CN110889327B - Intelligent detection method for sewage outlet around water area based on thermal infrared image - Google Patents
Intelligent detection method for sewage outlet around water area based on thermal infrared image Download PDFInfo
- Publication number
- CN110889327B CN110889327B CN201910983757.XA CN201910983757A CN110889327B CN 110889327 B CN110889327 B CN 110889327B CN 201910983757 A CN201910983757 A CN 201910983757A CN 110889327 B CN110889327 B CN 110889327B
- Authority
- CN
- China
- Prior art keywords
- thermal infrared
- image
- temperature
- pixel
- images
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 33
- 239000010865 sewage Substances 0.000 title claims abstract description 27
- 238000001514 detection method Methods 0.000 title claims abstract description 16
- 230000011218 segmentation Effects 0.000 claims abstract description 11
- 238000003384 imaging method Methods 0.000 claims abstract description 10
- 238000005192 partition Methods 0.000 claims abstract description 3
- 238000000034 method Methods 0.000 claims description 25
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 230000000750 progressive effect Effects 0.000 claims description 3
- 238000010187 selection method Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims 1
- 238000011835 investigation Methods 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract description 5
- 230000002159 abnormal effect Effects 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 8
- 238000012544 monitoring process Methods 0.000 description 4
- 230000005855 radiation Effects 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 3
- 239000010842 industrial wastewater Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 239000008239 natural water Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000005067 remediation Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
- G06V10/464—Salient features, e.g. scale invariant feature transforms [SIFT] using a plurality of salient features, e.g. bag-of-words [BoW] representations
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Multimedia (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Remote Sensing (AREA)
- Astronomy & Astrophysics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an intelligent detection method for a sewage outlet around a water area based on a thermal infrared image, which comprises the steps of constructing an unmanned aerial vehicle-mounted imaging equipment system and collecting thermal infrared image data; extracting homonymous feature points in an overlapping area between the thermal infrared images; calculating splicing parameters of the large image, and carrying out geographic parameter registration with the existing high-definition map; calculating the temperature estimated value of each pixel of the whole image, and carrying out threshold segmentation on the thermal infrared spliced image according to the pixel temperature value to extract abnormal pixel areas of the temperature field; calculating average temperature of pixels in each partition area, and extracting water pixel areas with temperature difference values greater than a certain threshold value in the water area; and positioning the extracted drain outlet pixels to a geographic coordinate system to obtain the geographic position of the drain outlet. The invention has wide observation range, accurate positioning precision and high data processing automation efficiency, and can be applied to the potential sewage drain investigation operation of the periphery of various water areas.
Description
Technical Field
The invention belongs to the technical field of environmental monitoring, and particularly relates to an intelligent detection method for a sewage outlet around a water area based on a thermal infrared image.
Background
The rapid monitoring of the water quality in natural waters is of great importance for the protection of water resources and related land resources. Nowadays, the discharge of industrial wastewater and domestic sewage is a major cause of water pollution. Some drain openings which do not meet the requirements of laws and regulations are usually hidden, and the drain period is unstable, such as avoiding daytime emission, which increases the difficulty of investigation and cleaning. In order to meet the requirement of protecting the water environment, the environmental protection department needs to be able to check illegal and unreasonable sewage outlets, and further provide supporting data for the remediation work.
The existing drain outlet detection method mainly relies on net pulling type on-site manual investigation, and staff walk or take a monitoring ship to search along the front of the bank. The method has the following disadvantages: (1) The manual searching has low working efficiency and large workload for detection and investigation in a large range; (2) For the condition that the sewage outlet is hidden under water or in weeds, the sewage outlet is difficult to find in time and easy to miss; (3) In the working environment along the coastal beach, the working platform has a certain personal risk for workers.
In addition, part of related works utilize satellite remote sensing images to detect sewage outlets, workers find potential positions of the sewage outlets on the satellite images through a visual interpretation method, and the detection is carried out by combining field comparison. However, the method relying on satellite remote sensing images has some problems: (1) The satellite images have certain timeliness, the data updating period is slow, and the monitoring is not timely; (2) The resolution ratio of the satellite remote sensing image is usually not high, the morphological characteristics of the ground object cannot be accurately reflected by the low-resolution image, and misjudgment and omission judgment situations can occur; (3) High resolution satellite images, such as sub-meter level data, are often expensive, increasing the cost of the operation.
Disclosure of Invention
The invention aims to: the intelligent detection method for the sewage outlet around the water area based on the thermal infrared image, which is provided by the invention, has the advantages of flexible taking-off and landing operation, wide observation range, accurate positioning precision and high data processing automation efficiency, and can be applied to the investigation operation of potential sewage outlets around various water areas.
The invention comprises the following steps: the invention discloses an intelligent detection method for a sewage outlet around a water area based on a thermal infrared image, which comprises the following steps:
(1) Setting up an unmanned aerial vehicle-mounted imaging equipment system, and calibrating camera parameters of a thermal infrared imager on the ground by using calibration equipment;
(2) According to the pre-collected flight environment information, a flight plan is arranged, a flight task is executed, and thermal infrared image data are collected;
(3) Extracting homonymous feature points between the thermal infrared images with the overlapping areas;
(4) Calculating splicing parameters of the large images, and carrying out image registration splicing of the large areas;
(5) Geographic parameters are registered, so that unmanned aerial vehicle-mounted data are converted into a geographic coordinate system frame where an existing high-definition map is located;
(6) Calculating the temperature estimated value of each pixel for the spliced large image;
(7) Threshold segmentation is carried out on the large image after the splicing is completed according to the temperature value of the pixels;
(8) Calculating average temperature of pixels in each partition area, and extracting a water body pixel area with a temperature difference value greater than a certain threshold value in the water area, wherein the water body pixel area is the extracted candidate drain outlet position area;
(9) And positioning the extracted drain outlet pixels to a geographic coordinate system to obtain the geographic position of the drain outlet, and carrying out multiplication operation on the pixel number and the resolution according to the pixel number statistics to obtain an estimated value of the primary influence range of the drain outlet.
Further, the onboard imaging device system in the step (1) comprises a thermal infrared imager and a positioning device, and the time stamp triggering the imager to take a picture is bound with the positioning data.
Further, the thermal infrared image acquisition process in the step (1) is as follows:
taking images according to the frequency between 3 frames and 30 frames per second, obtaining a thermal infrared image data sequence of an observation area, and storing the thermal infrared image data sequence in an onboard memory card;
the following conditions are satisfied for the settings between the thermal infrared image acquisition intervals t:
wherein->
The field angle of the thermal infrared images is v, the flight speed of the unmanned aerial vehicle is h, the flight height is h, and the overlapping degree between two adjacent thermal infrared images is not less than 30%.
Further, the step (4) includes the steps of:
(41) The image is projected onto the original cylinder surface by the following formula:
where f is the focal length of the image, x c And y c Is the center pixel coordinates of the image, (x, y) and (x ', y') are the coordinates of the pixels before and after projection, respectively;
(42) According to the computer vision theory, for two images shot by a camera, homogeneous coordinates of matching points can be associated by a homography matrix H, and for a pair of corresponding matching points p= [ x ] p ,y p ,1] T And q= [ x q ,y q ,1] T The relation is: p=hq;
(43) And splicing new images into the images spliced in advance one by a progressive projection conversion method, so that a large global spliced image is finally obtained.
Further, the step (5) includes the steps of:
(51) The method comprises the steps of utilizing the existing high-definition map, such as a topographic map or satellite images of an observation area, adopting an interactive point selection method to register and splice the thermal infrared large images and the corresponding matching points with the same name selected on the existing high-definition map;
(52) And a homography matrix calculation method is used again to obtain a conversion relation of the spliced thermal infrared large image to the existing high-definition map, so that unmanned aerial vehicle-mounted data are converted into the geographic coordinate system frame where the existing high-definition map is located.
Further, the step (7) includes the steps of:
(71) Constructing a temperature histogram of a large image, wherein the histogram has a plurality of peaks, and finding out a threshold value of temperature segmentation by adopting a multi-parabolic fitting method;
(72) Performing linear fitting by adopting ground actually measured individual temperature values and brightness values on the image, and establishing a fitting equation of the brightness values and the temperature values: t (T) p ＝aI p +b, where T p A temperature value indicating the p position of the pixel point, I p The image brightness value of the pixel point p is represented, and a and b represent linear fitting parameters obtained by fitting the ground measured temperature value and the brightness value of the corresponding pixel selected on the thermal infrared mosaic large image.
The beneficial effects are that: compared with the prior art, the invention has the beneficial effects that: 1. the unmanned aerial vehicle is portable, so that the unmanned aerial vehicle can flexibly carry out operation, the operation cost is reduced for sewage outlet detection operation, and the time efficiency is improved; 2. the radiation inversion characteristic of thermal infrared remote sensing is utilized, so that the detection capability of a hidden sewage outlet is improved; 3. the detected drain outlet image pixel data are converted into position coordinate data by combining the positioning data and the registration method, so that accurate drain outlet position information can be provided; 4. by using the pattern recognition calculation method, the invention can divide the pixels of different types of water bodies, thereby calculating the initial diffusion range area of the discharged sewage.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a raw thermal infrared image obtained by an onboard imaging device system;
FIG. 3 is a graph of matching correspondence between feature points of the same name extracted from two images in the image stitching process;
FIG. 4 is a thermal infrared mosaic large map obtained by stitching thermal infrared images of the entire observation area according to the calculated registration parameters;
FIG. 5 is a temperature map obtained by converting luminance values to temperature values;
FIG. 6 is a schematic diagram of histogram threshold segmentation based on temperature values;
FIG. 7 is a view of candidate drain location areas extracted through threshold segmentation and comparative analysis of each area.
Detailed Description
The technical scheme adopted by the invention is as follows: a thermal infrared image processing system based on unmanned aerial vehicle can detect drain outlet information around a water area, and the system flow is shown in figure 1, and comprises the following specific steps:
step one: and constructing an unmanned aerial vehicle imaging equipment system. A rotor wing type or fixed wing unmanned aerial vehicle is used as a flight carrier, a thermal infrared imager is equipped, and a damping ball and a triaxial stable tripod head for the imager are linked to the carrier. The shock-absorbing ball and the triaxial stabilized cradle head are provided by an unmanned aerial vehicle provider or purchased by themselves. Then, calibrating camera parameters of the imager on the ground, and obtaining the parameters in the camera of the thermal infrared image, including the focal length f and the central pixel x, by using a checkerboard calibration method c And y c And lens distortion parameters. Meanwhile, the unmanned aerial vehicle is provided with a global positioning system positioning device (such as a GPS or Beidou positioning module). Binding a time stamp triggering the imaging device to take a picture with positioning data, providing positioning parameters of imaging time of the image, and storing a thermal infrared image taken in the flight process by using a built-in memory card of the imaging device. The thermal infrared image shot by the unmanned aerial vehicle is shown in fig. 2, and a scene which can only reflect a small-range area can be observed by a single thermal infrared image without registration and splicing; in addition, a certain degree of overlap between adjacent images can be seen, which provides a necessary basis for homonymous point searching for registration stitching.
Step two: and (3) researching the environmental information acquired by the data, preparing the route planning, performing unmanned aerial vehicle flight operation, executing flight tasks and acquiring thermal infrared image data.
The method comprises the steps of collecting weather conditions and terrain information in advance, avoiding data acquisition in time under severe weather conditions, avoiding potential dangerous objects which can cause flight safety to an unmanned aerial vehicle, determining route planning information and providing necessary preparation information for unmanned aerial vehicle flight outside industry data acquisition. The unmanned aerial vehicle carrying equipment can cover 20 square kilometers once in flight, and the spatial resolution can be controlled between 5 cm and 10 cm.
And (3) starting field collection, carrying out flight by using unmanned aerial vehicle carrying equipment according to a route planning path, photographing images according to the frequency of 3 frames to 30 frames per second, wherein the resolution of the images depends on a supplier of an imager, and the image drawing amplitude above 640 multiplied by 480 pixels in width and height can be obtained. And obtaining a thermal infrared image data sequence of the observation area, and storing the thermal infrared image data sequence in an onboard memory card. According to the first step, the onboard positioning data associated with the image is recorded in the memory card.
To ensure that there is more than 50% overlap between two adjacent thermal infrared images, the field angle of the thermal infrared images is known
The following conditions are satisfied by the settings among the flight speed v, the flight height h and the thermal infrared image acquisition interval t of the unmanned aerial vehicle:
the overlap between two adjacent thermal infrared images may be set to be greater than 50%, and not less than 30% is recommended, otherwise image stitching of the global observation area is affected.
Step three: and extracting homonymous feature points between the thermal infrared images with overlapping. The acquisition of image data is continuous and requires registration stitching of the thermal infrared images within the field of view in order to obtain a complete large image of the field of view. According to step one, the imager and global positioning data have been time-stamp synchronized, and the downloaded image has on-board positioning parameters provided by the positioning module, the coordinate values being the initial position of the image. In the overlapping area between the adjacent images, according to the feature matching technology in the image processing method, the homonymous pixels between the overlapping images can be found by using feature extraction such as SIFT, SURF, harris, FAST and a feature matching method combined with correlation coefficient calculation, wherein false matching corresponding points are extracted by combining a random consistency test RANSAC (Random Sample Consensus) method, and an automatic feature point matching method can be replaced by manually interacted selected coordinate pixel points. As shown in fig. 3, a matching correspondence relationship of feature points with the same name in a pair of images is given, where pixels connected by a line are feature points corresponding to matching.
Step four: and calculating splicing parameters of the large images, and carrying out registration splicing on the thermal infrared images of the whole observation area to obtain the thermal infrared spliced large images. First, to prevent the stitched image from being greatly distorted, the image is projected onto the original cylinder surface by the following formula:
wherein, as in step one, f is the focal length of the image, x c And y c Is the center pixel coordinate of the image. (x, y) and (x ', y') are coordinates of pixels before projection and after projection, respectively, and projection calculation is performed pixel by pixel.
According to the computer vision theory, for two images taken by a camera, the homogeneous coordinates of the matching points can be correlated by a homography matrix H, so that for a corresponding matching point p= [ x p ,y p ,1] T And q= [ x q ,y q ,1] T The relation is: p=hq.
Homography matrix H is a matrix of 3 rows and 3 columns,
when the overlapping area has more than 4 groups of homonymous matching points, a homography matrix H can be calculated by using a Direct Linear Transformation (DLT) method. The homography conversion matrix between every two is adopted, new images are spliced into the images spliced in advance one by a progressive projection conversion method, and therefore a large global spliced image is finally obtained. And according to the calculated registration parameters, splicing the thermal infrared images of the whole observation area to obtain a thermal infrared spliced large image, wherein each pixel records a brightness value, and the spliced large image is shown in fig. 4.
Step five: and (3) geographic parameter registration, namely converting the data of the unmanned aerial vehicle into the geographic coordinate system frame where the existing high-definition map is positioned. After the large images are spliced, an existing high-definition map, such as a topographic map or a satellite image of an observation area, is utilized, an interactive point selection method is adopted, matching points corresponding to the same name are selected on the spliced thermal infrared large images and the existing geographic reference high-definition map in registration, and then a homography matrix calculation method is used again to obtain a conversion relation of mapping the spliced thermal infrared large images to the existing geographic reference map, so that unmanned aerial vehicle data are converted under a geographic coordinate system frame where the existing map is located. Thus, each pixel of the registered stitched thermal infrared large image has a geographic location coordinate attribute, while each pixel corresponds to a spatial range of the earth's surface, and the resolution mathematical symbol is denoted as s.
Step six: and calculating the temperature estimated value of each pixel for the large image after the splicing is completed. The emissivity of a water body indicates the ability of the water body to radiate electromagnetic waves outwards in a physical sense, and a temperature difference exists between industrial wastewater and domestic sewage, which are unavoidable, and a natural water body into which the industrial wastewater and domestic sewage are discharged, so that the emissivity is reflected on the electromagnetic wave radiation ability. The areas of different temperature response exhibit different brightness values on the image.
Before the brightness value is converted to the temperature value, the brightness value smoothing processing is carried out on the whole image by utilizing a Gaussian smoothing template in the image processing technology, so that the influence caused by observation noise is effectively reduced. The energy received by the thermal infrared sensor mainly comprises three parts: ground surface heat radiation after the atmospheric weakening; earth surface reflection of atmospheric downlink radiation; the atmosphere radiates upward. The first method focuses mainly on the relative temperature difference, not the absolute temperature value, for the following two reasons; the second unmanned aerial vehicle fly height is usually at a navigation height of hundreds of meters, and the task execution time is selected under good meteorological conditions, and the atmospheric environment is relatively stable, so that the atmospheric influence in the whole observation area can be summarized and analyzed by a constant value. Therefore, the method adopts a method of carrying out linear fitting on the ground actually measured individual temperature value and the brightness value on the image, establishes a fitting equation of the brightness value and the temperature value, and realizes calculation from the brightness value to the temperature value by taking the equation as a basis. The linear fit equation is in the form of:
T p ＝aI p +b
wherein T is p A temperature value indicating the p position of the pixel point, I p The image brightness value of the pixel point p is represented, and a and b represent linear conversion parameters of linear fitting established by the ground measured temperature value and the brightness value on the thermal infrared mosaic large graph correspondingly selected. The solution of the linear fitting parameters can be easily calculated directly by many calculation software such as ORIGIN or Matlab. After the fitting parameters are included, each pixel of the whole image is calculated according to a linear fitting equation, and the temperature value of each pixel is obtained. As shown in fig. 5, the stitched large image becomes a temperature-displayed large image, and at this time, the value recorded by each pixel is a temperature value.
Step seven: and (3) segmenting the thermal infrared spliced image based on the segmented threshold value of the temperature value, and extracting a temperature field abnormal pixel region. A contaminated water body area may be understood as a target area, and an uncontaminated area is defined as a background area. The temperature values of pixels in each region are relatively consistent, the temperature values of the target region and the background region are differentiated to a certain extent, threshold segmentation can be performed by using a histogram statistics method based on the temperature values, and the background region and the target region are segmented. A temperature histogram of a large image is constructed, as shown in fig. 6, which typically has a plurality of peaks. And (5) a multi-parabolic fitting method is adopted to find the threshold value of the brightness segmentation. Pixels corresponding to temperature values within the threshold interval are divided into one region.
Step eight: and (3) combining the results of the step six and the step seven, and analyzing the temperature characteristics in each divided area by taking the divided area of the step seven as a constraint. First, an average temperature value within the region is calculated. And then, comparing the temperatures of the adjacent areas, and extracting independent areas with the temperature difference value in the areas being larger or smaller than that of all the adjacent areas, wherein the areas are the extracted candidate drain outlet position areas. As shown in FIG. 7, after the region segmentation and region comparison analysis, the lower right corner of the image has a region temperature that is significantly different from the surrounding region temperature, as indicated by the arrow, highlighted by darkening. Therefore, the area is extracted as a candidate drain area, and the verification confirmation of the candidate is waited.
Step nine: according to the fifth step, the position and resolution information of each pixel are available, and the extracted candidate drain outlet pixels can be positioned into a geographic coordinate system, so that the geographic position coordinates of the candidate drain outlets are output. And according to the statistics of the number of pixels in the area after threshold segmentation, the area estimation value of the primary influence range of the candidate sewage outlet on the surrounding water area is obtained by multiplying the number of pixels and the spatial resolution of the pixels.
Step ten: the ground staff adopts the water quality sampler, the multi-parameter water quality tester, the turbidity tester, the non-dispersion infrared oil tester and other instruments and equipment, and according to the positioning result, the site judgment is carried out on the candidate sewage outlets, and the existence of the sewage outlets is detected and verified.
Claims (5)
1. The intelligent detection method for the sewage outlet around the water area based on the thermal infrared image is characterized by comprising the following steps of:
(1) Setting up an unmanned aerial vehicle-mounted imaging equipment system, and calibrating camera parameters of a thermal infrared imager on the ground by using calibration equipment;
(2) According to the pre-collected flight environment information, a flight plan is arranged, a flight task is executed, and thermal infrared image data are collected;
(3) Extracting homonymous feature points between the thermal infrared images with the overlapping areas;
(4) Calculating splicing parameters of the large images, and carrying out image registration splicing of the large areas;
(5) Geographic parameters are registered, so that unmanned aerial vehicle-mounted data are converted into a geographic coordinate system frame where an existing high-definition map is located;
(6) Calculating the temperature estimated value of each pixel for the spliced large image;
(7) Threshold segmentation is carried out on the large image after the splicing is completed according to the temperature value of the pixels;
(8) Calculating average temperature of pixels in each partition area, and extracting a water body pixel area with a temperature difference value greater than a certain threshold value in the water area, wherein the water body pixel area is the extracted candidate drain outlet position area;
(9) Positioning the extracted drain outlet pixels to a geographic coordinate system to obtain the geographic position of the drain outlet, and carrying out multiplication operation on the pixel number and the resolution according to the pixel number statistics to obtain an estimated value of the primary influence range of the drain outlet;
the step (4) comprises the following steps:
(41) The image is projected onto the original cylinder surface by the following formula:
where f is the focal length of the image, x c And y c Is the center pixel coordinates of the image, (x, y) and (x ', y') are the coordinates of the pixels before and after projection, respectively;
(42) According to the computer vision theory, for two images shot by a camera, homogeneous coordinates of matching points can be associated by a homography matrix H, and for a pair of corresponding matching points p= [ x ] p ,y p ,1] T And q= [ x q ,y q ,1] T The relation is: p=hq;
(43) And splicing new images into the images spliced in advance one by a progressive projection conversion method, so that a large global spliced image is finally obtained.
2. The intelligent detection method for the sewage outlet around the water area based on the thermal infrared image according to claim 1, wherein the onboard imaging equipment system in the step (1) comprises a thermal infrared imager and a positioning device, and a time stamp triggering the imager to take a picture is bound with positioning data.
3. The intelligent detection method for the sewage outlet around the water area based on the thermal infrared image as set forth in claim 1, wherein the thermal infrared image acquisition process in the step (1) is as follows:
taking images according to the frequency between 3 frames and 30 frames per second, obtaining a thermal infrared image data sequence of an observation area, and storing the thermal infrared image data sequence in an onboard memory card;
the following conditions are satisfied for the settings between the thermal infrared image acquisition intervals t:
wherein->
The field angle of the thermal infrared images is v, the flight speed of the unmanned aerial vehicle is h, the flight height is h, and the overlapping degree between two adjacent thermal infrared images is not less than 30%.
4. The intelligent detection method for the sewage outlet around the water area based on the thermal infrared image according to claim 1, wherein the step (5) comprises the following steps:
(51) The existing high-definition map is utilized, an interactive point selection method is adopted, and corresponding matching points with the same name are selected on the registered and spliced thermal infrared large image and the existing high-definition map;
(52) And a homography matrix calculation method is used again to obtain a conversion relation of the spliced thermal infrared large image to the existing high-definition map, so that unmanned aerial vehicle-mounted data are converted into the geographic coordinate system frame where the existing high-definition map is located.
5. The intelligent detection method for the sewage outlet around the water area based on the thermal infrared image according to claim 1, wherein the step (7) comprises the following steps:
(71) Constructing a temperature histogram of a large image, wherein the histogram has a plurality of peaks, and finding out a threshold value of temperature segmentation by adopting a multi-parabolic fitting method;
(72) Performing linear fitting by adopting ground actually measured individual temperature values and brightness values on the image, and establishing a fitting equation of the brightness values and the temperature values: t (T) p ＝aI p +b, where T p A temperature value indicating the p position of the pixel point, I p The brightness value of the image of the pixel point p is represented, a and b represent the brightness value simulation of the corresponding pixel selected on the large thermal infrared spliced graph through the ground measured temperature valueAnd (5) combining the obtained linear fitting parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910983757.XA CN110889327B (en) | 2019-10-16 | 2019-10-16 | Intelligent detection method for sewage outlet around water area based on thermal infrared image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910983757.XA CN110889327B (en) | 2019-10-16 | 2019-10-16 | Intelligent detection method for sewage outlet around water area based on thermal infrared image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110889327A CN110889327A (en) | 2020-03-17 |
| CN110889327B true CN110889327B (en) | 2023-05-26 |
Family
ID=69746220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910983757.XA Active CN110889327B (en) | 2019-10-16 | 2019-10-16 | Intelligent detection method for sewage outlet around water area based on thermal infrared image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110889327B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112485329B (en) * | 2020-11-27 | 2024-01-26 | 重庆商勤科技有限公司 | Method, device and system for detecting sewage outlet based on combination of thermal imaging and ultrasound |
| CN112987751B (en) * | 2021-03-18 | 2022-10-11 | 中冶华天工程技术有限公司 | System and method for quickly detecting hidden sewage draining outlet in automatic cruising mode |
| CN113011368B (en) * | 2021-03-31 | 2024-04-30 | 神华神东煤炭集团有限责任公司 | Mine exploitation surface conduction goaf crack identification method and electronic equipment |
| CN113786134B (en) * | 2021-09-27 | 2023-02-03 | 汤恩智能科技(上海)有限公司 | Cleaning method, program product, readable medium and electronic device |
| CN114359731A (en) * | 2022-01-05 | 2022-04-15 | 浙江中科空间信息技术应用研发中心 | Sewage hidden discharge detection traceability method based on unmanned aerial vehicle thermal infrared remote sensing |
| CN114371268B (en) * | 2022-01-10 | 2024-05-14 | 江苏大学 | Suspension type self-balancing self-cruising water quality on-line monitoring device, monitoring and evaluating method |
| CN114515663B (en) * | 2022-01-11 | 2023-01-31 | 北京市农林科学院信息技术研究中心 | Mushroom spraying control method, device and system |
| CN116612069A (en) * | 2023-04-07 | 2023-08-18 | 中国铁塔股份有限公司黑龙江省分公司 | Water pollution monitoring method, system and equipment based on spectrum and thermal infrared image |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485655A (en) * | 2015-09-01 | 2017-03-08 | 张长隆 | A kind of taken photo by plane map generation system and method based on quadrotor |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102088569B (en) * | 2010-10-13 | 2013-06-19 | 首都师范大学 | Sequence image splicing method and system of low-altitude unmanned vehicle |
| CN107843939B (en) * | 2017-10-24 | 2020-03-10 | 防灾科技学院 | Coal fire identification method based on unmanned aerial vehicle thermal infrared image |
| CN109523544B (en) * | 2018-11-26 | 2021-02-26 | 陕西汉通建设工程质量检测有限公司 | Building outer wall quality defect detection system and method thereof |
| CN109978862B (en) * | 2019-03-27 | 2021-04-27 | 北京邮电大学 | Air pollution estimation method based on satellite image |
-
2019
- 2019-10-16 CN CN201910983757.XA patent/CN110889327B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485655A (en) * | 2015-09-01 | 2017-03-08 | 张长隆 | A kind of taken photo by plane map generation system and method based on quadrotor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110889327A (en) | 2020-03-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110889327B (en) | Intelligent detection method for sewage outlet around water area based on thermal infrared image | |
| WO2021093283A1 (en) | Sea surface small-area oil spill region detection system and detection method based on multi-sensing fusion | |
| Bao et al. | Monitoring of beach litter by automatic interpretation of unmanned aerial vehicle images using the segmentation threshold method | |
| Puniach et al. | Application of UAV-based orthomosaics for determination of horizontal displacement caused by underground mining | |
| CN103218787B (en) | Multi-source heterogeneous remote sensing image reference mark automatic acquiring method | |
| Gance et al. | Target Detection and Tracking of moving objects for characterizing landslide displacements from time-lapse terrestrial optical images | |
| CN110703244B (en) | Method and device for identifying urban water body based on remote sensing data | |
| Sheng et al. | Automated georeferencing and orthorectification of Amazon basin-wide SAR mosaics using SRTM DEM data | |
| CN112308913B (en) | Vehicle positioning method and device based on vision and vehicle-mounted terminal | |
| KR101874498B1 (en) | System and Method for Aerial Photogrammetry of Ground Control Point for Space Information Acquisition based on Unmanned Aerial Vehicle System | |
| Gerhardinger et al. | Vehicles detection from very high resolution satellite imagery | |
| CN105527969A (en) | Mountain vegetation vertical zone investigation monitoring method based on UAV | |
| CN110988909A (en) | TLS-based vegetation coverage determination method for sandy land vegetation in alpine and fragile areas | |
| CN110413002B (en) | Unmanned aerial vehicle remote sensing information acquisition method and device | |
| CN111556157A (en) | Crop distribution monitoring method, equipment, storage medium and device | |
| Bektas Balcik et al. | Determination of magnitude and direction of land use/land cover changes in Terkos Water Basin, Istanbul | |
| Taherzadeh et al. | Using hyperspectral remote sensing data in urban mapping over Kuala Lumpur | |
| CN117392557A (en) | Public space digital treatment method for village plain | |
| CN111199557A (en) | Quantitative analysis method and system for decay of remote sensor | |
| Hashim et al. | Geometric and radiometric evaluation of RazakSAT medium-sized aperture camera data | |
| Misra et al. | An approach for generation of multi temporal co-registered optical remote sensing images from Resourcesat-2/2A sensors | |
| CN111489398B (en) | Imaging equipment calibration method and device | |
| Piermattei et al. | Analysis of glacial and periglacial processes using structure from motion. | |
| Asghar | Landslide mapping from analysis of UAV-SFM point clouds | |
| CN117994678B (en) | Positioning method and system for natural resource remote sensing mapping image |
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 |