering terminal basis infrared image judges car fills the safety of electric pile to show video image and positional information. The invention has the beneficial effects that: the image processing technology is applied to the safety monitoring of the automobile charging pile, and the remote and effective safety monitoring of the automobile charging pile is realized.
Description
Technical Field
The invention relates to the field of safety monitoring, in particular to an automobile charging pile monitoring system based on artificial intelligence.
Background
With the increasing environmental and energy pressure, the new energy automobile becomes an important direction for the development of urban low-carbon traffic, but the relatively limited endurance mileage restricts the further development of the new energy automobile to a certain extent. Therefore, the electric automobile charging pile is vigorously developed and becomes an important means for promoting the development of the electric automobile. Along with intelligent charging stake's wide deployment, electric automobile fills electric pile's safety problem serious day by day.
The temperature information that the car fills electric pile can audio-visually react the safety problem that the car filled electric pile, and when the temperature that the car filled electric pile was higher, this car filled electric pile to have great probability and is in dangerous condition, consequently, through the temperature information who fills electric pile to the car monitoring, can be timely, whether effectual judgement car fills electric pile is in dangerous condition.
Disclosure of Invention
Aiming at the problems, the invention aims to provide an automobile charging pile monitoring system based on artificial intelligence.
The purpose of the invention is realized by the following technical scheme:
an automobile charging pile monitoring system based on artificial intelligence comprises an intelligent monitoring module, an information transmission module and a remote monitoring terminal, wherein the intelligent monitoring module comprises a video monitoring unit, an infrared monitoring unit and a position information acquisition unit, the video monitoring unit is used for acquiring video images of an automobile charging pile, the infrared monitoring unit is used for acquiring infrared images of the automobile charging pile, the position information acquisition unit is used for acquiring position information of the automobile charging pile, the intelligent monitoring module transmits the acquired images and the position information to the remote monitoring terminal through the information transmission module, the remote monitoring terminal comprises an image processing unit, a danger early warning unit and an information display unit, the image processing unit is used for processing the received infrared images, and the danger early warning unit judges the safety of the automobile charging pile according to the processed infrared images, and when the automobile charging pile is judged to be dangerous, early warning is carried out, and the information display unit is used for displaying the received video image and the position information.
The beneficial effects created by the invention are as follows: the image processing technology is applied to safety monitoring of the automobile charging pile, the gray value of the infrared image can effectively reflect temperature information, the infrared image of the automobile charging pile is collected, the area image of the automobile charging pile in the infrared image is extracted, the extracted gray value of the area image of the automobile charging pile can effectively reflect the current state of the automobile charging pile, the gray value mean value of the area image of the automobile charging pile is compared with a given safety threshold value, abnormal conditions of the automobile charging pile can be effectively detected, and remote and real-time safety monitoring of the automobile charging pile is achieved.
Drawings
The invention is further described with the aid of the accompanying drawings, in which, however, the embodiments do not constitute any limitation to the invention, and for a person skilled in the art, without inventive effort, further drawings may be derived from the following figures.
FIG. 1 is a schematic diagram of the present invention.
Detailed Description
The invention is further described with reference to the following examples.
Referring to fig. 1, the artificial intelligence based automobile charging pile monitoring system of the embodiment includes an intelligent monitoring module, an information transmission module and a remote monitoring terminal, the intelligent monitoring module includes a video monitoring unit, an infrared monitoring unit and a position information collecting unit, the video monitoring unit is used for collecting video images of an automobile charging pile, the infrared monitoring unit is used for collecting infrared images of the automobile charging pile, the position information collecting unit is used for collecting position information of the automobile charging pile, the intelligent monitoring module transmits the collected images and position information to the remote monitoring terminal through the information transmission module, the remote monitoring terminal includes an image processing unit, a danger early warning unit and an information display unit, the image processing unit is used for processing the received infrared images, and the danger early warning unit judges the safety of the automobile charging pile according to the processed infrared images, and when the automobile charging pile is judged to be dangerous, early warning is carried out, and the information display unit is used for displaying the received video image and the position information.
In the preferred embodiment, the image processing technology is applied to the safety monitoring of the automobile charging pile, the gray value of the infrared image can effectively reflect temperature information, the infrared image of the automobile charging pile is collected, the area image of the automobile charging pile in the infrared image is extracted, the extracted gray value condition of the area image of the automobile charging pile can effectively reflect the current state of the automobile charging pile, the gray value mean value of the area image of the automobile charging pile is compared with the given safety threshold value, the abnormal condition of the automobile charging pile can be effectively detected, and the remote and real-time safety monitoring of the automobile charging pile is realized.
Preferably, the image processing unit performs filtering processing on the received infrared image by using a bilateral filtering algorithm, and extracts a target area image of the automobile charging pile from the filtered infrared image.
Preferably, let I denote the infrared image received by the image processing unit, I ' denote the infrared image after the infrared image I is filtered by the image processing unit, let the size of the infrared image I ' be M × N, divide the infrared image I ' into K image blocks with the size of N × N, where 0 < N < M and 0 < N, detect the divided image blocks, and let s be i Representing the ith image block, defining an image block s i Corresponding detection function ρ(s) i ) Comprises the following steps:
ρ(s i )＝A(s i )*B(s i )
in the formula, A(s) i ) Representing image blocks s i Gray scale detection factor of, B(s) i ) Representing image blocks s i M(s) of i ) Representing image blocks s i Kind of middle pixel gray value, s j Denotes the jth image block, m(s) j ) Representing image blocks s j Kind of middle pixel gray value, f y (s i ) Representing image blocks s i Of (d) the y-th gray value, N y (s i ) Representing image blocks s i The middle gray value is the number of pixels of the y-th gray value, f x (s j ) Representing image blocks s j Of (1) x-th gray value, N x (s j ) Representing image blocks s j The middle gray scale value is the number of pixels of the x-th gray scale value, N(s) i ) Representing image blocks s i Number of pixels in (1), N(s) j ) Representing image blocks s j Number of pixels in (1), d(s) i ，s j ) Representing image blocks s i And image block s j A distance therebetween, and
wherein (x) i ，y i ) Representing image blocks s i (x) of the center position of (c) j ，y j ) Representing image blocks s j (x) of the center position of (c) I′ ，y I′ ) Coordinates, U(s), representing the center position of the infrared image I i ) Representing image blocks s i A neighborhood image block set of, and
se denotes the E-th image block in the set U (si), (xe, ye) denotes the coordinates of the center position of the image block se, E(s) i ) Representation set U(s) i ) K(s) is a given gray detection threshold, and k(s) is mid j＝1，2，...，K A(s j )，A(s j ) Representing image blocks s j Gray scale detection factor of, A(s) e ) Representing image blocks s e The gray detection factor of (A (s)) e ) K (s)) represents a judgment function when A(s) e ) λ (A(s) > K(s) e ) K(s) ═ 1, when a(s) e ) When K(s) is not more than K(s), lambda (A(s) e )，K(s))＝0.01；
Given a target detection threshold H (ρ), an
When image block s i Corresponding detection function ρ(s) i ) When the value is more than or equal to H (rho), the image block s i For the target image block, image block s i The pixel in (b) is the target pixel, when the image block s is i Corresponding detection function ρ(s) i ) If < H (rho), then image block s i Is a background image block, where E (ρ) represents the mean value of the detection function values of the image block, σ (ρ) represents the standard deviation of the detection function values of the image block, ρ(s) j ) Representing image blocks s j Detecting a function value;
where n is a given value and n can be determined in the following manner:
the infrared monitoring unit collects an infrared image of an automobile charging pile as a reference image, marks an area image and a background area image of the automobile charging pile in the reference image, and sets a minimum distance value from a pixel of the marked area image of the automobile charging pile to an edge of the infrared image as d (min), wherein N is a maximum integer value meeting { M% N ═ 0, N% N ═ 0, and N ≦ d (min) }, wherein M% N ═ 0 represents that a remainder of M divided by N is 0, and N% N ═ 0 represents that a remainder of N divided by N is 0.
The preferred embodiment is used for extracting an area image of an automobile charging pile from an infrared image after filtering processing, dividing the infrared image into K image blocks, when the image block is the area image of the automobile charging pile, the image block is a target image block, when the image block is a background area image, the image block is a background image block, defining a detection function to detect the image block, wherein the detection function comprises a gray detection factor and a space detection factor, the gray detection factor determines the significance of the image block by comparing the gray value of pixels of the image block with the gray values of pixels of other image blocks, the significance of the gray value of pixels in the image block in the infrared image can be effectively measured, the space detection factor determines the possibility that the image block is the target image block according to the spatial distribution characteristics of the image block in the infrared image, and the spatial detection factor comprehensively considers the overall position distribution of the image block in the infrared image and the image block The pixel gray value of the neighborhood image block of the image block is more significant when the image block is closer to the center position of the infrared image, which indicates that the probability that the image block is the target image block is higher, so that the detection function detects the image block through the gray detection factor and the spatial detection factor, and the detection precision of the target image block is improved.
Preferably, the set Q (I ') is set to represent a target image block set obtained by detection, and Q (I') is { s } q Q ═ 1, 2., m (q) }, P (I ') denotes a set of detected background image blocks, and P (I') = { s } p 1, 2, m (p) }, wherein s is q Representing the Q-th target image block in the set Q (I '), M (Q) representing the number of target image blocks in the set Q (I'), s p Presentation setCombining the P-th background image block in P (I '), M (P) representing the number of background image blocks in the set P (I '), screening the background image blocks in the set P (I '), and defining a background image block s p The corresponding screening function is γ(s) p ) Then gamma(s) p ) The expression of (c) is:
in the formula, sigma' p Representing a background image block s p Standard deviation of middle pixel gray value, σ' j Representing image blocks s j Standard deviation of gray value of middle pixel, U(s) p ) Representing a background image block s p A neighborhood image block set of, and
s v representation set U(s) p ) (x) of the image block of (a) v ，y v ) Representing image blocks s v The coordinates of the center position of (a), E(s) p ) Representation set U(s) p ) Number of image blocks in, θ(s) p ) As a value function, when the neighborhood image block set U(s) p ) When there is a background image block, then θ(s) p ) When the neighborhood image block set U(s) is 1 p ) When there is no background image block, then θ(s) p )＝0，
As a value function, when the neighborhood image block set U(s) p ) When the target image block exists in the image, then
When neighborhood image block set U(s) p ) When there is no target image block, then
When the background image block s p Corresponding screening function
Then, the background image block s is determined p Where the target pixel is present, wherein,
representing the mean of the standard deviations of the gray values of the pixels of the target image block in the set Q (I'),
represents the mean of the standard deviations of the pixel gray values of the background image blocks in the set P (I').
The preferred embodiment defines a screening function to screen a background image block, so as to detect whether a target pixel exists in the background image block, and avoid incompleteness of target region extraction caused by the fact that the image block is determined as the background image block because the image block contains a small number of target pixels.
Preferably, for the background image block s p The detecting of the pixels in (1) specifically comprises:
(1) let C(s) p ) Representing a background image block s p Of (1) is the target pixel set of' p (i, j) represents a background image block s p Pixel at medium coordinate (I, j), defining pixel I' p (i, j) is ω 'to the initial pixel detection function' p (i, j), and ω' p The expression of (i, j) is:
in the formula, phi(s) v ) For judging the function, when the image block s v When it is the target image block, then phi(s) v ) When image block s is 1 v When it is a background image block, then phi (sv) ═ 0, D' p (I, j) is pixel I' p (i, j) neighborhood detection factor, and D' p The expression of (i, j) is:
of formula (II) to' p (I, j) represents a pixel I' p Grey scale value of (I, j), I' v (x, y) denotes an image block s v Pixel at medium coordinate (x, y), f' v (x, y) represents a pixel I' v Gradation value of (x, y), f'(s) v ) Representing image blocks s v Middle pixel to pixel I' p (ii) a reference gray value of (i, j);
calculating a background image block s p The initial pixel detection function value of each pixel is arranged according to the initial pixel detection function value from small to large, the first 2 pixels are judged as target pixels, and the two pixels are added into a set C(s) p ) Performing the following steps;
(2) for image block s in background area p Is detected from the other pixels, is provided with I' p (k, l) represents a background image block s p Pixel at medium coordinate (k, l), defining pixel I' p (k, l) is β 'as the corresponding pixel detection function' p (k, l), and β' p The expression of (k, l) is:
β′ p (k，l)＝σ(D′ p (k，l)，H(D))*ε(S′ p (k，l)，H(S))
in formula (II) to' p (k, l) is pixel I' p (kL) and H (D) is a neighborhood judgment threshold value
Representing image blocks s v The pixel with the maximum middle gray scale value, and (c, d) are pixels
In image block s v Coordinates of (1) in
Representing a pixel
Is determined by the gray-scale value of (a),
representing image blocks s v Median value of the medium pixel gray values, σ (D' p (k, l), H (D) is a neighborhood judgment factor, when D' p When (k, l) is less than or equal to H (D), then σ (D' p (k, l), H (D) ═ 1, when D' p When (k, l) > H (D), then σ (D' p (k，l)，H(D))＝0，S′ p (k, l) is pixel I' p (k, l) corresponding local detection factor, and S' p The expression of (k, l) is:
in the formula (II), f' p (k, l) represents a pixel I' p Grey value of (k, l), I' p (a, b) represents a background image block s p Pixel at medium coordinate (a, b), and l' p (a, b) is the set C(s) p ) H (S) is a local judgment threshold, and
f′ max (C) representing the set C(s) p ) Maximum value of middle pixel gray-scale value, f' min (C) Representing the set C(s) p ) Minimum value of middle pixel gray value, ε (S' p (k, l), H (S) is a local judgment factor, when S' p If (k, l) < H (S) < then ε (S' p (k, l), H (S) ═ 1, when S' p If (k, l) ≧ H (S), ε (S' p (k，l)，H(S))＝0，
When pixel I' p (k, l) corresponding pixel detection function β' p When (k, l) 'is 1, then pixel I' p (k, l) is a target pixel, and pixel I' p (k, l) is added to the set C(s) p ) In (1).
Preferably, the area image of the vehicle charging pile in the infrared image I' is determined according to the target image block obtained by the acquisition and the target pixel obtained by the detection in the background image block, and specifically includes:
let B 'represent a set of target pixels in the infrared image I', where the set B 'includes the target pixels detected in the background image block and the pixels in the target image block in the set Q (I'), and an area image composed of the target pixels included in the set B 'is an area image of the vehicle charging pile extracted in the infrared image I'.
In the preferred embodiment, the pixels in the background image block including the target pixel are detected through a pixel detection function, where the pixel detection function includes a neighborhood detection factor and a local detection factor, where the neighborhood detection factor compares the gray level value of the pixel in the background image block with the gray level value of the pixel in the target image block in the neighborhood image block set, and when the gray level value of the pixel is closer to the gray level value of the pixel in the target image block, it indicates that the pixel has a higher probability of being the target pixel, and further, compares the gray level value of the pixel with the gray level value of the pixel in the target pixel set in the background image block, and the target pixel set in the background image block includes the target pixel that has been detected in the background image block, so that when the gray level value of the pixel is closer to the gray level value of the pixel in the target pixel set, the pixel has a high probability of being a target pixel, a neighborhood judgment threshold and a local judgment threshold are set according to the characteristics of a target image block in a neighbor image block set of the background image block and the characteristics of pixels in a target pixel set of the background image block, a neighborhood detection factor of the pixel is compared with the set neighborhood judgment threshold, and the local detection factor of the pixel is compared with the set local judgment threshold, so that the target pixel in the background image block can be effectively detected; considering that the target pixel set does not include the target pixel when the pixels in the background image block are just detected, the preferred embodiment defines an initial pixel detection function, which comprehensively considers the similarity between the gray-scale values of the pixels in the background image block and the gray-scale values of the pixels in the neighboring target image blocks, and the distance between the coordinates of the pixels in the background image block and the center positions of the neighboring target image blocks, and takes the first two pixels in the background image block, which have the gray-scale values closest to the gray-scale values of the pixels in the neighboring target image blocks and the center positions closest to the gray-scale values of the pixels in the neighboring target image blocks as the target pixels, thereby improving the accuracy of target pixel detection.
Preferably, the area image of the automobile charging pile extracted by the image processing unit in the infrared image I ' is set as M ', the danger early warning unit calculates a mean value of gray values of the area image M ' of the automobile charging pile, compares the calculated mean value of gray values with a given safety threshold, judges that the automobile charging pile is dangerous when the mean value of gray values is higher than the given safety threshold, and performs early warning when the danger early warning unit judges that the automobile charging pile is dangerous.
Preferably, the safety threshold may be determined in the following manner:
the method comprises the steps of enabling an infrared monitoring unit to collect infrared images of the automobile charging pile in a safe state, enabling an image processing unit to carry out filtering processing on the collected infrared images, extracting regional images of the automobile charging pile from the filtered infrared images, calculating a mean value of gray values of the regional images of the automobile charging pile, and setting the mean value of the gray values as a safety threshold.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (3)
1. An automobile charging pile monitoring system based on artificial intelligence is characterized by comprising an intelligent monitoring module, an information transmission module and a remote monitoring terminal, wherein the intelligent monitoring module comprises a video monitoring unit, an infrared monitoring unit and a position information acquisition unit, the video monitoring unit is used for acquiring video images of an automobile charging pile, the infrared monitoring unit is used for acquiring infrared images of the automobile charging pile, the position information acquisition unit is used for acquiring position information of the automobile charging pile, the intelligent monitoring module transmits the acquired images and the position information to the remote monitoring terminal through the information transmission module, the remote monitoring terminal comprises an image processing unit, a danger early warning unit and an information display unit, the image processing unit is used for processing the received infrared images, and the danger early warning unit judges the safety of the automobile charging pile according to the processed infrared images, when the automobile charging pile is judged to be dangerous, early warning is carried out, and the information display unit is used for displaying the received video image and the position information;
the image processing unit is used for filtering the received infrared image and extracting an area image of the automobile charging pile from the filtered infrared image;
setting I to represent the infrared image received by the image processing unit, setting I ' to represent the infrared image obtained by filtering the infrared image I by the image processing unit, setting the size of the infrared image I ' to be M multiplied by N, dividing the infrared image I ' into K image blocks with the size of N multiplied by N, wherein N is more than 0 and less than M and N is more than 0 and less than N, and dividing the divided imageThe block is detected, set s i Representing the ith image block, defining an image block s i Corresponding detection function ρ(s) i ) Comprises the following steps:
ρ(s i )＝A(s i )*B(s i )
in the formula, A(s) i ) Representing image blocks s i Gray scale detection factor of, B(s) i ) Representing image blocks s i M(s) of i ) Representing image blocks s i Kind of middle pixel gray value, s j Denotes the jth image block, m(s) j ) Representing image blocks s j Kind of middle pixel gray value, f y (s i ) Representing image blocks s i Of (d) the y-th gray value, N y (s i ) Representing image blocks s i The middle gray value is the number of pixels of the y-th gray value, f x (s j ) Representing image blocks s j Of (1) x-th gray value, N x (s j ) Representing image blocks s j The middle gray scale value is the number of pixels of the x-th gray scale value, N(s) i ) Representing image blocks s i Number of pixels in (1), N(s) j ) Representing image blocks s j D(s) is the number of pixels in i ，s j ) Representing image blocks s i And image block s j A distance therebetween, and
wherein (x) i ，y i ) Representing image blocks s i (x) of the center position of (c) j ，y j ) Representing image blocks s j (x) of the center position of (c) I′ ，y I′ ) Coordinates, U(s), representing the center position of the infrared image I i ) Representing image blocks s i A neighborhood image block set of, and
s e representation set U(s) i ) The e-th image block in (x) e ，y e ) Representing image blocks s e The coordinates of the center position of (a), E(s) i ) Representation set U(s) i ) K(s) is a given gray detection threshold, and
A(s j ) Representing image blocks s j Gray scale detection factor of, A(s) e ) Representing image blocks s e The gray detection factor of (A (s)) e ) K (s)) represents a judgment function when A(s) e ) λ (A(s) > K(s) e ) K(s) ═ 1, when a(s) e ) When K(s) is not more than K(s), lambda (A(s) e )，K(s))＝0.01；
Given a target detection threshold H (ρ), an
When image block s i Corresponding detection function ρ(s) i ) When more than or equal to H (rho), then image block s i For a target image block, image block s i The pixel in (b) is the target pixel, when the image block s is i Corresponding detection function ρ(s) i ) If < H (rho), then image block s i Is a background image block, where E (ρ) represents the mean value of the detection function values of the image block, σ (ρ) represents the standard deviation of the detection function values of the image block, ρ(s) j ) Representing image blocks s j Detecting a function value;
let Q (I ') denote the set of target image blocks obtained by detection, and Q (I') { s } q Q 1, 2., m (q) }, P (I') denotesThe resulting set of background image blocks is detected, and P (I') { s }, is p 1, 2, m (p) }, wherein s q Representing the Q-th target image block in the set Q (I '), M (Q) representing the number of target image blocks in the set Q (I'), s p Representing the P-th background image block in the set P (I '), M (P) representing the number of background image blocks in the set P (I '), screening the background image blocks in the set P (I '), defining a background image block s p The corresponding screening function is γ(s) p ) Then gamma(s) p ) The expression of (a) is:
in formula (II), sigma' p Representing a background image block s p Standard deviation of grey value of middle pixel, sigma' j Representing image blocks s j Standard deviation of gray value of middle pixel, U(s) p ) Representing a background image block s p A neighborhood image block set of
s v Representation set U(s) p ) (x) of the image block of (a) v ，y v ) Representing image blocks s v The coordinates of the center position of (a), E(s) p ) Representation set U(s) p ) Number of image blocks in, θ(s) p ) As a value function, when the neighborhood image block set U(s) p ) When there is a background image block, then θ(s) p ) 1, when the set of neighborhood image blocks U(s) p ) When there is no background image block in the image, then theta(s) p )＝0，
As a function of value, when the neighborhood image block set U(s) p ) When the target image block exists in the image, then
When the neighborhood image block set U(s) p ) When there is no target image block, then
2. The artificial intelligence based automobile charging pile monitoring system according to claim 1, wherein:
when the background image block s p Corresponding screening function
Then, the background image block s is determined p Where the target pixel is present, wherein,
representing the mean of the standard deviations of the gray values of the pixels of the target image block in the set Q (I'),
representing the mean of the standard deviations of the gray-scale values of the pixels of the background image blocks in the set P (I'), for the background image block s p The detecting of the pixels in (1) specifically includes:
(1) let C(s) p ) Representing a background image block s p Of (1) is the target pixel set of' p (i, j) represents a background image block s p Pixel at medium coordinate (I, j), defining pixel I' p (i, j) is ω 'to the initial pixel detection function' p (i, j), and ω' p The expression of (i, j) is:
in the formula, phi(s) v ) For judging the function, when the image block s v When it is the target image block, then phi(s) v ) When image block s is equal to 1 v When being a background image blockThen phi(s) v )＝0，D′ p (I, j) is pixel I' p Neighborhood detection factors of (i, j), and D' p The expression of (i, j) is:
in the formula (II), f' p (I, j) represents a pixel I' p Grey scale value of (I, j), I' v (x, y) denotes an image block s v Pixel at medium coordinate (x, y), f' v (x, y) denotes a pixel I' v Gradation value of (x, y), f'(s) v ) Representing image blocks s v Middle pixel to pixel I' p (ii) a reference gray value of (i, j);
calculating a background image block s p The initial pixel detection function value of each pixel is arranged according to the initial pixel detection function value from small to large, the first 2 pixels are judged as target pixels, and the two pixels are added into a set C(s) p ) Performing the following steps;
(2) for image block s p Is detected from the other pixels of (1), is provided with I' p (k, l) represents a background image block s p Pixel at medium coordinate (k, l), defining pixel I' p (k, l) is β 'as the corresponding pixel detection function' p (k, l), and β' p The expression of (k, l) is:
β′ p (k，l)＝σ(D′ p (k，l)，H(D))*ε(S′ p (k，l)，H(S))
in formula (II) to' p (k, l) is pixel I' p (k, l) neighborhood detection factor, H (D) neighborhood decision threshold, set
Representing image blocks s v The pixel with the highest gray value in (c,d) is a pixel
In the image block s v Coordinates of (1) in
Representing a pixel
Is measured in a predetermined time period, and the gray value of (b),
representing image blocks s v Median value of the medium pixel gray values, σ (D' p (k, l), H (D) is a neighborhood judgment factor, when D' p When (k, l) is less than or equal to H (D), then σ (D' p (k, l), H (D) ═ 1, when D' p When (k, l) > H (D), then σ (D' p (k，l)，H(D))＝0，S′ p (k, l) is pixel I' p Local detection factor of (k, l), and S' p The expression of (k, l) is:
in the formula (II), f' p (k, l) represents a pixel I' p Grey value of (k, l), I' p (a, b) represents a background pixel image block s p Pixel at medium coordinate (a, b), and l' p (a, b) is the set C(s) p ) H (S) is a local judgment threshold, and
f′ max (C) representation collectionC(s p ) Maximum value of gray value of middle pixel, f' min (C) Representing the set C(s) p ) Minimum value of middle pixel gray value, ε (S' p (k, l), H (S) is a local judgment factor, and when S' p If (k, l) < H (S) < then ε (S' p (k, l), H (S) ═ 1, when S' p If (k, l) ≧ H (S), ε (S' p (k，l)，H(S))＝0，
When pixel I' p (k, l) corresponding pixel detection function β' p When (k, l) 'is 1, then pixel I' p (k, l) is a target pixel, and pixel I' p (k, l) is added to the set C(s) p ) In (1).
3. The artificial intelligence based automobile charging pile monitoring system as claimed in claim 2, wherein the regional image of the automobile charging pile in the infrared image I' is determined according to the target image block obtained and the target pixel detected from the background image block.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011073912.3A CN112200877B (en) | 2020-04-02 | 2020-04-02 | Car fills electric pile monitored control system based on artificial intelligence |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011073912.3A CN112200877B (en) | 2020-04-02 | 2020-04-02 | Car fills electric pile monitored control system based on artificial intelligence |
| CN202010253409.XA CN111462259B (en) | 2020-04-02 | 2020-04-02 | Car fills electric pile monitored control system based on artificial intelligence |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010253409.XA Division CN111462259B (en) | 2020-04-02 | 2020-04-02 | Car fills electric pile monitored control system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112200877A CN112200877A (en) | 2021-01-08 |
| CN112200877B true CN112200877B (en) | 2022-08-23 |
Family
ID=71681404
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010253409.XA Active CN111462259B (en) | 2020-04-02 | 2020-04-02 | Car fills electric pile monitored control system based on artificial intelligence |
| CN202011073912.3A Active CN112200877B (en) | 2020-04-02 | 2020-04-02 | Car fills electric pile monitored control system based on artificial intelligence |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010253409.XA Active CN111462259B (en) | 2020-04-02 | 2020-04-02 | Car fills electric pile monitored control system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN111462259B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950450A (en) * | 2020-08-11 | 2020-11-17 | 李国安 | Intelligent medical care management system based on block chain and image processing |
| CN111942375B (en) * | 2020-08-24 | 2021-02-19 | 米传科技（上海）有限公司 | Automatic parking system based on millimeter wave radar and 5G |
| CN116840693B (en) * | 2023-06-30 | 2024-03-19 | 深圳市盛弘新能源设备有限公司 | Charge and discharge test control method and system based on artificial intelligence |
| CN117227551B (en) * | 2023-08-28 | 2024-03-05 | 大唐昌裕(北京)新能源有限公司 | New energy equipment safety monitoring method, device, equipment and readable storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106826821A (en) * | 2017-01-16 | 2017-06-13 | 深圳前海勇艺达机器人有限公司 | The method and system that robot auto-returned based on image vision guiding charges |
| CN108492517A (en) * | 2018-03-06 | 2018-09-04 | 深圳智达机械技术有限公司 | A kind of fire monitoring system for building |
Family Cites Families (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19517517B4 (en) * | 1994-05-28 | 2004-07-01 | Cerberus AG, Männedorf | Passive infrared intrusion detector |
| KR20080101979A (en) * | 2007-05-17 | 2008-11-24 | 주식회사 엔엔티 | A thermal detection monitoring apparatus and that of operation method |
| US8363098B2 (en) * | 2008-09-16 | 2013-01-29 | Plantronics, Inc. | Infrared derived user presence and associated remote control |
| CN202150904U (en) * | 2010-12-29 | 2012-02-22 | 上海市电力公司 | Mobile real-time video monitoring device of transformer substation and power distribution station |
| DE202012005170U1 (en) * | 2012-05-25 | 2012-07-11 | Abb Ag | Mobile motion and camera terrain |
| US20170147885A1 (en) * | 2013-11-11 | 2017-05-25 | Osram Sylvania Inc. | Heat-Based Human Presence Detection and Tracking |
| CN104966375B (en) * | 2015-07-01 | 2017-10-10 | 安徽创世科技股份有限公司 | A kind of safety defense monitoring system |
| CN105243627A (en) * | 2015-09-06 | 2016-01-13 | 天维尔信息科技股份有限公司 | Fire-fighting monitoring system based on unmanned aerial vehicle |
| CN206402354U (en) * | 2017-01-02 | 2017-08-11 | 南京国电南自新能源工程技术有限公司 | A kind of charging pile monitoring system |
| CN108200205A (en) * | 2018-02-08 | 2018-06-22 | 四川道勤信业科技有限公司 | A kind of charging station monitoring remote video control system |
| CN108357382B (en) * | 2018-03-09 | 2020-08-21 | 宁德时代新能源科技股份有限公司 | Battery charging method and system, remote monitoring platform and storage medium |
| BR102018009044A2 (en) * | 2018-05-04 | 2019-11-19 | Universidade Tecnologica Federal Do Parana | method and arrangement for the monitoring and control of temperature in high temperature furnaces based on infrared radiation |
| CN109703410B (en) * | 2019-01-23 | 2021-08-27 | 北京交通大学 | Charging station safety protection system and early warning method |
| CN209514378U (en) * | 2019-05-13 | 2019-10-18 | 深圳市恩逸新能源有限公司 | A kind of new-energy automobile charging pile long-distance monitorng device |
| CN110297498B (en) * | 2019-06-13 | 2022-04-26 | 暨南大学 | Track inspection method and system based on wireless charging unmanned aerial vehicle |
| CN110320843A (en) * | 2019-07-19 | 2019-10-11 | 云南北方驰宏光电有限公司 | Intelligent building security protection monitoring system and method based on double spectrum |
| CN110599479A (en) * | 2019-09-16 | 2019-12-20 | 北京航天宏图信息技术股份有限公司 | Monitoring area change detection method and device and storage medium |
| CN110458839B (en) * | 2019-10-09 | 2020-01-14 | 江西太平洋电缆集团有限公司 | Effective wire and cable monitoring system |
| CN110458157B (en) * | 2019-10-14 | 2020-01-07 | 江西太平洋电缆集团有限公司 | Intelligent monitoring system for power cable production process |
| CN110774919A (en) * | 2019-12-02 | 2020-02-11 | 广州供电局有限公司 | Charging pile monitoring system |
-
2020
- 2020-04-02 CN CN202010253409.XA patent/CN111462259B/en active Active
- 2020-04-02 CN CN202011073912.3A patent/CN112200877B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106826821A (en) * | 2017-01-16 | 2017-06-13 | 深圳前海勇艺达机器人有限公司 | The method and system that robot auto-returned based on image vision guiding charges |
| CN108492517A (en) * | 2018-03-06 | 2018-09-04 | 深圳智达机械技术有限公司 | A kind of fire monitoring system for building |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111462259B (en) | 2020-11-17 |
| CN111462259A (en) | 2020-07-28 |
| CN112200877A (en) | 2021-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112200877B (en) | Car fills electric pile monitored control system based on artificial intelligence | |
| CN108960065B (en) | Driving behavior detection method based on vision | |
| CN108469806B (en) | Driving right transfer method in alternating type man-machine common driving | |
| US8634593B2 (en) | Pixel-based texture-less clear path detection | |
| CN107578012B (en) | Driving assistance system for selecting sensitive area based on clustering algorithm | |
| CN102509291B (en) | Pavement disease detecting and recognizing method based on wireless online video sensor | |
| CN105744232A (en) | Method for preventing power transmission line from being externally broken through video based on behaviour analysis technology | |
| CN110728241A (en) | Driver fatigue detection method based on deep learning multi-feature fusion | |
| CN110021133B (en) | All-weather fire-fighting fire patrol early-warning monitoring system and fire image detection method | |
| CN110781873A (en) | Driver fatigue grade identification method based on bimodal feature fusion | |
| CN104902265A (en) | Background edge model-based video camera anomaly detection method and system | |
| CN103945197B (en) | Electric power facility external force damage prevention early warning scheme based on Video Motion Detection technology | |
| CN112149618B (en) | Pedestrian abnormal behavior detection method and device suitable for inspection vehicle | |
| CN111563468B (en) | Driver abnormal behavior detection method based on attention of neural network | |
| CN110781872A (en) | Driver fatigue grade recognition system with bimodal feature fusion | |
| CN109034038B (en) | Fire identification device based on multi-feature fusion | |
| CN111523416A (en) | Vehicle early warning method and device based on highway ETC portal | |
| CN112287861A (en) | Road information enhancement and driving early warning method based on night environment perception | |
| CN110728212B (en) | Road well lid monitoring device and monitoring method based on computer vision | |
| CN114329074B (en) | Traffic energy efficiency detection method and system for ramp road section | |
| CN109325426B (en) | Black smoke vehicle detection method based on three orthogonal planes time-space characteristics | |
| CN112232235B (en) | Intelligent factory remote monitoring method and system based on 5G sum algorithm | |
| CN109543610B (en) | Vehicle detection tracking method, device, equipment and storage medium | |
| WO2023124221A1 (en) | Area edge detection method and apparatus for vehicle drivable area, and storage medium | |
| CN115410114A (en) | Urban rail flood prevention early warning method and system based on multiple characteristics |
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 |