CN112037251B - Method for monitoring marine vessel exhaust emission by using smart phone - Google Patents
Method for monitoring marine vessel exhaust emission by using smart phone Download PDFInfo
- Publication number
- CN112037251B CN112037251B CN202010752750.XA CN202010752750A CN112037251B CN 112037251 B CN112037251 B CN 112037251B CN 202010752750 A CN202010752750 A CN 202010752750A CN 112037251 B CN112037251 B CN 112037251B
- Authority
- CN
- China
- Prior art keywords
- image
- blackness
- gray value
- pixels
- frame
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/10024—Color image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for monitoring marine vessel tail gas emission by using a smart phone, which comprises the following steps: s1, collecting a driving video of the suspected illegal marine vessel by the smart phone; s2, tracking the position of the ship in the rest images based on the position of the ship in the first frame image; s3, manufacturing a ringer Mannich colorimetric card for evaluating the blackness of the tail gas in each frame of image; s4, processing all pixels of the tail gas area in each frame of image in the same image processing mode as the step S3 to extract the brightness value of the representative pixel to be compared with a LINGMANN color chart, and determining the blackness of the tail gas of the ship; s5, judging whether the tail gas of the marine vessel is illegally discharged; the method meets the requirement that when a maritime law enforcement officer executes a daily patrol task, videos shot under the state that a platform, hands and targets are not static are used for monitoring the illegal tail gas emission ship, automatic tracking of the suspected illegal ship can be realized, whether black smoke of the illegal ship reaches the illegal degree or not is quantitatively judged, the operation is convenient, the efficiency is high, and the judgment result is accurate.
Description
Technical Field
The invention relates to the technical field of methods for catching fear of black smoke emitted by mobile pollution sources, in particular to a method for monitoring marine exhaust emission by using a smart phone.
Background
At present, ship tail gas treatment is a main treatment object of the current overwater blue sky protection action. The most intuitive and objectionable problem of ship tail gas of residents in coastal and coastal rivers is that ships smoke on the spot. In 2018, the Shanghai city is in the first place in China to require that' motor vehicles and ships cannot discharge obvious visible black smoke.
The ringelman blackness colorimetric card is built in a camera lens and has been widely applied to the emission of black smoke of fixed pollution sources (steel mills, power plants and the like) as a ringelman blackness tester, but the method is not suitable for being applied to the environment of a mobile platform (sea patrol boat) and a mobile object (ship) with complexity.
At present, the method for snapshotting black smoke emitted by a sea ship is that law enforcement personnel record a video for a certain time (transient black smoke emission caused by sudden acceleration of a ship is not illegal), and simultaneously carry a ringer Mannheim colorimetric card to judge whether the black smoke degree exceeds two levels or more by contrast; however, this method has a problem that subjectivity in determining the black smoke level is high, and law enforcement disputes are likely to occur.
Disclosure of Invention
The invention aims to provide a method for monitoring marine vessel tail gas emission by using a smart phone, which aims at effectively monitoring and judging whether the marine vessel tail gas emission is violated or not based on an image acquisition mode under the condition that a patrol platform, a human hand and an image acquisition target are all in an unsteady state.
Therefore, the technical scheme of the invention is as follows:
a method for monitoring marine vessel exhaust emission by using a smart phone comprises the following steps:
s1, acquiring the driving video of the suspected illegal marine vessel by law enforcement personnel through a smart phone to obtain a plurality of frames of images of the suspected illegal marine vessel; the intelligent mobile phone always keeps the state of the first frame image during the video acquisition process;
s2, sequentially processing the other frame images obtained in the step S1 based on the position information of the ships suspected to be illegally discharged in the first frame image in the image, so as to sequentially determine the position information of the ships in the other frame images in the image;
the specific treatment process is as follows:
s201, establishing a plane image coordinate system by taking the row number of pixels in the image as a vertical coordinate x and the column number as an abscissa y so as to align a target area in a first frame imageDescribing the domain; the target area is a rectangular frame which is divided into four sub-areas, namely an upper left sub-area, a lower left sub-area, an upper right sub-area and a lower right sub-area, the central point of the rectangular frame is aligned with a chimney port of the target ship, so that the ship body of the marine ship is positioned in one sub-area, namely the ship body sub-area, and the tail gas discharged by the marine ship is positioned in the other sub-area, namely the tail gas sub-area; based on this, the location information of the target area is described as: [ x ] ofi~xj,ym~yn],xiAnd xjRespectively the start line number and the end line number of the rectangular area, j > i, ymAnd ynRespectively, starting line numbers and ending column numbers of the rectangular areas, wherein n is more than m, and the total pixel number z of the target area is (j-i +1) x (n-m + 1);
s202, utilizing an edge operator of the hull subregion in the first frame image to highlight edge pixels (including junctions between ships and water, between ships and sky, between black chimneys on ships and white buildings and the like) in the region, and based on position information of the hull subregion in the first frame image: [ x ] ofa~xb,yc~yd]B > a, d > c, respectively intercepting the position information in the second frame image as [ xa-1~xb-1,yc-1~yd-1]、[xa-1~xb-1,yc~yd]、[xa-1~xb-1,yc+1~yd+1]、[xa~xb,yc-1~yd-1]、[xa~xb,yc~yd]、[xa~xb,yc+1~yd+1]、[xa+1~xb+1,yc-1~yd-1]、[xa+1~xb+1,yc~yd]、[xa+1~xb+1,yc+1~yd+1]Respectively processing the images of the nine regions by using edge operators to highlight edge pixels in the regions;
s203, pixel brightness operation is carried out on the hull sub-area in the first frame image and nine to-be-selected area images obtained from the second frame image, namely the brightness values of each pair of same row-column number pixels in every two areas are subtracted, and the absolute value is obtained, so that nine difference processing images are obtained;
s204, summing all pixel values in the nine difference processing images respectively, and taking the difference processing image with the minimum summation result, wherein the image of the to-be-selected area corresponding to the difference processing image is determined as the ship body sub-area of the second frame image;
s205, repeating the steps S201 to S204, processing the frame of image based on the previous frame of image of each frame of image, obtaining a hull subregion of the frame of image, and realizing the tracking of the target marine vessel;
the image acquisition and processing mode of the step S2 solves the problem that the position of a chimney opening in a picture is unstable due to the fact that a sea patrol boat shakes, a photographer shakes both hands, a target ship moves and the like in the current real-time video acquisition, and the purpose of automatically tracking the ship in the video is achieved.
S3, sequentially processing and sorting the brightness of all pixels in the target area in each frame of image obtained in the step S1, and extracting the brightness value of representative pixels to manufacture a LINGMANM colorimetric card for evaluating the blackness of the tail gas in each frame of image;
s4, sequentially processing all pixels of the tail gas subregion in the target region in each frame of image obtained in the step S1 and sequencing the brightness by adopting the same image processing mode as the ringer Mannich colorimetric card manufactured in the step S3, extracting the brightness value of representative pixels, and comparing the brightness value with the ringer Mannich colorimetric card manufactured based on the same image to judge the blackness of the tail gas of the ship in the image;
and S5, determining whether the ship has the problem of illegal tail gas emission according to the ship running time corresponding to the multi-frame images which are continuously judged to be illegal by the blackness of the ship tail gas.
Further, in step S3, the specific method for obtaining the lingerman color chart includes:
s301, using brightness values of all pixels in the target area in the image as processing objects, and using blue brightness value DN of each pixelblueGreen brightness value DNgreenAnd red luminance value DNredSelecting the minimum brightness value as the gray value of the pixel;
s302, counting a gray value histogram of all pixels by taking a gray value as a horizontal coordinate and taking the number of the pixels as a vertical coordinate; in the grey value histogram, selecting the grey value of the pixel which is sorted at the Mth bit in the positive direction in the grey value sorting from small to large as the Ringelmann 5-level blackness, and selecting the grey value of the pixel which is sorted at the Mth bit in the reverse direction in the grey value sorting from small to large as the Ringelmann 0-level blackness;
s303, correspondingly defining the following definition mode based on the definition mode of the step S302:
the gray value corresponding to the Ringelman level 1 blackness is multiplied by 80% by the gray value corresponding to the Ringelman level 0 blackness and multiplied by 20% by the gray value corresponding to the Ringelman level 5 blackness,
the gray value corresponding to the Ringelman level 2 blackness is multiplied by 60% by the gray value corresponding to the Ringelman level 0 blackness and multiplied by 40% by the gray value corresponding to the Ringelman level 5 blackness,
the gray value corresponding to the Ringelman 3-level blackness is equal to the gray value corresponding to the Ringelman 0-level blackness multiplied by 40% + the gray value corresponding to the 5-level blackness multiplied by 60%,
the gray value corresponding to the blackness level of lingeman 4 is multiplied by 20% by the gray value corresponding to the blackness level of lingeman 0 and multiplied by 80% by the gray value corresponding to the blackness level of lingeman 5.
Further, in step S302, M takes a value of: the number of all pixels within the target area in the image is multiplied by 1%.
Further, in step S4, the specific implementation method for determining the blackness of the ship exhaust gas in the image is as follows:
s401, taking the brightness values of all pixels in the exhaust subregion in the target region in the image as processing objects, and taking the blue brightness value DN of each pixelblueGreen brightness value DNgreenAnd red luminance value DNredSelecting the minimum brightness value as the gray value of the pixel;
s402, counting a gray value histogram of all pixels by taking a gray value as a horizontal coordinate and taking the number of the pixels as a vertical coordinate; selecting the gray value of the pixel which is sorted at the Nth bit in the positive direction in the sorting from small to large of the gray value in the gray value histogram as the tail gas gray value;
and S403, comparing the tail gas gray value obtained in the step S402 with a ringer Mannich colorimetric card prepared based on the same image, and taking the ringer Mannich blackness grade closest to the tail gas gray value as the ringer Mannich blackness grade of the ship tail gas in the image.
Further, in step S402, N takes the values: the number of all pixels within the target area in the image is multiplied by 1%.
Compared with the prior art, the method for monitoring the marine vessel exhaust emission by using the smart phone meets the requirement that when marine law enforcement personnel perform daily patrol tasks, videos shot under the state that a platform, hands and targets are not static are used for monitoring the illegal exhaust emission vessel, the automatic tracking of the illegal suspected vessel can be realized, whether the black smoke reaches the illegal degree or not is quantitatively judged, the operation is convenient, the efficiency is high, and the judgment result is accurate.
Drawings
FIG. 1 is a flow chart of a method for monitoring marine exhaust emission using a smart phone according to the present invention;
FIG. 2 is a schematic diagram illustrating the target area in the first image frame in step S2 according to an embodiment of the present invention;
FIG. 3 is a gray scale image obtained after edge pixels are highlighted by an edge operator in a target region portion in a first frame image according to an embodiment of the present invention;
fig. 4 is a grayscale image obtained after edge pixels are highlighted by an edge operator in a target area portion in a 75 th frame image obtained by recording a video for 3 seconds in the embodiment of the present invention;
fig. 5 is a gray level histogram obtained after all pixels in the target area of the first frame image are processed in step S3 in the embodiment of the present invention;
fig. 6 is a grayscale image obtained after the exhaust subregion in the target region of the first frame image is processed in step S4 in the embodiment of the present invention.
Detailed Description
The invention will be further described with reference to the following figures and specific examples, which are not intended to limit the invention in any way.
The monitoring method of the present application is further explained and illustrated by taking as an example a video of a black-smoke emitting ship taken at a wharf of the naval office of Zhenjiang at long river at 14 pm of 25 pm of 2020. The current day is cloudy and the distance between ships is long, so that the difficulty in visually judging black smoke is high, but the monitoring method can still effectively judge whether the ships violate the regulations on discharge.
As shown in fig. 1, the method for monitoring marine vessel exhaust emission by using a smart phone comprises the following steps:
s1, acquiring the driving video of the suspected illegal marine vessel by law enforcement personnel through the smart phone, wherein the smart phone always keeps the state of the first frame of image acquisition in the video acquisition process; the video duration is 16s, and 480 frames of images are contained in the video; the number of all pixels of each frame of image is 921600, the number of pixels corresponding to each row is 1280, and the number of pixels of each column is 720;
s2, sequentially processing the other frame images obtained in the step S1 based on the position information of the ships suspected to be illegally discharged in the first frame image in the image to determine the position information of the ships in the other frame images;
the specific processing procedure of step S2 is as follows:
s201, establishing a plane image coordinate system by taking the row number of pixels in the image as a vertical coordinate x and the column number as a horizontal coordinate y so as to describe a target area in a first frame image; as shown in fig. 3, the target area (number 1) is a rectangular frame, which is divided into four sub-areas, namely, upper left, lower left, upper right and lower right, the central point of the rectangular frame is aligned with the chimney port of the target ship, so that the hull of the ship is located in the lower left sub-area (number 2), and the exhaust gas discharged by the ship is located in the upper right sub-area (number 3);
based on this, the location information of the target area is described as: [595 to 864,261 to 468], 595 and 864 are start and end row numbers of the rectangular region, respectively, 261 and 468 are start and end column numbers of the rectangular region, respectively, and the total number of pixels z of the target region is (j-i +1) × (n-m +1) ═ 56160;
s202, highlighting edge pixels in the area by using an edge operator of the hull sub-area in the first frame image, and based on the position information of the hull sub-area in the first frame image: [595 to 729,365 to 468], respectively intercepting the position information in the second frame image as: [595 to 729,365 to 468], the position information of the nine regions extracted in the second frame image is: images of nine regions to be selected of [ 594-728,364-467 ], [ 594-728,365-468 ], [ 594-728,366-469 ], [ 595-729,364-467 ], [ 595-729,365-468 ], [ 595-729,366-469 ], [ 596-730,364-467 ], [ 596-730,365-468 ], [ 596-730,366-469 ], are processed by edge operators respectively to highlight edge pixels in the regions;
s203, pixel brightness operation is carried out on the hull sub-area in the first frame image and nine areas to be selected in the second frame image respectively, namely the brightness values of each pair of pixels with the same row number and column number in each two areas are subtracted, and an absolute value is obtained, so that nine difference value processing images are obtained;
s204, summing all pixel values in the nine difference processing images respectively, and taking the difference processing image with the minimum summation result, wherein the image of the to-be-selected area corresponding to the difference processing image is determined as the ship body sub-area of the second frame image;
FIG. 3 shows a gray image obtained by processing a first frame image with an edge operator in the embodiment; as can be seen from the edge pixels in fig. 3, the automatic tracking ship mainly depends on the boundary between the ship and water, the texture inside the ship body is almost kept unchanged from frame to frame, and the boundary between the far forest belt and the sky is unreliable. Fig. 4 is a grayscale image of a vessel subregion in the 75 th frame of image determined after the processing of step S2 of the 75 th frame of image obtained by recording the video for the 3 rd second in the embodiment; as can be seen from the figure, the picture in the target area in the 75 th image after the automatic ship tracking algorithm has run for 3 seconds shows that the automatic ship tracking scheme is effective and accurate.
S3, sequentially processing and sorting the brightness of all pixels in the target area in each frame of image obtained in the step S1, and extracting the brightness value of representative pixels to manufacture a LINGMANM colorimetric card for evaluating the blackness of the tail gas in each frame of image;
the specific processing procedure of step S3 is as follows:
s301, using brightness values of all pixels in the target area in the image as processing objects, and using blue brightness value DN of each pixelblueGreen brightness value DNgreenAnd red luminance value DNredSelecting the minimum brightness value as the gray value of the pixel;
s302, taking the gray value as a horizontal coordinate and the number of pixels as a vertical coordinate, and counting the gray value histograms of all the pixels as shown in FIG. 5; in the grey value histogram, selecting the grey value of the pixel which is sorted at the 562 th bit in the positive direction in the grey value sorting from small to large as the Ringelmann 5-level blackness, and selecting the grey value of the pixel which is sorted at the 562 th bit in the reverse direction in the grey value sorting from small to large as the Ringelmann 0-level blackness;
s303, based on the definition mode in the step S302, the gray value corresponding to the Ringelman 5-level blackness is 141, and the gray value corresponding to the Ringelman 0-level blackness is 217; accordingly, define:
the gray value corresponding to the blackness of the ringer Mann level 1 is 80% of the gray value corresponding to the blackness of the ringer Mann level 0 and the gray value corresponding to the blackness of the ringer Mann level 5 is 156.2 of the gray value,
the gray value corresponding to the blackness of the ringelman level 2 is 60% corresponding to the blackness of the ringelman level 0, and the gray value corresponding to the blackness of the ringelman level 5 is 40% corresponding to the gray value of 171.4,
the gray value corresponding to the blackness of the ringelman level 3 is 40% of the gray value corresponding to the blackness of the ringelman level 0 and the gray value corresponding to the blackness of the ringelman level 5 is 60% of the gray value corresponding to the blackness of the ringelman level 186.6,
the gray value corresponding to the 4-level blackness of lingeman is multiplied by 20% by the gray value corresponding to the 0-level blackness of lingeman, and multiplied by 80% by the gray value corresponding to the 5-level blackness of lingeman is multiplied by 201.8;
s4, sequentially processing all pixels of the tail gas subregion in the target region in each frame of image obtained in the step S1 and sequencing the brightness by adopting the same image processing mode as the ringer Mannich colorimetric card manufactured in the step S3, extracting the brightness value of representative pixels, and comparing the brightness value with the ringer Mannich colorimetric card manufactured based on the same image to judge the blackness of the tail gas of the ship in the image;
the specific processing procedure of step S4 is as follows:
s401, taking the brightness values of all pixels in the exhaust subregion in the target region in the image as processing objects, and taking the blue brightness value DN of each pixelblueGreen brightness value DNgreenAnd red luminance value DNredSelecting the minimum brightness value as the gray value of the pixel;
s402, counting a gray value histogram of all pixels by taking a gray value as a horizontal coordinate and taking the number of the pixels as a vertical coordinate; selecting the gray value of the pixel which is sorted at the 140 th bit in the positive direction in the sorting from small to large of the gray value in the gray value histogram as the tail gas gray value;
and S403, comparing the tail gas gray value obtained in the step S402 with a ringer Mannich colorimetric card prepared based on the same image, and taking the ringer Mannich blackness grade closest to the tail gas gray value as the ringer Mannich blackness grade of the ship tail gas in the image.
Specifically, as shown in fig. 6, a gray scale map obtained by the step S4 of the tail gas subregion in the target region of the first frame image; the method comprises the following steps that a regional division map is obtained by carrying out color comparison on each pixel and a Lingemann colorimetric card obtained based on a first frame image, specifically, a Lingemann blackness 2-level region is arranged in a red frame range, a Lingemann blackness 1-level region is arranged in a blue frame range, and a Lingemann blackness 0-level region is arranged outside the blue frame range; in order to avoid the problem that the few end value pixels have errors, in the forward sorting of the gray values corresponding to the first frame image from small to large, the gray value of the pixel at the 140 th bit: 175.3, as the exhaust gas gray value, when the ship is compared with the ringelmann colorimetric card obtained based on the first frame image, it is found that the gray value is between the ringelmann 2-level blackness (171.4) and the ringelmann 3-level blackness (186.6), but is closer to the ringelmann 2-level blackness, and therefore, it is determined that the ringelmann blackness of the exhaust gas of the ship of the present embodiment in the first frame image is the ringelmann 2-level blackness.
S5, determining whether the problem of illegal tail gas emission exists in the sea vessel according to the ship running time corresponding to the multiframe images which are continuously judged to be illegal by the blackness of the tail gas of the ship; the specific Ringelman blackness level for judging the violation of exhaust emission and the running time of the ship are determined by rules set by local law enforcement.
Claims (5)
1. A method for monitoring marine vessel exhaust emission by using a smart phone is characterized by comprising the following steps:
s1, acquiring the driving video of the suspected illegal marine vessel by law enforcement personnel through a smart phone to obtain a plurality of frames of images of the suspected illegal marine vessel; the intelligent mobile phone always keeps the state of the first frame image during the video acquisition process;
s2, sequentially processing the other frame images obtained in the step S1 based on the position information of the ships suspected to be illegally discharged in the first frame image in the image to determine the position information of the ships in the other frame images;
the specific treatment process is as follows:
s201, establishing a plane image coordinate system by taking the row number of pixels in the image as a vertical coordinate x and the column number as a horizontal coordinate y so as to describe a target area in a first frame image; the target area is a rectangular frame which is divided into four sub-areas, namely an upper left sub-area, a lower left sub-area, an upper right sub-area and a lower right sub-area, the central point of the rectangular frame is aligned with a chimney port of the target ship, so that the ship body of the marine ship is positioned in one sub-area, namely the ship body sub-area, and the tail gas discharged by the marine ship is positioned in the other sub-area, namely the tail gas sub-area; based on this, the location information of the target area is described as: [ x ] ofi~xj,ym~yn],xiAnd xjRespectively the start line number and the end line number of the rectangular area, j > i, ymAnd ynRespectively, a starting column number and an ending column number of the rectangular area, wherein n is more than m, and the total pixel number z of the target area is (j-i +1) x (n-m + 1);
s202, highlighting edge pixels in the area by using an edge operator of the hull sub-area in the first frame image, and based on the position information of the hull sub-area in the first frame image: [ x ] ofa~xb,yc~yd]B > a, d > c, respectively intercepting the position information in the second frame image as [ xa-1~xb-1,yc-1~yd-1]、[xa-1~xb-1,yc~yd]、[xa-1~xb-1,yc+1~yd+1]、[xa~xb,yc-1~yd-1]、[xa~xb,yc~yd]、[xa~xb,yc+1~yd+1]、[xa+1~xb+1,yc-1~yd-1]、[xa+1~xb+1,yc~yd]、[xa+1~xb+1,yc+1~yd+1]Respectively processing the images of the nine regions by using edge operators to highlight edge pixels in the regions;
s203, pixel brightness operation is carried out on the hull sub-area in the first frame image and nine to-be-selected area images obtained from the second frame image, namely the brightness values of each pair of same row-column number pixels in every two areas are subtracted, and the absolute value is obtained, so that nine difference processing images are obtained;
s204, summing all pixel values in the nine difference processing images respectively, and taking the difference processing image with the minimum summation result, wherein the image of the area to be selected corresponding to the difference processing image is determined as the hull subregion of the second frame image;
s205, repeating the steps S201 to S204, processing the frame of image based on the previous frame of image of each frame of image, obtaining a hull subregion of the frame of image, and realizing the tracking of the target marine vessel;
s3, sequentially processing and sorting the brightness of all pixels in the target area in each frame of image obtained in the step S1, and extracting the brightness value of representative pixels to manufacture a LINGMANM colorimetric card for evaluating the blackness of the tail gas in each frame of image; the representative pixels are pixels which are all arranged at the Mth bit in a forward sequence and pixels which are arranged at the Mth bit in a reverse sequence in a descending-to-ascending sequence of the gray value; the gray value is the minimum brightness value among the blue brightness value, the green brightness value and the red brightness value of the pixel;
s4, sequentially processing all pixels of the tail gas subregion in the target region in each frame of image obtained in the step S1 and sequencing the brightness by adopting the same image processing mode as the ringer Mannich colorimetric card manufactured in the step S3, extracting the brightness value of representative pixels, and comparing the brightness value with the ringer Mannich colorimetric card manufactured based on the same image to judge the blackness of the tail gas of the ship in the image; the representative pixels are all pixels which are sorted at the Nth bit in the positive direction in the sorting of the gray value from small to large; the gray value is the minimum brightness value among the blue brightness value, the green brightness value and the red brightness value of the pixel;
and S5, determining whether the ship has the problem of illegal tail gas emission according to the ship running time corresponding to the multi-frame images which are continuously judged to be illegal by the blackness of the ship tail gas.
2. The method for realizing marine vessel exhaust emission monitoring by using the smart phone according to claim 1, wherein in step S3, the specific method for obtaining the ringelman color chart comprises the following steps:
s301, using brightness values of all pixels in the target area in the image as processing objects, and using blue brightness value DN of each pixelblueGreen brightness value DNgreenAnd red luminance value DNredSelecting the minimum brightness value as the gray value of the pixel;
s302, counting a gray value histogram of all pixels by taking a gray value as a horizontal coordinate and taking the number of the pixels as a vertical coordinate; in the grey value histogram, selecting the grey value of the pixel which is sorted at the Mth bit in the positive direction in the grey value sorting from small to large as the Ringelmann 5-level blackness, and selecting the grey value of the pixel which is sorted at the Mth bit in the reverse direction in the grey value sorting from small to large as the Ringelmann 0-level blackness;
s303, correspondingly defining the following definition mode based on the definition mode of the step S302:
the gray value corresponding to the Ringelman level 1 blackness is multiplied by 80% by the gray value corresponding to the Ringelman level 0 blackness and multiplied by 20% by the gray value corresponding to the Ringelman level 5 blackness,
the gray value corresponding to the Ringelman level 2 blackness is multiplied by 60% by the gray value corresponding to the Ringelman level 0 blackness and multiplied by 40% by the gray value corresponding to the Ringelman level 5 blackness,
the gray value corresponding to the Ringelman 3-level blackness is equal to the gray value corresponding to the Ringelman 0-level blackness multiplied by 40% + the gray value corresponding to the 5-level blackness multiplied by 60%,
the gray value corresponding to the blackness level of lingeman 4 is multiplied by 20% by the gray value corresponding to the blackness level of lingeman 0 and multiplied by 80% by the gray value corresponding to the blackness level of lingeman 5.
3. The method for monitoring marine vessel exhaust emission by using a smart phone according to claim 2, wherein in step S302, M takes the values of: the number of all pixels within the target area in the image is multiplied by 1%.
4. The method for monitoring marine exhaust emission by using a smart phone according to claim 1, wherein in step S4, the specific implementation method for determining the blackness of the marine exhaust in the image is as follows:
s401, taking the brightness values of all pixels in the exhaust subregion in the target region in the image as processing objects, and taking the blue brightness value DN of each pixelblueGreen brightness value DNgreenAnd red luminance value DNredSelecting the minimum brightness value as the gray value of the pixel;
s402, counting a gray value histogram of all pixels by taking a gray value as a horizontal coordinate and taking the number of the pixels as a vertical coordinate; selecting the gray value of the pixel which is sorted at the Nth bit in the positive direction in the sorting from small to large of the gray value in the gray value histogram as the tail gas gray value;
and S403, comparing the tail gas gray value obtained in the step S402 with a ringer Mannich colorimetric card prepared based on the same image, and taking the ringer Mannich blackness grade closest to the tail gas gray value as the ringer Mannich blackness grade of the ship tail gas in the image.
5. The method for monitoring marine vessel exhaust emission by using a smart phone according to claim 4, wherein in step S402, N is selected from the following values: the number of all pixels within the target area in the image is multiplied by 1%.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010752750.XA CN112037251B (en) | 2020-07-30 | 2020-07-30 | Method for monitoring marine vessel exhaust emission by using smart phone |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010752750.XA CN112037251B (en) | 2020-07-30 | 2020-07-30 | Method for monitoring marine vessel exhaust emission by using smart phone |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112037251A CN112037251A (en) | 2020-12-04 |
CN112037251B true CN112037251B (en) | 2021-05-04 |
Family
ID=73583577
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010752750.XA Active CN112037251B (en) | 2020-07-30 | 2020-07-30 | Method for monitoring marine vessel exhaust emission by using smart phone |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112037251B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112712454B (en) * | 2021-01-07 | 2021-09-07 | 交通运输部天津水运工程科学研究所 | Automatic snapshot system of boats and ships black cigarette suitable for ship lock |
CN113822217A (en) * | 2021-09-30 | 2021-12-21 | 杭州春来科技有限公司 | Ship tail gas monitoring method based on AIS and video image analysis |
CN115909220B (en) * | 2023-01-07 | 2023-05-09 | 广州市云景信息科技有限公司 | Method and system for realizing intelligent management and control of atmospheric pollution of ship |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4266535B2 (en) * | 2001-04-27 | 2009-05-20 | 株式会社シー・イー・デー・システム | Black smoke detection system |
CN102456142A (en) * | 2010-11-02 | 2012-05-16 | 上海宝信软件股份有限公司 | Analysis method for smoke blackness based on computer vision |
JP5360682B2 (en) * | 2009-03-31 | 2013-12-04 | 三菱自動車工業株式会社 | Exhaust gas measuring device |
CN106769732A (en) * | 2016-12-31 | 2017-05-31 | 中国科学技术大学 | A kind of rectilinear diesel vehicle smoke intensity detection method |
CN108007573A (en) * | 2017-12-04 | 2018-05-08 | 佛山市南海区环境保护监测站(佛山市南海区机动车排气污染管理所) | A kind of motor-vehicle tail-gas blackness analysis system and method |
CN108088799A (en) * | 2017-12-04 | 2018-05-29 | 佛山市南海区环境保护监测站(佛山市南海区机动车排气污染管理所) | The measuring method and system of motor-vehicle tail-gas lingemann blackness |
CN109035298A (en) * | 2018-09-05 | 2018-12-18 | 中南大学 | A kind of black smoke detection and DG calculation method based on black smoke kinetic characteristic |
-
2020
- 2020-07-30 CN CN202010752750.XA patent/CN112037251B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4266535B2 (en) * | 2001-04-27 | 2009-05-20 | 株式会社シー・イー・デー・システム | Black smoke detection system |
JP5360682B2 (en) * | 2009-03-31 | 2013-12-04 | 三菱自動車工業株式会社 | Exhaust gas measuring device |
CN102456142A (en) * | 2010-11-02 | 2012-05-16 | 上海宝信软件股份有限公司 | Analysis method for smoke blackness based on computer vision |
CN106769732A (en) * | 2016-12-31 | 2017-05-31 | 中国科学技术大学 | A kind of rectilinear diesel vehicle smoke intensity detection method |
CN108007573A (en) * | 2017-12-04 | 2018-05-08 | 佛山市南海区环境保护监测站(佛山市南海区机动车排气污染管理所) | A kind of motor-vehicle tail-gas blackness analysis system and method |
CN108088799A (en) * | 2017-12-04 | 2018-05-29 | 佛山市南海区环境保护监测站(佛山市南海区机动车排气污染管理所) | The measuring method and system of motor-vehicle tail-gas lingemann blackness |
CN109035298A (en) * | 2018-09-05 | 2018-12-18 | 中南大学 | A kind of black smoke detection and DG calculation method based on black smoke kinetic characteristic |
Non-Patent Citations (3)
Title |
---|
Methods of descriptive statistics in the analysis of pollutants of exhaust gases of ship diesel engines;KE Vladimirovna;《OALib Journal》;20101231;全文 * |
基于背景差分法的尾气烟度检测系统设计;薛梦;《电子技术应用》;20190506;全文 * |
面向烟气黑度检测的工业排放烟尘;王亚楠;《中国优秀硕士学位论文全文数据库电子期刊》;20200430;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN112037251A (en) | 2020-12-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112037251B (en) | Method for monitoring marine vessel exhaust emission by using smart phone | |
AU2021100176A4 (en) | A Monitoring Method of Seagoing Vessels Exhaust Emission by Smart Phones | |
CN113808282B (en) | Multi-navigation element data fusion method | |
CN110866926B (en) | Infrared remote sensing image rapid and fine sea-land segmentation method | |
CN113887412B (en) | Detection method, detection terminal, monitoring system and storage medium for pollution emission | |
CN109064479B (en) | Sea-sky-line detection method based on gray dynamic features of adjacent video frames | |
CN113591592B (en) | Overwater target identification method and device, terminal equipment and storage medium | |
CN111123251B (en) | Target object detection method and device of radar | |
CN110120073B (en) | Method for guiding recovery of unmanned ship based on lamp beacon visual signal | |
CN110610485A (en) | Ultra-high voltage transmission line channel hidden danger early warning method based on SSIM algorithm | |
CN115100174A (en) | Ship sheet metal part paint surface defect detection method | |
CN103413320A (en) | Port contaminant saliency detection method | |
CN110728212A (en) | Road well lid monitoring device and method based on computer vision | |
CN112686106A (en) | Method for converting video image into maritime radar image | |
CN111914624B (en) | Method for identifying ship illegal closing AIS (automatic identification system) behavior by utilizing high-resolution satellite image | |
CN113989265B (en) | Speed sensor bolt loss fault identification method based on deep learning | |
CN112712454B (en) | Automatic snapshot system of boats and ships black cigarette suitable for ship lock | |
CN114120061A (en) | Small target defect detection method and system for power inspection scene | |
CN111665499A (en) | Judgment method for reducing marine oil spill early warning misjudgment rate of shipborne radar | |
CN113808117A (en) | Lamp detection method, device, equipment and storage medium | |
CN112560589A (en) | Method and device for identifying ship pollution on water based on remote sensing technology and storage medium | |
AU2021102903A4 (en) | An Automatic Black Smoke Capture System for Ship Locks | |
CN111583325A (en) | Image processing-based method for detecting sea waves by unmanned ship | |
CN118038165A (en) | Video-based automatic identification algorithm for black smoke event of ship | |
CN116503767B (en) | River course floater recognition system based on semantic image processing |
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 |