CN112461209A - Double-light fusion system of visible light and infrared light - Google Patents
Double-light fusion system of visible light and infrared light Download PDFInfo
- Publication number
- CN112461209A CN112461209A CN202110135777.9A CN202110135777A CN112461209A CN 112461209 A CN112461209 A CN 112461209A CN 202110135777 A CN202110135777 A CN 202110135777A CN 112461209 A CN112461209 A CN 112461209A
- Authority
- CN
- China
- Prior art keywords
- building
- data
- rural
- infrared
- light
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/02—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
- G01C11/06—Interpretation of pictures by comparison of two or more pictures of the same area
- G01C11/08—Interpretation of pictures by comparison of two or more pictures of the same area the pictures not being supported in the same relative position as when they were taken
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/04—Texture mapping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Software Systems (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
A double-light fusion system of visible light and infrared light is applied to an unmanned aerial vehicle and a modeling terminal remotely connected with the unmanned aerial vehicle; the modeling terminal sets a first time axis and a second time axis to acquire data of the residential building with the courtyard; collecting the stored home data for the time segments of the first timeline includes: the infrared shooting subunit carries out data acquisition on the infrared image of the residence to obtain building outline data, three-dimensional vertex three-dimensional data of the residence building and four anchor point elements of the residence building; the collecting and storing of the residential building data in the time period corresponding to the second time axis and the first time axis comprises: the method comprises the steps that a texture map of a residential building is shot by a visible light shooting subunit, and courtyard spectrum data in a rectangle formed by four anchor point elements are obtained; and fusing the texture mapping of the time period of the second time axis with the three-dimensional vertex stereogram of the time period corresponding to the first time axis to obtain the real three-dimensional stereogram of the residential building, thereby providing an accurate data base for determining the right of the residential building.
Description
Technical Field
The invention relates to the technical field of image shooting by fusing infrared light and visible light, in particular to a visible light and infrared light double-light fusion system for shooting house building images.
Background
In the integral right-confirming registration work of rural houses and lands, the most time-consuming technical link is basic data acquisition. The conventional measurement means mainly adopts a data acquisition mode combining GNSS-RTK and a total station, and the mode has high precision and less omission, but needs a large amount of outdoor measurement operation, has heavy work task, long period and high cost, and has no advantages in regions with scattered villages.
Therefore, the problems of the prior art are to be further improved and developed.
Disclosure of Invention
The object of the invention is: in order to solve the problems in the prior art, the invention aims to provide a visible light and infrared light double-light fusion system, which can perform accurate three-dimensional modeling on rural buildings and provide data support for the affirmation of the rural buildings.
The technical scheme is as follows: in order to solve the technical problem, the technical scheme provides a visible light and infrared light double-light fusion system, which is applied to an unmanned aerial vehicle and a modeling terminal remotely connected with the unmanned aerial vehicle;
the unmanned aerial vehicle comprises a shooting device, wherein the shooting device comprises a forward shooting unit and four inclined shooting units around the forward shooting unit; the positive shooting unit and the inclined shooting unit respectively comprise an infrared shooting subunit and a visible light shooting subunit;
the modeling terminal is provided with a first time axis and a second time axis and controls the unmanned aerial vehicle to acquire data of rural buildings at different time periods;
the collecting and storing rural building data in the time period of the first time axis comprises the following steps: an infrared shooting subunit of the unmanned aerial vehicle acquires infrared images of rural buildings to obtain building contour data, three-dimensional vertex three-dimensional data of the rural buildings and four anchor point elements of the rural buildings;
the rural building data collected and stored in the time period of the second time axis corresponding to the first time axis comprises the following steps: the method comprises the steps that a texture map of a rural building is shot by a visible light shooting sub-unit of an unmanned aerial vehicle, and courtyard spectral data in a rectangle formed by four anchor point elements;
and fusing the texture mapping of the time period of the second time axis with the three-dimensional vertex stereogram of the time period corresponding to the first time axis to obtain the real three-dimensional stereogram of the rural building.
The visible light and infrared light double-light fusion system is characterized in that the unmanned aerial vehicle further comprises a distance measuring device, a positioning device, an image processing device and a control device; the modeling terminal comprises a house three-dimensional vertex model, a real-time modeling unit and a modeling control unit.
The double-light fusion system of visible light and infrared light is characterized in that,
the unmanned aerial vehicle sends the acquired infrared image to a modeling terminal, and the modeling control unit extracts building outline data by using the infrared image;
the modeling terminal stores a house three-dimensional vertex model of the rural building;
a modeling control unit of the modeling terminal selects a corresponding three-dimensional vertex model from the three-dimensional vertex models by utilizing a deep learning algorithm according to building contour data extracted from the infrared image;
and the real-time modeling unit of the modeling terminal improves the three-dimensional vertex model according to the building outline to obtain a three-dimensional vertex stereogram of the building outline corresponding to the infrared image.
The double-light fusion system of the visible light and the infrared light is characterized in that for the rural building with the surrounding wall, the modeling control unit respectively arranges four anchor point elements on four vertexes of the outer edge of the rural building, or arranges the four anchor point elements on four vertexes of the outer edge of the rural building plus the extension distance.
The double-light fusion system of visible light and infrared light, wherein, for rural buildings without enclosing walls, the setting of the modeling control unit to four anchor point elements is as follows: two anchor point elements are determined according to rural buildings without enclosing walls; the other two anchor points are determined by reconstructing a rectangle according to the sum of the areas of 200 square meters and the extended area.
The visible light and infrared light double-light fusion system is characterized in that the modeling terminal sends the geographic position of the anchor point element determined in real time to the unmanned aerial vehicle; after the infrared shooting subunit of the unmanned aerial vehicle obtains the positions of the anchor point elements, the image acquisition resolution ratio in the rectangle formed by the four anchor point elements is higher than the image acquisition resolution ratio outside the rectangle formed by the four anchor point elements.
According to the visible light and infrared light double-light fusion system, on a second time axis, the unmanned aerial vehicle collects visible light images of overlooking and front, back, left and right dimensions of corresponding rural buildings according to received positioning data of the rural buildings and corresponding anchor point elements; the resolution of the acquisition of the visible image within the rectangle made up of the four anchor elements is higher than the resolution of the acquisition of the visible image outside the rectangle made up of the four anchor elements.
The double-light fusion system of the visible light and the infrared light is characterized in that when an image shot/collected by a visible light shooting subunit of the unmanned aerial vehicle is within a rectangle formed by four anchor point elements, the start of an imaging spectrum subunit is triggered.
The visible light and infrared light double-light fusion system is characterized in that the imaging spectrum subunit utilizes laser remote sensing data to acquire accurate data of surface height, namely flatness, in a rectangle formed by four anchor point elements, and sends the acquired surface height data to a modeling terminal to correct a three-dimensional vertex stereogram.
(III) the beneficial effects are as follows: according to the visible light and infrared light double-light fusion system, the three-dimensional vertex stereogram is constructed through the line graph of the rural building collected in the time period of the first time axis, and then the three-dimensional stereogram of the rural building with the anchor point elements is obtained through the collection of the visible light image of the second time axis corresponding to the time period of the first time axis one by one, wherein the three-dimensional stereogram of the rural building is provided with four anchor points, so that an accurate data base is provided for the right determination of the rural building. The unmanned aerial vehicle avoids the problem of entering a home in the homestead measurement through non-contact measurement, simultaneously transfers most of work to three-dimensional modeling and anchor point element positioning, reduces about 90 percent of field work, and finally saves labor and time cost to the maximum extent.
Drawings
FIG. 1 is a functional structure diagram of a dual light fusion system of visible light and infrared light according to the present invention;
FIG. 2 is a schematic diagram of a process for performing dual light fusion of visible light and infrared light according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to preferred embodiments, and more details are set forth in the following description in order to provide a thorough understanding of the present invention, but it is apparent that the present invention can be embodied in many other forms different from the description herein and can be similarly generalized and deduced by those skilled in the art based on the practical application without departing from the spirit of the present invention, and therefore, the scope of the present invention should not be limited by the contents of this detailed embodiment.
The drawings are schematic representations of embodiments of the invention, and it is noted that the drawings are intended only as examples and are not drawn to scale and should not be construed as limiting the true scope of the invention.
A double light fusion system of visible light and infrared light is disclosed, as shown in figure 1, and is applied to an unmanned aerial vehicle and a modeling terminal remotely connected with the unmanned aerial vehicle; the unmanned aerial vehicle comprises a distance measuring device, a positioning device, a shooting device, an image processing device and a control device; the modeling terminal comprises a house three-dimensional vertex model, a real-time modeling unit and a modeling control unit.
The unmanned aerial vehicle is used for shooting rural buildings needing to be authenticated, and the shooting device of the unmanned aerial vehicle comprises a positive shooting unit and four inclined shooting units around the positive shooting unit; the positive shooting unit and the inclined shooting unit respectively comprise an infrared shooting subunit and a visible light shooting subunit. The rural building is mainly a single-storey house and comprises a part of small building with 2-3 floors. The infrared shooting and shooting subunit is used for acquiring a line profile map of the rural building; the visible light shooting and shooting subunit is used for obtaining an overlook of the rural building and visible light images of four dimensions, namely front, back, left and right, as texture maps of the three-dimensional vertex stereogram.
The distance measuring device preferably comprises a laser distance measuring subunit and an imaging spectrum subunit.
According to the invention, the positions of the building and the courtyard can be determined according to the continuity of the ground height by measuring the ground distance through the laser ranging subunit, so that the anchor point element is determined and used for positioning the boundary of the house.
The invention can also determine the anchor point element by the acquired infrared image and by analyzing the continuity of the building outline corresponding to the infrared image.
The visible light and infrared light double-light fusion system can realize real-time modeling of rural buildings.
The modeling terminal of the dual-light fusion system is provided with a first time axis and a second time axis, wherein the time periods correspond to the mutual matching of the acquired data. Preferably, a map of the area to be modeled may be obtained by the modeling control unit, the map comprising positioning locations, preferably GPS positioning data.
The double-light fusion of visible light and infrared light of the invention generally comprises the following steps, as shown in fig. 2:
the modeling terminal is provided with a first time axis and a second time axis and controls the unmanned aerial vehicle to acquire data of rural buildings at different time periods;
the collecting and storing rural building data in the time period of the first time axis comprises the following steps: an infrared shooting subunit of the unmanned aerial vehicle acquires infrared images of rural buildings to obtain building contour data, three-dimensional vertex three-dimensional data of the rural buildings and four anchor point elements of the rural buildings;
the rural building data collected and stored in the time period corresponding to the second time axis and the first time axis comprises the following steps: the method comprises the steps that a texture map of a rural building is shot by a visible light shooting sub-unit of an unmanned aerial vehicle, and courtyard spectral data in a rectangle formed by four anchor point elements;
and fusing the texture mapping of the time period of the second time axis with the three-dimensional vertex stereogram of the time period corresponding to the first time axis to obtain the real three-dimensional stereogram of the rural building.
The first time axis corresponds to an image record shot by the unmanned aerial vehicle infrared shooting subunit and the first time. The modeling control unit of the modeling terminal can be set in a way that the unmanned aerial vehicle utilizes the infrared shooting subunit to carry out infrared shooting on the selected area in the map at the first time, and the line profile of rural buildings in the selected area is obtained according to the shot infrared image. The infrared shooting subunit triggers the distance measuring device of the unmanned aerial vehicle to start when starting shooting.
The modeling control unit of the modeling terminal acquires a map, and sets a first shooting route of the unmanned aerial vehicle according to the performance of the unmanned aerial vehicle, wherein the first shooting route is a block diagram of a street line in the acquired map and marks the blocks divided by the block diagram. The unmanned aerial vehicle shoots a first shooting route, namely the route during blind shooting, in a block partitioned by a block diagram of a street line of a map.
In order to model the rural home base, based on the characteristic that the rural building is not a high-rise building, the flying height of the unmanned aerial vehicle and the distance from the unmanned aerial vehicle to the building need to be fully considered in order to save the performance of the unmanned aerial vehicle during shooting, so that unnecessary shooting pictures can be reduced when the image shot by the unmanned aerial vehicle is a sufficient modeling picture, and the performance of the unmanned aerial vehicle and the modeling efficiency are improved.
When the unmanned aerial vehicle shoots for the first time, the infrared shooting subunit triggers the laser ranging subunit to start. In a first preferred embodiment, when the infrared shooting subunit works, the infrared shooting subunit sends a first trigger signal for starting the laser ranging subunit to the control device, the control device sends the first trigger signal to the laser ranging subunit of the ranging device, and the laser ranging subunit starts according to the received first trigger signal. In a second preferred embodiment, when the infrared shooting subunit works, the infrared shooting subunit sends a first trigger signal for starting the laser ranging subunit to the ranging device, and the laser ranging subunit is started according to the received first trigger signal. In a third preferred embodiment, the control device may send a control instruction for starting operation to the infrared shooting subunit at the same time, and the laser ranging subunit of the ranging device sends a first trigger signal for starting operation, and the laser ranging subunit is started according to the received first trigger signal.
The laser ranging subunit can transmit laser radar scanning signals, and judge the height of the ground and the height of a building by collecting the laser radar scanning signals returned by transmission; and adjusting the flying height of the unmanned aerial vehicle in real time according to the height of the ground and the height of the building.
The unmanned aerial vehicle comprises a forward shooting unit, a top view of a building needs to be acquired, and the flying height of the forward shooting unit is the sum of the height of the building and a top view acquisition distance threshold. According to the real-time height data obtained by the laser ranging subunit, the shooting height of the unmanned aerial vehicle is adjusted in real time, so that the shooting requirement of the top view of the rural building is met. The method is a technical improvement according to the actual situation that the height fluctuation between rural buildings, courtyards and streets has large difference, and the accurate measurement of the terrain height can accurately evaluate the modeling and the actual area measurement of the rural buildings.
The unmanned aerial vehicle utilizes the infrared camera subunit to obtain the infrared image of rural building, can carry out the building profile data of infrared image and draw at the unmanned aerial vehicle is local, also can be for practicing thrift the performance of unmanned aerial vehicle, sends the infrared image that obtains to the terminal of modelling, the control unit that models the terminal utilizes infrared image to carry out the extraction of building profile data. The modeling terminal stores house three-dimensional vertex models of rural buildings, including three-dimensional vertex models of buildings such as a house, a bedroom, a kitchen, a miscellaneous house, a toilet, a livestock shed and the like. The modeling control unit selects a corresponding three-dimensional vertex model from the three-dimensional vertex models by utilizing a depth learning algorithm according to the building contour data extracted from the infrared image; and the modeling control unit improves the three-dimensional vertex model according to the building outline to obtain a three-dimensional vertex stereogram of the building outline corresponding to the infrared image.
The double-light fusion system adopts a transmission method of streaming data to carry out three-dimensional modeling on the rural buildings and provides a data base for the certainty of the rural home base.
Rural homesteads have a common characteristic that all the rural homesteads have courtyards, and the area of the building plus the courtyards is the area of the rural homesteads. The invention carries out preliminary positioning on the courtyard through anchor point elements of the distance measuring subunit so as to give a high-precision picture value of the courtyard exploration.
The positive shooting unit sends the shot infrared image to the modeling terminal, the modeling control unit analyzes the top view of the infrared image obtained by the positive shooting unit in real time, and sets four boundary points, namely anchor point elements, for the rural buildings in the top view according to the buildings in the top view and the enclosing wall intervals between the buildings and rectangles with specified areas.
Preferably, the determination of the anchor point element of the present invention is based on a wire frame diagram of a top view of the infrared image.
The unmanned aerial vehicle can integrally shoot a map area in an overlook mode, and then shoot front, back, left and right infrared images of corresponding rural buildings after anchor point elements are determined, so that the efficiency can be improved, the resolution ratio used for shooting is determined according to the anchor point elements, high-quality pictures can be obtained, and the performance of the unmanned aerial vehicle can be saved.
For rural buildings with enclosing walls, the modeling control unit respectively sets four anchor point elements on four vertexes of the outer edge of the rural building (including the area of the rural building plus the courtyard), or sets four anchor point elements on the outer edge of the rural building plus four vertexes of the extension distance. The extended distance can be a redundant distance range, and is not limited, so that various possible problems of rural buildings in the right-confirming process are fully considered, and sufficient data are provided for accurate right-confirming.
For an open rural building without a fence but with only a building, the invention determines two vertexes by the outer edge of the building house, and determines four anchor point elements for the open rural building according to the maximum value of the area of the rural building. The statutory rural building can not exceed 200 square meters, the invention can arrange the anchor point elements on a rectangle formed by the statutory 200 square meters plus the extension area, two anchor point elements of the rectangle are determined according to the existing building, and the other two anchor points are determined by reconstructing the rectangle according to the area of the statutory 200 square meters plus the extension area. Therefore, the diversity of rural buildings can be fully considered, and a sufficient data base is provided for later right confirmation.
The modeling terminal sends the geographical location (including the GPS location) of the anchor element determined in real-time to the drone. After the infrared shooting subunit of the unmanned aerial vehicle obtains the position values of the anchor point elements, the image acquisition resolution ratio within the rectangle formed by the four anchor point elements is higher than the image acquisition resolution ratio outside the rectangle formed by the four anchor point elements.
The image processing apparatus of the present invention is based on: the geographic positions of the four anchor point elements, including the GPS position given by the positioning device; the laser ranging subunit measures the height of the earth surface in real time; and controlling the inclination angles between the four inclined shooting units and the positive shooting unit in real time, so that the inclined shooting units can shoot texture maps at four angles of the front, the rear, the left and the right of the rural building at the highest position.
The image processing device further controls the infrared shooting route of the unmanned aerial vehicle to be a rectangle formed by surrounding the four anchor point elements, so that the time period on the first time axis is ensured to be in one-to-one correspondence with the rural buildings formed by the corresponding four anchor point elements.
The method adopts the first time axis and the second time axis to acquire images of the rural buildings twice, and performs image fusion after the second time axis is acquired to obtain the final three-dimensional vertex stereogram of the rural buildings.
According to the invention, the first time axis is used for acquiring the data of the contour of the rural building by using the infrared shooting subunit of the unmanned aerial vehicle, so that the first time axis can be in dark time such as morning or evening, the unmanned aerial vehicle is prevented from being disturbed to obtain the contour of the rural building, and a three-dimensional vertex stereogram of the rural building is completed; and then four anchor point elements of the rural buildings are obtained through image analysis of the top view, and the geographic positions (including the GPS positions) of the anchor point elements correspond to the designated rural buildings.
The infrared image of the rural building and the three-dimensional vertex stereo data of the rural building correspond to time periods on a first time axis, namely different time periods of the first time axis correspond to different rural building data. And after all data or part of data on the first time axis are acquired, part of data comprises a plurality of complete rural building data. And when the second time axis meets the light condition acquired by the texture mapping, the modeling terminal starts the visible light image acquisition of the second time axis according to the GPS data corresponding to the time period on the first time axis, namely the data of the rural buildings acquired on the first time axis.
And the modeling terminal takes the GPS data of different time periods and the corresponding four anchor point elements as a group of data according to the sequence on the first time axis and sequentially sends the group of data to the unmanned aerial vehicle. Unmanned aerial vehicle and the unmanned aerial vehicle that infrared image shot can be same unmanned aerial vehicle, also can be different unmanned aerial vehicles, do not do the restriction here.
The unmanned aerial vehicle overlooks corresponding rural buildings and collects visible light images of four dimensions, namely front, back, left and right according to received positioning data of the rural buildings, including GPS data and corresponding anchor point elements. According to the determination of the four anchor point elements, the acquisition resolution of the visible light image in the rectangle formed by the four anchor point elements is higher than that of the visible light image outside the rectangle formed by the four anchor point elements. And when the position of the unmanned aerial vehicle and the image of the visible light shooting subunit are within a rectangle formed by the four anchor point elements, triggering the starting of the imaging spectrum subunit. The imaging spectrum subunit utilizes laser remote sensing data to acquire the surface height, namely the accurate data of flatness, in a rectangle formed by four anchor point elements, and sends the acquired surface height data to a modeling terminal to correct the three-dimensional vertex stereogram.
According to the invention, data storage is carried out on the second time axis and the time period corresponding to the first time axis, namely, the first time period of the second time axis and the first time period of the first time axis are data collected from the same rural building. The infrared light and the visible light images are fused according to the time axis, so that the troubles of image classification and matching are eliminated, the operation is easier, the accuracy is higher, and the data processing efficiency is higher.
The second time axis collects texture maps of rural buildings using a visible light shooting and shooting sub-unit of the unmanned aerial vehicle and accurate courtyard spectral height data in a rectangle formed by four anchor point elements. And the data acquisition map of the second time axis takes the rural buildings and the four anchor point elements determined by the first time axis as the standard, and sequentially acquires the images of the visible light according to the acquisition sequence of the first time axis to different rural buildings.
According to the method, the vertex data of the three-dimensional stereogram are corrected according to the courtyard spectral data (namely courtyard height data) in sequence according to the time periods corresponding to the first time axis and the second time axis, and then the second time texture mapping is fused with the three-dimensional vertex stereogram of the first time axis to obtain the real three-dimensional stereogram of the rural building.
The modeling terminal constructs a three-dimensional vertex stereogram through a line graph of a rural building acquired in a time period of a first time axis, and acquires visible light images of a second time axis in one-to-one correspondence with the time period of the first time axis, wherein the second time of the visible light images acquired by the second time axis is different from the first time of the infrared images acquired by the first time axis in whole or in part, and the brightness of the second time needs to meet a threshold value so as to acquire visible images with better visual effects.
According to the invention, the second shooting route of the visible light image is acquired by the second time axis, and the second shooting route is determined for the rural building sequence corresponding to the time period of the first time axis, namely the rural building sequence stored at the first time. The method obtains the three-dimensional stereo map of the rural building with the anchor point elements, the three-dimensional stereo map of the rural building has four anchor points, and an accurate data basis is provided for the right determination of the rural building. The unmanned aerial vehicle avoids the problem of entering a home in the homestead measurement through non-contact measurement, simultaneously transfers most of work to three-dimensional modeling and anchor point element positioning, reduces about 90 percent of field work, and finally saves labor and time cost to the maximum extent.
The above description is provided for the purpose of illustrating the preferred embodiments of the present invention and will assist those skilled in the art in more fully understanding the technical solutions of the present invention. However, these examples are merely illustrative, and the embodiments of the present invention are not to be considered as being limited to the description of these examples. For those skilled in the art to which the invention pertains, several simple deductions and changes can be made without departing from the inventive concept, and all should be considered as falling within the protection scope of the invention.
Claims (9)
1. A double light fusion system of visible light and infrared light is characterized by being applied to an unmanned aerial vehicle and a modeling terminal remotely connected with the unmanned aerial vehicle;
the unmanned aerial vehicle comprises a shooting device, wherein the shooting device comprises a forward shooting unit and four inclined shooting units around the forward shooting unit; the positive shooting unit and the inclined shooting unit respectively comprise an infrared shooting subunit and a visible light shooting subunit;
the modeling terminal is provided with a first time axis and a second time axis and controls the unmanned aerial vehicle to acquire data of rural buildings at different time periods;
the collecting and storing rural building data in the time period of the first time axis comprises the following steps: an infrared shooting subunit of the unmanned aerial vehicle acquires infrared images of rural buildings to obtain building contour data, three-dimensional vertex three-dimensional data of the rural buildings and four anchor point elements of the rural buildings;
the rural building data collected and stored in the time period of the second time axis corresponding to the first time axis comprises the following steps: the method comprises the steps that a texture map of a rural building is shot by a visible light shooting sub-unit of an unmanned aerial vehicle, and courtyard spectral data in a rectangle formed by four anchor point elements;
and fusing the texture mapping of the time period of the second time axis with the three-dimensional vertex stereogram of the time period corresponding to the first time axis to obtain the real three-dimensional stereogram of the rural building.
2. A dual light fusion system of visible light and infrared light as claimed in claim 1, wherein the unmanned aerial vehicle further comprises a distance measuring device, a positioning device, an image processing device and a control device; the modeling terminal comprises a house three-dimensional vertex model, a real-time modeling unit and a modeling control unit.
3. A dual light fusion system of visible and infrared light as claimed in claim 2,
the unmanned aerial vehicle sends the acquired infrared image to a modeling terminal, and the modeling control unit extracts building outline data by using the infrared image;
the modeling terminal stores a house three-dimensional vertex model of the rural building;
a modeling control unit of the modeling terminal selects a corresponding three-dimensional vertex model from the three-dimensional vertex models by utilizing a deep learning algorithm according to building contour data extracted from the infrared image;
and the real-time modeling unit of the modeling terminal improves the three-dimensional vertex model according to the building outline to obtain a three-dimensional vertex stereogram of the building outline corresponding to the infrared image.
4. The system of claim 3, wherein the modeling control unit sets four anchor point elements at four vertices of the outer edge of the rural building or sets four anchor point elements at four vertices of the outer edge of the rural building plus an extension distance for the rural building with the enclosure.
5. A dual light fusion system of visible and infrared light as claimed in claim 3, wherein for rural buildings without enclosing walls, the setting of the four anchor point elements by the modeling control unit is as follows: two anchor point elements are determined according to rural buildings without enclosing walls; the other two anchor points are determined by reconstructing a rectangle according to the sum of the areas of 200 square meters and the extended area.
6. A dual light fusion system of visible and infrared light as claimed in claim 4 or 5, wherein the modeling terminal sends the geographical location of the anchor point element determined in real time to the drone; after the infrared shooting subunit of the unmanned aerial vehicle obtains the positions of the anchor point elements, the image acquisition resolution ratio in the rectangle formed by the four anchor point elements is higher than the image acquisition resolution ratio outside the rectangle formed by the four anchor point elements.
7. The system of claim 6, wherein on a second time axis, the unmanned aerial vehicle collects visible light images of four dimensions, namely, an overhead view, a front dimension, a rear dimension, a left dimension and a right dimension, of the corresponding rural building according to the received positioning data of the rural building and the corresponding anchor point element; the resolution of the acquisition of the visible image within the rectangle made up of the four anchor elements is higher than the resolution of the acquisition of the visible image outside the rectangle made up of the four anchor elements.
8. A dual light fusion system of visible light and infrared light as claimed in claim 7, wherein the activation of the imaging spectrum subunit is triggered when the image captured/collected by the visible light capture subunit of the UAV is within the rectangle formed by the four anchor elements.
9. The dual-light fusion system of visible light and infrared light as claimed in claim 8, wherein the imaging spectrum subunit performs accurate data acquisition of surface height, i.e. flatness, within a rectangle formed by four anchor point elements by using laser remote sensing data, and sends the acquired surface height data to the modeling terminal for correction of the three-dimensional vertex stereogram.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110135777.9A CN112461209B (en) | 2021-02-01 | 2021-02-01 | Double-light fusion system of visible light and infrared light |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110135777.9A CN112461209B (en) | 2021-02-01 | 2021-02-01 | Double-light fusion system of visible light and infrared light |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112461209A true CN112461209A (en) | 2021-03-09 |
| CN112461209B CN112461209B (en) | 2021-04-30 |
Family
ID=74802471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110135777.9A Active CN112461209B (en) | 2021-02-01 | 2021-02-01 | Double-light fusion system of visible light and infrared light |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112461209B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017091268A2 (en) * | 2015-09-25 | 2017-06-01 | Board Of Regents, The University Of Texas System | Measurement of non-uniformity noise |
| US9886632B1 (en) * | 2016-11-04 | 2018-02-06 | Loveland Innovations, LLC | Systems and methods for autonomous perpendicular imaging of test squares |
| CN208953862U (en) * | 2018-10-31 | 2019-06-07 | 深圳市大疆创新科技有限公司 | Double light cameras, clouds terrace system and mobile platform |
| CN110611765A (en) * | 2019-08-01 | 2019-12-24 | 深圳市道通智能航空技术有限公司 | Camera imaging method, camera system and unmanned aerial vehicle |
| CN110866531A (en) * | 2019-10-15 | 2020-03-06 | 深圳新视达视讯工程有限公司 | Building feature extraction method and system based on three-dimensional modeling and storage medium |
| CN111402134A (en) * | 2020-03-15 | 2020-07-10 | 国科天成（北京）科技有限公司 | Visible/infrared double-light fusion system |
-
2021
- 2021-02-01 CN CN202110135777.9A patent/CN112461209B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017091268A2 (en) * | 2015-09-25 | 2017-06-01 | Board Of Regents, The University Of Texas System | Measurement of non-uniformity noise |
| US9886632B1 (en) * | 2016-11-04 | 2018-02-06 | Loveland Innovations, LLC | Systems and methods for autonomous perpendicular imaging of test squares |
| CN208953862U (en) * | 2018-10-31 | 2019-06-07 | 深圳市大疆创新科技有限公司 | Double light cameras, clouds terrace system and mobile platform |
| CN110611765A (en) * | 2019-08-01 | 2019-12-24 | 深圳市道通智能航空技术有限公司 | Camera imaging method, camera system and unmanned aerial vehicle |
| CN110866531A (en) * | 2019-10-15 | 2020-03-06 | 深圳新视达视讯工程有限公司 | Building feature extraction method and system based on three-dimensional modeling and storage medium |
| CN111402134A (en) * | 2020-03-15 | 2020-07-10 | 国科天成（北京）科技有限公司 | Visible/infrared double-light fusion system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112461209B (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fruh et al. | Constructing 3D city models by merging aerial and ground views | |
| CN110287519A (en) | A kind of the building engineering construction progress monitoring method and system of integrated BIM | |
| CN105700525B (en) | Method is built based on Kinect sensor depth map robot working environment uncertainty map | |
| EP3361235A1 (en) | Device and method for analysing objects | |
| Kaartinen et al. | Accuracy of 3D city models: EuroSDR comparison | |
| CN113936108A (en) | Unmanned aerial vehicle shooting and reconstruction method and device for building facade fine modeling | |
| CN113012292B (en) | AR remote construction monitoring method and system based on unmanned aerial vehicle aerial photography | |
| KR20120099952A (en) | Sensor system, and system and method for preparing environment map using the same | |
| CN109191533B (en) | Tower crane high-altitude construction method based on fabricated building | |
| CN111602335A (en) | Simulation method, system, and program for photovoltaic power generation device | |
| JP3514469B2 (en) | 3D object measurement system using laser | |
| CN206741555U (en) | The house type 3D modeling system of indoor 3D scannings based on more splicing cameras | |
| Meschini et al. | Point cloud-based survey for cultural heritage–An experience of integrated use of range-based and image-based technology for the San Francesco convent in Monterubbiano | |
| CN105910585A (en) | Rapid inspection and measuring method of illegal buildings based on oblique photography | |
| CN114529585A (en) | Mobile equipment autonomous positioning method based on depth vision and inertial measurement | |
| CN112461209B (en) | Double-light fusion system of visible light and infrared light | |
| CN116824067B (en) | Indoor three-dimensional reconstruction method and device thereof | |
| Adan et al. | Robot for thermal monitoring of buildings | |
| Wang et al. | Automatic texture acquisition for 3D model using oblique aerial images | |
| CN111399014A (en) | Local stereoscopic vision infrared camera system and method for monitoring wild animals | |
| CN114531700B (en) | Non-artificial base station antenna work parameter acquisition system and method | |
| Kurisu et al. | Development of a laser range finder for 3D map-building in rubble | |
| CN115601517A (en) | Rock mass structural plane information acquisition method and device, electronic equipment and storage medium | |
| CN112507979B (en) | Building information identification system and method based on block chain and double-light fusion | |
| CN112284351A (en) | Method for measuring cross spanning line |
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 |