AU2021102903A4 - An Automatic Black Smoke Capture System for Ship Locks - Google Patents
An Automatic Black Smoke Capture System for Ship Locks Download PDFInfo
- Publication number
- AU2021102903A4 AU2021102903A4 AU2021102903A AU2021102903A AU2021102903A4 AU 2021102903 A4 AU2021102903 A4 AU 2021102903A4 AU 2021102903 A AU2021102903 A AU 2021102903A AU 2021102903 A AU2021102903 A AU 2021102903A AU 2021102903 A4 AU2021102903 A4 AU 2021102903A4
- Authority
- AU
- Australia
- Prior art keywords
- white grid
- blackness
- black
- white
- grid
- 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.)
- Ceased
Links
- 239000000779 smoke Substances 0.000 claims abstract description 22
- 230000008859 change Effects 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 238000000034 method Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004297 night vision Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
- G01N15/075—Investigating concentration of particle suspensions by optical means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N2015/0042—Investigating dispersion of solids
- G01N2015/0046—Investigating dispersion of solids in gas, e.g. smoke
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention discloses an automatic black smoke capture system for ship locks,
mainly comprising camera system, black-and-white grid map across the lock, hull obscuration
recognition subsystem, recognition subsystem for blackness of the exhaust. The invention uses
the camera system installed on one side of the lock to continuously record the black and white
grid map installed on the other side of the lock side wall, once a ship appears in the camera
screen, there will be two situations at the same time, in which the ship body obscures the black
and white grid map and the exhaust changes the brightness of the black and white grid map.
The present invention uses the ship hull obscuration recognition algorithm to automatically
identify the obscured part of the black and white grid map and, for the black and white grid
map of the unobscured part, to identify the part of the white grid with reduced brightness caused
by black smoke and to assess the level of exhausted black smoke according to the degree of
reduced brightness. The invention achieves the purpose of automatic and accurate
identification of smoky ships in ship locks.
1/7
bleek-mcd-white grid
=np
4 orner black 4 corner white Edgpel n
grid grid
Edge pixel L n] EdgepixelLn
Edgeirensity L. Edge pixe Ii
Threshold
value=Is/.2
Wh11e grid Y e Gralle -. af
(unnbscmd) NI
I No
I mal pixelBn Em I rnal Pixd An DN
brightess Whitegrid
Dfelass0 (unobscured)
blackness.
DN value of the Bi ss
class 5 DN
blacknessI
Ab andon
Le...iof blaclmssof the
exst in the white grid
Blackdeso efexhat frozmthe stack= highest blacness levelofall white grids
Figure 1
Description
1/7
bleek-mcd-white grid =np
4 orner black 4 corner white Edgpel n grid grid
Edge pixel L n] EdgepixelLn
Edgeirensity L. Edge pixe Ii
Threshold value=Is/.2
grid Wh11e Ye Gralle -. af
(unnbscmd) NI
I No I mal pixelBn Em I rnal Pixd An DN brightess Whitegrid Dfelass0 (unobscured) blackness. DN value of the Bi ss class 5 DN blacknessI Ab andon
Le...iof blaclmssof the exst in the white grid
Blackdesoefexhat frozmthe stack= highest blacness levelofall white grids
Figure 1
An Automatic Black Smoke Capture System for Ship Locks
The present invention relates to the field of exhaust detection, and in particular to an automatic black smoke capture system for ship locks.
In the context of the country's war for blue sky , the major enemy of water and blue sky is ship exhaust. Among them, the most intuitive and objectionable problem for residents of coastal river cities to ship exhaust is the phenomenon of black smoke from ships. In 2018, Shanghai was the first city in China to require that "motor vehicles and boats must not emit visible black smoke." , followed by Hangzhou, Qinhuangdao and other cities one after another. Considering that the ship is sailing in the open water and is a moving target, at present, maritime law enforcement officers mainly use cell phone recording video, and carry a Ringelman blackness colorimetric card to evaluate the blackness of the exhaust, which leads to a problem of subjective determination. For ships, the problem is not serious because the background when recording video is often a relatively pure sky; for inland river ships, the problem is much more serious because the background may be various riverside buildings. The maritime authorities urgently need a controlled environment to carry out black smoke capture operations to eliminate the phenomenon of black smoke from ships by strengthening deterrence. SUMMARY
The invention simplifies the environment of ship's black smoke capture by artificially setting the background of the ship - black and white grid map, and then uses the camera system to automatically capture the phenomenon of ship's black smoke through the ship's hull obscuration recognition algorithm and exhaust blackness grading algorithm, realizing the purpose of automatic and accurate identification of smoky ships by ship locks. To achieve the above purpose, the present invention provides the following solution: The automatic black smoke capture system for ship locks comprises: Camera system: used to collect images and provide data for the hull obscuration and blackness recognition subsystems.
Black and white grid map across the locks: used to provide a background reference to quantify the exhausted blackness. Hull obscuration recognition subsystem: used to identify the change of white grid brightness caused by hull obscuration. Recognition subsystem for blackness of the exhaust: used to automatically quantify the blackness of the exhaust according to the degree of white grid brightness reduction. Preferably, the height of the camera system should be the same as the average height of the passing ships' chimney. The camera system's angle is horizontal, perpendicular to the direction of the lock to capture the black and white grid map of the opposite side of the lock. Preferably, the white grids in the black and white grid map across the locks are numbered, each white grid has a unique mark n, and each white grid has four adjacent black grids and four edges. Preferably, pixels falling within the black and white grid map are categorized, pixels falling entirely within a white grid n are categorized as An pixels, pixels falling on four edges of the white grid are categorized as Ln pixels, and pixels falling within a black grid n are categorized as Bn pixels. Preferably, the operating steps of the hull obscuration identification subsystem include: S1.1: calculating the edge intensity of the black and white grid graph; by using the edge operator, each pixel within the graph obtain the edge intensity value I. S1.2: setting a threshold value for the edge intensity, calculating the average value of the edge intensity ILnfor each of the four edges falling on the white grid, with one-half of its average value set as the threshold value for the edge intensity. S1.3. determining whether any one white grid is obscured by the hull. If there are more than one Ln pixels of the four edges of any one white grid, as long as the ILn value of one of the Ln pixels < threshold, the whole white grid is determined to be completely obscured or partially obscured, and vice versa, the white grid is determined to be non-obscured. Preferably, the operation steps of the blackness grading subsystem include: S2.1: for the unobscured white grid, calculating the brightness DN values of all its An pixels, and take the DN values of the pixels as the DN value of the white grid.
S2.2: making a virtual Ringelman colorimetric card with the maximum brightness DN value in the four corner of the white grids representing the brightness of Ringelmann blackness level 0 and the minimum brightness DN value in the four corner black of the grids representing the brightness of Ringelman black level 5. S2.3: for each brightness DN value of the white grid, calculating the percentage of Ringelman blackness. The formula is: White grid DN value = Level 0 blackness DN value x (1 - x) + Level 5 blackness DN value x x When x =20%, the blackness of this white grid is level 1, when x = 40%, the blackness of this white grid is level 2, when x = 60%, the blackness of this white grid is level 3, when x = 80%, the blackness of this white grid is level 4. Since the exhaust continue to dilute and fade as soon as they leave the stack, the blackness level of the white grid with the largest x-value represents the blackness of the exhaust exiting the ship's stack. Preferably, DN brightness values include blue, green, and red colors, which are represented byDNblue, DNgreen, and DNred, respectively. Compared with the prior art, the present invention has the following advantages: At the checkpoint where ships must pass through such as ship locks, through a simple modification of the side walls of the locks, simplifying the background of the camera system's side-view capture of ship exhaust, designing and using the ship hull obscuration recognition algorithm and exhaust blackness grading algorithm on this basis, it created an automatic black smoke capture system for ship locks, establishing the ability to automatically identify black smoke for the maritime department, and realizing an efficient and accurate supervision capability.
In order to more clearly illustrate the technical solutions in the embodiments or prior art of the present invention, the following is a brief description of the drawings to be used in the embodiments, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained according to these drawings without creative labor for those of ordinary skill in the art.
Figure 1 is a flow chart of the system of the present invention Figure 2 is a schematic diagram of the composition and description of the system of the present invention. Figure 3 is a diagram of an example black and white grid of the present invention Figure 4 is a partial schematic diagram of the black and white grid diagram of the present invention at an imaging resolution of 1/4 grid width Figure 5 is an example diagram of the hull obscuration recognition of the present invention. Figure 6 is a partially enlarged schematic diagram of an example hull obscuration of the present invention Figure 7 is a schematic diagram of ship occlusion in an embodiment of the present invention Where 1 is the white grid internal An pixel, 2 is the white grid edge Ln pixel, 3 is the black grid internal Bn pixel, 4 is the unobscured grid, and 5 is the obscured grid. DESCRIPTION OF THE INVENTION
The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention, and it is clear that the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments in the present invention, all other embodiments obtained by a person of ordinary skill in the art without making creative labor fall within the scope of protection of the present invention. In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, the following is a further detailed description of the present invention in conjunction with the accompanying drawings and specific embodiments. A flow chart of the present invention as shown in Figure 1: The automatic black smoke capture system for ship locks (shown in Figure 2) includes: Camera system: used to collect images and provide data for the hull obscuration and blackness recognition subsystems.
Black and white grid map across the locks: used to provide a background reference to quantify the exhausted blackness. Hull obscuration identification subsystem: used to identify the change of white grid brightness caused by hull obscuration. Recognition subsystem for blackness of the exhaust: used to automatically quantify the blackness of the exhaust according to the degree of white grid brightness reduction. SI: the camera system on one side of the lock continuously records the black and white grid map on the other side of the lock. (1) Installation requirements: the camera system is installed on one side of the lock, either on the side wall of the lock or on the shore of the lock, depending on the height of the stack of the passing ship in the lock; the height of the camera system should be the same or close to the average height of the chimney of the passing ship. The center height of the black and white grid map is the same as or close to the height of the camera system. The camera system's angle is horizontal, perpendicular to the direction of the lock, recording the black and white grid map directly opposite. In general, the ship locks among the mountain are deeper, the water level drop is large, suitable for installation in the side wall of the locks; ship locks among the ship lock are shallow, the water level drop is small, suitable for installation in the lock bank, or even on the fixed platform on the high ground. (2) Performance requirements: the invention embodiment of the selected camera system has infrared night vision, suitable for night shooting; the infrared integrated camera uses a special wavelength of 850nm-940nm infrared to shot into the "double pass filter", so that visible light and part of the wavelength of infrared light at the same time transmit into the light-sensitive components. A black and white grid diagram (shown in Figure 3) contains at least 3 x 3 pixels in a grid, ensuring that at least 1 pixel can be completely within the grid. (3) White grid numbering. The white grids in the black and white grid diagram are numbered, each white grid has a unique mark n, and each white grid has 4 adjacent black grids and 4 edges. The reason for the numbering is that the hull obscuration recognition algorithm is used to determine whether white grid n is obscured based on whether its 4 edges are fully visible, while the reason why the exhaust blackness grading algorithm quantifies the blackness of exhaust at white grid n is based on the decrease in the brightness value of white grid n (if the change in brightness value is not caused by obscuration, then the decrease in brightness value can only be caused by exhaust). (4) Categorization of pixels within a white grid (as shown in Figure 4). All pixels in the screen are categorized; pixels that fall entirely within a particular white grid n are categorized as An pixels; pixels that fall on 4 edges of that grid are categorized as Ln pixels; pixels that fall entirely within black grid n are categorized as Bn pixels, pixels that fall on 4 edges of the black grid are not categorized because these pixels are not involved in the subsequent operations of the present invention. S2: Hull obscuration identification (example shown in Figure 5). (1) Calculating the edge intensity of the grid map: Using edge operators, such as Sobel operator and Roberts operator, the edge intensity value I is obtained for each pixel. In general, the edge intensity value IAn for An pixel is extremely low, while the edge intensity value ILn for Ln pixel is extremely high. The Sobel operator, a discrete derivative filter for edge detection that combines Gaussian smoothing and Calculus derivatives, is used in this embodiment of the invention to calculate the edge intensity of a grid map. The operator is used to calculate an approximation of the brightness of the image, and a specific point in the region that exceeds a certain number is recorded as an edge according to the brightness next to the edge of the image. The Sobel operator adds the concept of weight to the Prewitt operator, considering that the distance of neighboring points has different effects on the current pixel point, and the closer the pixel point corresponds to the current pixel, the greater the effect, so as to sharpen the image and highlight the edge contour. The Sobel operator detects the pixel point according to the phenomenon that the grayscale weighted difference between the upper, lower, left and right neighboring points reaches the extreme value at the edge. It has a smoothing effect on the noise and provides more accurate information on the direction of the edges. Because the Sobel operator combines Gaussian smoothing and Calculus derivation (discretization), the results will have more immunity to noise. (2) Setting the threshold value of edge strength: By default, hull obscuration or exhaust interference cannot affect the white grids in the four corners of the grid map, namely upper left, upper right, lower left and lower right, at the same time. Therefore, for each corner of the white grid, the average value of ILn is calculated, and the largest average value of ILn among the 4 corner white grids is considered as the white grid that is not obscured by the hull or exhaust, and 1/2 of the average value of ILn is set as the threshold to determine whether the Ln pixels of any white grid are obscured or not. 3) Determining whether any white grid is obscured by the hull If there is more than one Ln pixel on the 4 sides of any white grid, as long as the ILn value of one of the Ln pixels is < threshold, the whole white grid is considered to be completely obscured or partially obscured, and vice versa, the white grid is considered to be unobscured. S3: exhaust blackness grading. (1) Calculating the brightness values of unobscured white grids For each unobscured white grid, the DN value of all its An pixels is calculated (the average of the brightness values DNlue, DNgreen and DNre of the 3 colors blue, green and red). The average of the DN values of all the pixels of this white grid is taken as the DN value of this white grid. The the DN value is is the brightness value of the remote sensing image image element, and the grayscale value of the recorded feature. Without any unit of measurement, it is an integer value, and the value size is related to the radiometric resolution of the sensor, the emissivity of the feature, the atmospheric transmittance and scattering rate, etc. (2) Making virtual Ringelmann colorimetric cards The Ringelman blackness is a method to evaluate the blackness of the smoke by visual method. It is divided into six levels: 0, 1, 2, 3, 4 and 5, with level 5 being the most serious pollution. By default, the hull obscuration or exhaust interference cannot affect the 4 comer grids of the upper left, upper right, lower left and lower right of the grid map at the same time. Therefore, the largest DN value in the white grid of the 4 corners represents the brightness of Ringelman blackness level 0, and the smallest DN value in the black grid of the 4 corners represents the brightness of Ringelman blackness level 5. (3) Quantification of exhaust blackness DN value of class 1 blackness = DN value of class 0 blackness x 80% + DN value of class 5 blackness x 20%.
DN value of class 2 blackness = DN value of class 0 blackness x 60% + DN value of class 5 blackness x 40%. DN value of class 3 blackness = DN value of class 0 blackness x 40% + DN value of class 5 blackness x 60%. level 4 blackness DN value = DN value of class 0 blackness x 20% +DN value of class 5 blackness x 80%. For each white grid DN value, its Ringelman blackness percentage x is calculated. The formula is as follows: White grid DN value = DN value of class 0 blackness x (1-x) + DN value of class 5 blackness x x When x=20%, the blackness of the white grid is level 1. When x=40%, the blackness of the white grid is level 2. When x=60%, the blackness of the white grid is level 3 When x=80%, the blackness of the white grid is level 4. Since the exhaust continue to dilute and fade as soon as they leave the stack, the blackness level of the white grid with the largest x-value represents the blackness of the exhaust exiting the ship's stack. The above described embodiments are only a description of the preferred way of the present invention, not a limitation of the scope of the present invention. Without departing from the spirit of the design of the present invention, all kinds of deformations and improvements made to the technical solutions of the present invention by a person of ordinary skill in the art shall fall within the scope of protection determined by the claims of the present invention.
Claims (7)
1. An automatic black smoke capture system for ship locks characterizes in: Camera system: used to collect images and provide data for the hull obscuration and blackness recognition subsystems. Black and white grid map across the locks: used to provide a background reference to quantify the exhausted blackness. Hull obscuration identification subsystem: used to identify the change of white grid brightness caused by hull obscuration. Recognition subsystem for blackness of the exhaust: used to automatically quantify the blackness of the exhaust according to the degree of white grid brightness reduction.
2. The automatic black smoke capture system for ship locks according to claim 1 characterizes in that the height of the camera system should be the same as the average height of the passing ships' chimney. The camera system's angle is horizontal, perpendicular to the direction of the lock to capture the black and white grid map of the opposite side of the lock.
3. The automatic black smoke capture system for ship locks according to claim 1 characterizes in that the white grids in the black and white grid map across the locks are numbered, each white grid has a unique mark n, and each white grid has four adjacent black grids and four edges.
4. The automatic black smoke capture system for ship locks according to claim 3 characterizes in that pixels falling within the black and white grid map are categorized, pixels falling entirely within a white grid n are categorized as An pixels, pixels falling on four edges of the white grid are categorized as Ln pixels, and pixels falling within a black grid n are categorized as Bn pixels.
5. The automatic black smoke capture system for ship locks according to claim 1 characterizes in that: The operating steps of the hull obscuration identification subsystem include: S1.1: calculating the edge intensity of the black and white grid graph; by using the edge operator, each pixel within the graph obtain the edge intensity value I.
S1.2: setting a threshold value for the edge intensity, calculating the average value of the edge intensity ILn for each of the four edges falling on the white grid, with one-half of its average value set as the threshold value for the edge intensity. S1.3. determining whether any one white grid is obscured by the hull. If there are more than one Ln pixels of the four edges of any one white grid, as long as the ILn value ofone of the Ln pixels < threshold, the whole white grid is determined to be completely obscured or partially obscured, and vice versa, the white grid is determined to be non-obscured.
6. The automatic black smoke capture system for ship locks according to claim 1 characterizes in that the operation steps of the blackness grading subsystem include: S2.1: for the unobscured white grid, calculating the brightness DN values of all its An pixels, and take the DN values of the pixels as the DN value of the white grid. S2.2: making a virtual Ringelman colorimetric card with the maximum brightness DN value in the four corner of the white grids representing the brightness of Ringelmann blackness level 0 and the minimum brightness DN value in the four corner black of the grids representing the brightness of Ringelman black level 5. S2.3: for each brightness DN value of the white grid, calculating the percentage of Ringelman blackness. The formula is: White grid DN value = DN value of level 0 blackness x (1 - x) + DN value level 5 blackness x x when x = 20%, the blackness of this white grid is level 1, when x = 40%, the blackness of this white grid is level 2, when x = 60%, the blackness of this white grid is level 3, when x = 80%, the blackness of this white grid is level 4. Since the exhaust continue to dilute and fade as soon as they leave the stack, the blackness level of the white grid with the largest x-value represents the blackness of the exhaust exiting the ship's stack.
7. The automatic black smoke capture system for ship locks according to claim 6 characterizes in that DN brightness values include blue, green, and red colors, which are represented by DNlue, DNgreen, and DNred, respectively.
Figure 1 1/7
Figure 2 2/7
Figure 3 3/7
Figure 4 4/7
Figure 5 5/7
Figure 6 6/7
Figure 7 7/7
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021102903A AU2021102903A4 (en) | 2021-05-27 | 2021-05-27 | An Automatic Black Smoke Capture System for Ship Locks |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021102903A AU2021102903A4 (en) | 2021-05-27 | 2021-05-27 | An Automatic Black Smoke Capture System for Ship Locks |
Publications (1)
Publication Number | Publication Date |
---|---|
AU2021102903A4 true AU2021102903A4 (en) | 2021-07-22 |
Family
ID=76858469
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
AU2021102903A Ceased AU2021102903A4 (en) | 2021-05-27 | 2021-05-27 | An Automatic Black Smoke Capture System for Ship Locks |
Country Status (1)
Country | Link |
---|---|
AU (1) | AU2021102903A4 (en) |
-
2021
- 2021-05-27 AU AU2021102903A patent/AU2021102903A4/en not_active Ceased
Similar Documents
Publication | Publication Date | Title |
---|---|---|
AU2021100176A4 (en) | A Monitoring Method of Seagoing Vessels Exhaust Emission by Smart Phones | |
CN103077539B (en) | Motion target tracking method under a kind of complex background and obstruction conditions | |
CN102081801B (en) | Multi-feature adaptive fused ship tracking and track detecting method | |
CN101727748B (en) | Method, system and equipment for monitoring vehicles based on vehicle taillight detection | |
CN109409283A (en) | A kind of method, system and the storage medium of surface vessel tracking and monitoring | |
CN103763515A (en) | Video anomaly detection method based on machine learning | |
CN111402247A (en) | Machine vision-based method for detecting defects of suspension clamp on power transmission line | |
CN103903230A (en) | Video image sea fog removal and clearing method | |
CN111163290A (en) | Device and method for detecting and tracking night navigation ship | |
CN112037251B (en) | Method for monitoring marine vessel exhaust emission by using smart phone | |
CN114266299A (en) | Method and system for detecting defects of steel structure of railway bridge based on unmanned aerial vehicle operation | |
CN111123251B (en) | Target object detection method and device of radar | |
CN108614998A (en) | A kind of single pixel infrared target detection method | |
AU2021102903A4 (en) | An Automatic Black Smoke Capture System for Ship Locks | |
CN106204504A (en) | The enhancement method of low-illumination image mapped based on dark channel prior and tone | |
CN103413320A (en) | Port contaminant saliency detection method | |
CN112712454B (en) | Automatic snapshot system of boats and ships black cigarette suitable for ship lock | |
CN110728212A (en) | Road well lid monitoring device and method based on computer vision | |
US20040114054A1 (en) | Method of detecting a significant change of scene | |
AU2002232008A1 (en) | Method of detecting a significant change of scene | |
CN109389132A (en) | A kind of mist Concentration Testing method for early warning and system based on image | |
CN112927459A (en) | Sudoku fire behavior prediction method based on unmanned aerial vehicle vision and application | |
Sumimoto et al. | Machine vision for detection of the rescue target in the marine casualty | |
CN115170523A (en) | Low-complexity infrared dim target detection method based on local contrast | |
US8433139B2 (en) | Image processing apparatus, image processing method and program for segmentation based on a degree of dispersion of pixels with a same characteristic quality |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FGI | Letters patent sealed or granted (innovation patent) | ||
MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |