Light-emitting diode (LED) ultraviolet lamp oil stain remote sensing detection system

Abstract

The invention provides an LED purple light lamp oil stain remote sensing detection system, which takes purple light emitted by an LED purple light lamp as an excitation light source and is used for generating a purple light detection signal irradiating a water surface to be detected; a high-definition camera serves as an image data real-time acquisition end and is used for acquiring image data, acquired in real time, of a water surface to be measured; the wireless transmission module is connected with the output end of the high-definition camera and the input end of the oil stain identification end and is used for transmitting image data acquired by the high-definition camera in real time to the oil stain identification end; an oil spill intelligent recognition algorithm is pre-stored in the oil stain recognition end, the RGB component value of the image data of the water surface to be detected is recognized through the oil spill intelligent recognition algorithm according to the image data collected in real time, and whether oil stain exists on the surface of the water surface to be detected or not is judged according to the RGB component value. According to the invention, the LED ultraviolet lamp is used as an excitation light source, and when the LED ultraviolet lamp hits the spindrift, the spindrift is purple, so that the problems that oil fluorescence is easily generated and the spindrift is misjudged when ultraviolet laser or an ultraviolet LED is used as the excitation light source are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of oil pollution detection, and in particular to an LED ultraviolet light oil pollution remote sensing detection system. Background Art

[0002] With the rapid advancement of global industrialization, human society's demand for oil is increasing day by day, the scale of its exploitation is rapidly expanding, and the number of offshore oil wells and offshore oil transportation volume are increasing sharply. The number of oil spills on the sea surface caused by offshore operations, transportation and equipment is also increasing, which has aggravated marine oil pollution, and further endangered the living environment of marine life, seriously threatening the marine ecological environment and fishery resources.

[0003] At present, the oil spill monitoring systems used in ports and oil platforms in my country mainly use ultraviolet lasers or ultraviolet LEDs as excitation light sources. During use, it was found that the fluorescence wavelength of ultraviolet light on oil pollution is between 450-600 nanometers, which is similar to the waves of huge waves generated in the deep sea in imaging, so its spectral image and RGB image are similar to those of oil spills. Therefore, when judging whether there is an oil spill on the water surface, it is easy to judge the waves as oil spills, resulting in misjudgment and false alarms. Summary of the invention

[0004] According to the technical problem that ultraviolet laser or ultraviolet LED is prone to produce oil fluorescence and wave misjudgment when used as an excitation light source, an LED ultraviolet lamp oil pollution remote sensing detection system is provided, which uses an LED ultraviolet lamp (wavelength of 400-440 nanometers) as an excitation light source. Like the existing ultraviolet light, it will cause the oil pollution to produce fluorescence, and the wavelength of the fluorescence is also between 450-600 nanometers. However, unlike ultraviolet light as an excitation light source, when the LED ultraviolet lamp is hit on the waves, the waves appear purple; while when ultraviolet light is hit on the waves, the light produced is blue-green between 450-600 nanometers. This solves the problem that ultraviolet laser or ultraviolet LED is prone to produce oil fluorescence and wave misjudgment when used as an excitation light source.

[0005] The technical means adopted by the present invention are as follows:

[0006] An LED ultraviolet light oil pollution remote sensing detection system includes: an LED ultraviolet light, a high-definition camera, a wireless transmission module and an oil pollution identification terminal, wherein:

[0007] LED purple light, using the purple light emitted by the LED purple light as an excitation light source to generate a purple light detection signal irradiated to the water surface to be tested;

[0008] A high-definition camera is used as a real-time image data acquisition terminal to obtain real-time image data of the water surface to be measured;

[0009] A wireless transmission module is connected to the output end of the high-definition camera and the input end of the oil pollution identification end, and is used to transmit the image data of the water surface to be tested collected in real time by the high-definition camera to the oil pollution identification end;

[0010] The oil pollution identification terminal has an oil spill intelligent identification algorithm pre-stored inside. According to the image data of the water surface to be tested collected in real time, the oil spill intelligent identification algorithm is used to identify the RGB component values ​​of the image data of the water surface to be tested, and whether there is oil pollution on the surface of the water surface to be tested is judged according to the RGB component values.

[0011] Furthermore, the LED ultraviolet lamp adopts a focusing long-range LED ultraviolet lamp, and the long wave of the ultraviolet light source is 400-440nm.

[0012] Furthermore, the clean water surface image under the illumination of the focused long-range LED ultraviolet lamp appears purple, and the RGB component values ​​of the clean water surface image show a weak G value and a strong RB value; the oil-contaminated water surface image under the illumination of the focused long-range LED ultraviolet lamp has a stronger G value compared with the RB value.

[0013] Furthermore, in the oil pollution identification terminal, the RGB component values ​​of the image data of the water surface to be tested are identified by using the oil spill intelligent identification algorithm, which specifically includes:

[0014] The image data of the water surface to be measured collected in real time by a high-definition camera is used as a source image;

[0015] The oil spill intelligent recognition algorithm is used to perform threshold segmentation on the source image to obtain the corresponding binary image;

[0016] The image area corresponding to the pixel value of 255 in the binary image is identified as the target area, and the image area corresponding to the pixel value of 0 is identified as the background area, so as to segment the image area with oil spill and the image area without oil.

[0017] Furthermore, the oil spill intelligent recognition algorithm is used to perform threshold segmentation on the source image, specifically including:

[0018] Assume that the number of pixels in one of the source images is N, the grayscale range is [0, L-1], and calculate the probability p of the pixel point with grayscale level i appearing. i ,as follows:

[0019] p i =n i / N,i=0,1,2,...,L-1,

[0020] Among them, n i represents the number of pixels of gray level i; at the same time,

[0021] The pixels of the source image are divided into a background pixel set C0 and a target pixel set C1 according to the gray value using the segmentation threshold variable k, where C0 consists of pixels with gray values ​​between [0, k] and C1 consists of pixels with gray values ​​between [k+1, L-1];

[0022] Based on the grayscale distribution probability, calculate the mean u of the source image k ,as follows:

[0023]

[0024] Based on the grayscale distribution probability, the corresponding mean u0 of C0 is calculated as follows:

[0025]

[0026] Among them, w0 represents the cumulative probability of the pixel being classified into the background class pixel set C0,

[0027] Based on the grayscale distribution probability, calculate the corresponding mean u1 of C1 as follows:

[0028]

[0029] Among them, w represents the cumulative probability of the pixel being classified into the background class pixel set C0,

[0030] Further calculate the mean u of the source image k ,as follows:

[0031] u k =w0u0+w1u1

[0032] Calculate the mean u k The corresponding between-class variance as follows:

[0033]

[0034] Based on the calculated between-class variance Let the segmentation threshold variable k take values ​​in the range of [0, L-1], when When it is maximum, the corresponding k value is used as the optimal segmentation threshold;

[0035] Perform threshold segmentation on the source image according to the obtained optimal segmentation threshold to obtain a binary image;

[0036] If there is a pixel in the image whose G component relative to the RB component in the RGB value is greater than the set threshold, the pixel is confirmed to be the pixel corresponding to the image area with oil spill, thereby segmenting the image area with oil spill and the image area without oil.

[0037] Compared with the prior art, the present invention has the following advantages:

[0038] 1. The present invention provides an LED ultraviolet lamp oil pollution remote sensing detection system, which adopts an LED ultraviolet lamp (wavelength of 400-440 nanometers) as an excitation light source. When it hits the waves, the waves appear purple, which solves the problem of oil fluorescence and misjudgment of waves caused by ultraviolet lasers or ultraviolet LEDs as excitation light sources.

[0039] 2. The LED ultraviolet lamp oil pollution remote sensing detection system provided by the present invention adopts the LED ultraviolet lamp as the excitation light source, and also retains the advantages of large water surface irradiation area and high detection efficiency.

[0040] 3. The LED ultraviolet light oil pollution remote sensing detection system provided by the present invention is easy to modularize, small in size, and can be easily embedded in the existing port and oil platform oil spill monitoring system.

[0041] Based on the above reasons, the present invention can be widely promoted in the fields of oil pollution detection and the like. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0043] Figure 1 Schematic diagram of the system structure of the present invention.

[0044] Figure 2 A simulated image of an oil spill water surface under LED purple light at night provided by an embodiment of the present invention.

[0045] Figure 3 This is an image of waves illuminated by a non-LED purple light provided by an embodiment of the present invention.

[0046] Figure 4 This is a simulated image of waves illuminated by an LED ultraviolet lamp provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0048] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0049] like Figure 1 As shown, the present invention provides an LED ultraviolet light oil pollution remote sensing detection system, including: an LED ultraviolet light, a high-definition camera, a wireless transmission module and an oil pollution identification terminal, wherein:

[0050] LED purple light, using the purple light emitted by the LED purple light as an excitation light source to generate a purple light detection signal irradiated to the water surface to be tested;

[0051] A high-definition camera is used as a real-time image data acquisition terminal to obtain real-time image data of the water surface to be measured;

[0052] A wireless transmission module is connected to the output end of the high-definition camera and the input end of the oil pollution identification end, and is used to transmit the image data of the water surface to be tested collected in real time by the high-definition camera to the oil pollution identification end;

[0053] The oil pollution identification terminal has an oil spill intelligent identification algorithm pre-stored inside. According to the image data of the water surface to be tested collected in real time, the oil spill intelligent identification algorithm is used to identify the RGB component values ​​of the image data of the water surface to be tested, and whether there is oil pollution on the surface of the water surface to be tested is judged according to the RGB component values.

[0054] In the specific implementation, as a preferred embodiment of the present invention, the LED ultraviolet lamp adopts a focusing long-range LED ultraviolet lamp, and the long wave of the ultraviolet light source is 400-440nm. The ultraviolet light is emitted to the water surface within a certain range of the water surface to be tested, such as a port or an oil platform.

[0055] In specific implementation, as a preferred embodiment of the present invention, the clean water surface image under the irradiation of the focused long-range LED ultraviolet lamp appears purple, and the RGB component values ​​of the clean water surface image show a weak G value and a strong RB value; the oil-contaminated water surface image under the irradiation of the focused long-range LED ultraviolet lamp has a stronger G value compared with the RB value.

[0056] In specific implementation, as a preferred embodiment of the present invention, in the oil pollution identification terminal, the RGB component value of the image data of the water surface to be tested is identified by using the oil spill intelligent identification algorithm, which specifically includes:

[0057] The image data of the water surface to be measured collected in real time by a high-definition camera is used as a source image;

[0058] The oil spill intelligent recognition algorithm is used to perform threshold segmentation on the source image to obtain the corresponding binary image;

[0059] The image area corresponding to the pixel value of 255 in the binary image is identified as the target area, and the image area corresponding to the pixel value of 0 is identified as the background area, so as to segment the image area with oil spill and the image area without oil.

[0060] In specific implementation, as a preferred embodiment of the present invention, the use of the oil spill intelligent recognition algorithm to perform threshold segmentation on the source image specifically includes:

[0061] Assume that the number of pixels in one of the source images is N, the grayscale range is [0, L-1], and calculate the probability p of the pixel point with grayscale level i appearing. i ,as follows:

[0062] p i =n i / N,i=0,1,2,...,L-1,

[0063] Among them, n i represents the number of pixels of gray level i; at the same time,

[0064] The pixels of the source image are divided into a background pixel set C0 and a target pixel set C1 according to the gray value using the segmentation threshold variable k, where C0 consists of pixels with gray values ​​between [0, k] and C1 consists of pixels with gray values ​​between [k+1, L-1];

[0065] Based on the grayscale distribution probability, calculate the mean u of the source image k ,as follows:

[0066]

[0067] Based on the grayscale distribution probability, the corresponding mean u0 of C0 is calculated as follows:

[0068]

[0069] Among them, w0 represents the cumulative probability of the pixel being classified into the background class pixel set C0,

[0070] Based on the grayscale distribution probability, calculate the corresponding mean u1 of C1 as follows:

[0071]

[0072] Among them, w represents the cumulative probability of the pixel being classified into the background class pixel set C0,

[0073] Further calculate the mean u of the source image k ,as follows:

[0074] u k =w0u0+w1u1

[0075] Calculate the mean u k The corresponding between-class variance as follows:

[0076]

[0077] Based on the calculated between-class variance Let the segmentation threshold variable k take values ​​in the range of [0, L-1], when When it is maximum, the corresponding k value is used as the optimal segmentation threshold;

[0078] Perform threshold segmentation on the source image according to the obtained optimal segmentation threshold to obtain a binary image;

[0079] If there is a pixel in the image whose G component relative to the RB component in the RGB value is greater than the set threshold, the pixel is confirmed to be the pixel corresponding to the image area with oil spill, thereby segmenting the image area with oil spill and the image area without oil.

[0080] In summary, the present invention uses a focused long-range LED ultraviolet lamp instead of a laser as an excitation light source for exciting oil spills on the water surface. The LED ultraviolet lamp (wavelength is 400-440 nanometers) is used as the excitation light source. Like the existing ultraviolet light, it will cause the oil to produce fluorescence, and the wavelength of the fluorescence is also between 450-600 nanometers. However, unlike ultraviolet light as an excitation light source, Figure 2-4 As shown in the figure, when the LED purple light hits the waves, the waves appear purple; while when the ultraviolet light hits the waves, the light produced is blue-green between 450-600 nanometers. This solves the problem of oil fluorescence and misjudgment of waves when ultraviolet laser or ultraviolet LED is used as the excitation light source.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An LED purple light oil pollution remote sensing detection system, characterized in that: include: LED purple light, high-definition camera, wireless transmission module and oil pollution identification terminal, including: LED purple light, using the purple light emitted by the LED purple light as an excitation light source to generate a purple light detection signal irradiated to the water surface to be tested; A high-definition camera is used as a real-time image data acquisition terminal to obtain real-time image data of the water surface to be measured; A wireless transmission module is connected to the output end of the high-definition camera and the input end of the oil pollution identification end, and is used to transmit the image data of the water surface to be tested collected in real time by the high-definition camera to the oil pollution identification end; The oil pollution identification terminal has an oil spill intelligent identification algorithm pre-stored inside. According to the image data of the water surface to be tested collected in real time, the oil spill intelligent identification algorithm is used to identify the RGB component values ​​of the image data of the water surface to be tested, and whether there is oil pollution on the surface of the water surface to be tested is judged according to the RGB component values.

2. According to claim 1, the LED ultraviolet lamp oil pollution remote sensing detection system is characterized in that: The LED ultraviolet light lamp adopts a focusing long-range LED ultraviolet light lamp, and the long wave of the ultraviolet light source is 400-440nm.

3. According to claim 2, the LED ultraviolet lamp oil pollution remote sensing detection system is characterized in that: The clean water surface image under the illumination of the focused long-range LED ultraviolet lamp appears purple, and the RGB component values ​​of the clean water surface image show a weak G value and a strong RB value; the oil-contaminated water surface image under the illumination of the focused long-range LED ultraviolet lamp has a stronger G value compared with the RB value.

4. The LED ultraviolet lamp oil pollution remote sensing detection system according to claim 1 is characterized in that: In the oil pollution identification terminal, the oil spill intelligent identification algorithm is used to identify the RGB component values ​​of the image data of the water surface to be tested, which specifically includes: The image data of the water surface to be measured collected in real time by a high-definition camera is used as a source image; The oil spill intelligent recognition algorithm is used to perform threshold segmentation on the source image to obtain the corresponding binary image; The image area corresponding to the pixel value of 255 in the binary image is identified as the target area, and the image area corresponding to the pixel value of 0 is identified as the background area, so as to segment the image area with oil spill and the image area without oil.

5. The LED ultraviolet lamp oil pollution remote sensing detection system according to claim 4 is characterized in that: The method of using the oil spill intelligent recognition algorithm to perform threshold segmentation on the source image specifically includes: Assume that the number of pixels in one of the source images is N, the grayscale range is [0, L-1], and calculate the probability p of the pixel point with grayscale level i appearing. i ,as follows: p i =n i / N,i=0,1,2,...,L-1, Among them, n i represents the number of pixels of gray level i; at the same time, The pixels of the source image are divided into a background pixel set C0 and a target pixel set C1 according to the gray value using the segmentation threshold variable k, where C0 consists of pixels with gray values ​​between [0, k] and C1 consists of pixels with gray values ​​between [k+1, L-1]; Based on the grayscale distribution probability, calculate the mean u of the source image k ,as follows: Based on the grayscale distribution probability, the corresponding mean u0 of C0 is calculated as follows: Among them, w0 represents the cumulative probability of the pixel being classified into the background class pixel set C0, Based on the grayscale distribution probability, calculate the corresponding mean u1 of C1 as follows: Among them, w represents the cumulative probability of the pixel being classified into the background class pixel set C0, Further calculate the mean u of the source image k ,as follows: u k =w0u0+w1u1 Calculate the mean u k The corresponding between-class variance as follows: Based on the calculated between-class variance Let the segmentation threshold variable k take values ​​in the range of [0, L-1], when When it is maximum, the corresponding k value is used as the optimal segmentation threshold; Perform threshold segmentation on the source image according to the obtained optimal segmentation threshold to obtain a binary image; If there is a pixel in the image whose G component relative to the RB component in the RGB value is greater than the set threshold, the pixel is confirmed to be the pixel corresponding to the image area with oil spill, thereby segmenting the image area with oil spill and the image area without oil.

Images