CN114895304B - Method, equipment and device for cleaning, detecting and planning building outer wall - Google Patents
Method, equipment and device for cleaning, detecting and planning building outer wall Download PDFInfo
- Publication number
- CN114895304B CN114895304B CN202210817939.1A CN202210817939A CN114895304B CN 114895304 B CN114895304 B CN 114895304B CN 202210817939 A CN202210817939 A CN 202210817939A CN 114895304 B CN114895304 B CN 114895304B
- Authority
- CN
- China
- Prior art keywords
- building
- detection
- wall
- cleaning
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- 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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C27/00—Rotorcraft; Rotors peculiar thereto
- B64C27/04—Helicopters
- B64C27/08—Helicopters with two or more rotors
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
Abstract
The invention discloses a method, equipment and a device for cleaning, detecting and planning an outer wall of a building, wherein the system utilizes a detection unmanned aerial vehicle provided with a millimeter wave radar sensor to detect and sample characteristic data of the outer wall of the building, and transmits the detection data back to a terminal system through a wireless communication module for data processing and analysis, so that a distance unit set of all sampling directions of a two-dimensional scanning plane along the visual axis direction of an antenna beam is formed, and a three-dimensional image of the surface of the outer wall of the building is generated. The system can well complete tasks such as the planning of the target cleaning area of the outer wall of the building, the planning of the cleaning path and the like according to the image characteristic judgment and analysis, thereby determining the priority of each cleaning area, avoiding the outer wall obstacle and the cleaning restricted area and solving the problems of low working efficiency and high interference of the existing automatic cleaning equipment.
Description
Technical Field
The invention relates to the field of radar imaging identification and civil unmanned aerial vehicles, in particular to a method, equipment and a device for detecting and planning outer wall cleaning of a building.
Background
In recent years, the increasing tension in available land resources in cities has led to a significant increase and an increasing density of high-rise buildings. With the increase of time, high-rise buildings are easily attached by dust in air and rainwater, and the overall attractiveness of the city is reduced, so that the municipal demand for cleaning the outer wall of the building is increased sharply. The traditional building cleaning mode is that a cleaner carries out manual cleaning operation by utilizing an overhead safety rope or a crane, the working efficiency is low, the risk coefficient is high, and the interference and the influence on workers in a building are extremely easy to cause during the cleaning operation. Therefore, the automatic cleaning equipment for the outer wall is produced at the same time, and a simple, safe and effective solution is provided for the high-altitude cleaning operation. However, since the automatic cleaning device is still in the development stage, the degree of intelligence is limited, and when the automatic cleaning device faces to the external shapes of various high-rise buildings, the problems of insufficient cleaning, repeated cleaning, entering into a cleaning restricted area and the like exist, so that a plurality of problems and difficulties exist in practical application, and the automatic cleaning device cannot well replace a manual cleaning operation mode.
Disclosure of Invention
The invention provides a method, equipment and a device for detecting and planning the cleaning of an external wall of a building, aiming at the defects of poor judging capability of the existing automatic cleaning equipment for the cleaning area, low working efficiency and the like, and the method, the equipment and the device for detecting and planning the cleaning area of the external wall of the building are used for completing target detection and identification, defining the cleaning area and an forbidden area and planning an optimal cleaning path by utilizing a millimeter wave radar.
In order to achieve the purpose, the invention provides the following technical scheme:
the invention discloses a method for detecting and planning the cleanness of an outer wall of a building, which specifically comprises the following operations:
s1, determining the azimuth resolution of the radar sensor according to the parameters of the radar sensor; determining a horizontal sampling interval and a vertical sampling interval according to the azimuth resolution;
s2, controlling the detection unmanned aerial vehicle to hover to the outside of the outer wall of the building, and detecting the outer wall of the building through the radar sensor to obtain detection data; the detection data are processed by the data acquisition module and then transmitted to the terminal system;
s3, after receiving the detection data transmitted by the data acquisition module, the terminal system generates a three-dimensional image of the surface of the building outer wall through the data processing module;
s4, judging and deciding a building outer wall cleaning target area and a forbidden area according to the three-dimensional image characteristics, determining a cleaning priority and planning a cleaning path; the specific operation is as follows:
s41, for buildings with regular shapes on the outer wall surface, performing direct region judgment according to the three-dimensional image characteristics; the specific operation is as follows: if the three-dimensional image features show that the detection distance and the fluctuation of the scattering intensity of the echo signal are generally kept consistent, judging that the three-dimensional image features are a building wall part; if the three-dimensional image features are consistent in detection distance, but the amplitude of the echo signal is obviously enhanced and forms a closed shape, judging as a window area; if the three-dimensional image features are areas with abrupt changes of obvious distances and the detection distances of all echo signals in the areas are consistent, judging that the three-dimensional image features are clean forbidden areas;
s42, for buildings with complex external surface shape characteristics, acquiring external detection data of various buildings in the region in advance, adding labels for classification, and forming a sub-classification data set; building a characteristic training network, extracting the scattering image characteristics of the building wall surface part and the window area in each data set through model training of each sub-classification data set, and generating a corresponding characteristic model library; and finally, according to the belonged classification of the target detection building, importing the corresponding feature model library which is trained, and finishing the distinguishing of the clean area and the forbidden area of the target building.
Preferably, the azimuth resolution of the radar sensor in step S1 is determined by the E/H plane antenna beam width and the distance from the radar to the outer wall of the building, and the horizontal sampling interval and the vertical sampling interval are determined by the azimuth resolution.
Preferably, the specific process of step S2 is as follows:
s21, controlling the detection unmanned aerial vehicle to hover to a first detection area of the outer wall of the building; detecting the detection area through a radar sensor to obtain detection data, processing the detection data through a data acquisition module, and transmitting the detection data to a terminal system;
s22, controlling the detection unmanned aerial vehicle to keep the distance from the unmanned aerial vehicle to the outer wall of the building unchanged, moving the horizontal sampling interval along the horizontal direction, and hovering the unmanned aerial vehicle to the next detection area; detecting the detection area through a radar sensor to obtain detection data, processing the detection data through a data acquisition module, and transmitting the detection data to a terminal system; repeating the step S22 to finish the detection of the building outer wall at the same height;
s23, controlling the detection unmanned aerial vehicle to keep the distance from the unmanned aerial vehicle to the outer wall of the building unchanged, and hovering the unmanned aerial vehicle to the next height after moving the vertical sampling interval in the vertical direction; repeating step S22; completing the detection of the building outer wall in the height;
s24, repeating the step S23 to finish the detection of the building outer wall;
preferably, in step S2, the detecting by the radar sensor building exterior wall to obtain the detection data, and the processing the detection data by the data acquisition module and transmitting the detection data to the terminal system specifically includes the following sub-steps:
a1, transmitting a linear frequency modulation continuous sawtooth wave signal by a radar transmitting antenna; receiving echo signals scattered by the detection area by a receiving antenna; the radar sensor obtains an IQ baseband signal containing detection information by mixing the echo signals; and transmitting to a data acquisition module;
a2, a data acquisition module receives IQ baseband signals generated by a radar sensor; carrying out signal conditioning and ADC sampling on the IQ baseband signal; obtaining LVDS parallel signals;
a3, receiving LVDS parallel signals by the FPGA device, and transmitting the LVDS parallel signals to the first wireless communication module through the network port;
a4, the first wireless communication module transmits the received LVDS parallel signal to the second wireless communication module of the terminal system.
Preferably, step S3 specifically includes the following sub-steps:
s31, after the wireless communication module of the terminal system receives the detection data transmitted by the data acquisition module, forming an IQ baseband signal three-dimensional matrix containing all sampling directions;
and S32, forming a distance unit set along the visual axis direction of the antenna beam in all sampling orientations by the data processing module of the terminal system by using a signal processing technology, thereby generating a three-dimensional image of the surface of the building outer wall.
Preferably, for the building wall surface part, high cleaning priority is set; if the window area is the window area, setting the window area as a low cleaning priority; if the cleaning forbidden zone is formed, the cleaning operation is forbidden.
Preferably, the first detection area is one of an upper left corner, an upper right corner, a lower left corner or a lower right corner of an outer wall of the building.
The invention also discloses a device for cleaning, detecting and planning the outer wall of the building, which comprises:
the detection unmanned aerial vehicle comprises a sensing detection module, adopts a single-channel millimeter wave radar sensor and is used for detecting the outer wall of the building;
the terminal system comprises a data processing module, a display module and a display module, wherein the data processing module is used for forming a three-dimensional image of the surface of the outer wall of the building through a signal processing technology;
the data acquisition module is used for receiving and processing signals of the radar sensor;
the first wireless communication module is used for receiving the signal of the data acquisition module and is in communication connection with the second wireless communication module;
the flight power module is used for providing flight power and attitude control for the detection unmanned aerial vehicle;
the navigation positioning module is used for determining and feeding back the position of each detection and sampling of the detection unmanned aerial vehicle;
the control module is used for sending action instructions to the detection unmanned aerial vehicle;
and the second wireless communication module is used for receiving the signal sent by the first communication module.
The invention also discloses a device for detecting and planning the cleaning of the outer wall of the building, which comprises a memory and one or more processors, wherein executable codes are stored in the memory, and when the one or more processors execute the executable codes, the device is used for the method for detecting and planning the cleaning of the outer wall of the building.
The invention also discloses a computer readable storage medium, which stores a program, when the program is executed by a processor, the method for detecting and planning the cleaning of the outer wall of the building is realized.
The invention has the beneficial effects that:
according to the building outer wall cleaning detection and planning method provided by the invention, a distance unit set of all sampling directions is formed by a millimeter wave radar detection means and a signal processing technology, so that three-dimensional imaging of the surface of the building outer wall is realized.
According to the invention, for the building with the regular external surface shape characteristics, the direct judgment is carried out according to the image characteristics, and tasks such as the planning of the target cleaning area of the external wall of the building, the planning of the cleaning path and the like are completed; for buildings with complex external surface shape characteristics, the detection sample data of various buildings are collected, and a characteristic training network is introduced, so that the system is optimized to distinguish a target building cleaning area from a forbidden area, the efficiency and the accuracy of area judgment are greatly improved, and a good detection and planning technical means support is provided for the work of the existing automatic cleaning equipment.
The features and advantages of the present invention will be described in detail by embodiments in conjunction with the accompanying drawings.
Drawings
Fig. 1 is a schematic diagram of the working implementation of the method for detecting and planning the cleaning of the outer wall of the building.
Fig. 2 is a working flow chart of the method for detecting and planning the cleaning of the outer wall of the building.
Fig. 3 is a schematic structural diagram of a device for detecting and planning the cleaning of the outer wall of a building.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood, however, that the description herein of specific embodiments is only intended to illustrate the invention and not to limit the scope of the invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
The invention relates to a method for detecting and planning the cleanness of an outer wall of a building, which specifically comprises the following operations:
s1, determining the azimuth resolution of the radar sensor according to the parameters of the radar sensor; determining a horizontal sampling interval and a vertical sampling interval according to the azimuth resolution;
s2, controlling the detection unmanned aerial vehicle to hover outside the outer wall of the building, and detecting the outer wall of the building through the radar sensor to obtain detection data; the detection data are processed by the data acquisition module and then transmitted to the terminal system;
s3, after receiving the detection data transmitted by the data acquisition module, the terminal system generates a three-dimensional image of the surface of the building outer wall through the data processing module;
s4, judging and deciding a building outer wall cleaning target area and a forbidden area according to the three-dimensional image characteristics, determining a cleaning priority and planning a cleaning path; the specific operation is as follows:
s41, for buildings with regular shapes on the outer wall surface, performing direct region judgment according to the three-dimensional image characteristics; the specific operation is as follows: if the three-dimensional image features show that the detection distance and the fluctuation of the scattering intensity of the echo signal are generally kept consistent, judging that the three-dimensional image features are a building wall part; if the three-dimensional image features are consistent in detection distance, but the amplitude of the echo signal is obviously enhanced and forms a closed shape, judging as a window area; if the three-dimensional image features are areas with abrupt changes of obvious distances and the detection distances of all echo signals in the areas are consistent, judging that the three-dimensional image features are clean forbidden areas;
s42, for buildings with complex external surface shape characteristics, acquiring external detection data of various buildings in the region in advance, adding labels for classification, and forming a sub-classification data set; building a characteristic training network, extracting the scattering image characteristics of the building wall surface part and the window area in each data set through model training of each sub-classification data set, and generating a corresponding characteristic model library; and finally, according to the belonged classification of the target detection building, importing the corresponding feature model library which is trained, and finishing the distinguishing of the clean area and the forbidden area of the target building.
In a possible embodiment, the azimuth resolution of the radar sensor in step S1 is determined by the E/H plane antenna beam width and the distance from the radar to the outer wall of the building, and the horizontal sampling interval and the vertical sampling interval are determined by the azimuth resolution.
In a possible embodiment, the specific process of step S2 is as follows:
s21, controlling the detection unmanned aerial vehicle to hover to a first detection area of the outer wall of the building; detecting the detection area through a radar sensor to obtain detection data, processing the detection data through a data acquisition module, and transmitting the detection data to a terminal system;
s22, controlling the detection unmanned aerial vehicle to keep the distance from the unmanned aerial vehicle to the outer wall of the building unchanged, and hovering the unmanned aerial vehicle to the next detection area after moving the horizontal sampling interval along the horizontal direction; detecting the detection area through a radar sensor to obtain detection data, processing the detection data through a data acquisition module, and transmitting the detection data to a terminal system; repeating the step S22 to finish the detection of the building outer wall at the same height;
s23, controlling the detection unmanned aerial vehicle to keep the distance from the unmanned aerial vehicle to the outer wall of the building unchanged, and hovering the unmanned aerial vehicle to the next height after moving the vertical sampling interval in the vertical direction; repeating step S22; completing the detection of the building outer wall in the height;
s24, repeating the step S23 to finish the detection of the building outer wall;
in a feasible embodiment, the detecting by the radar sensor building outer wall to obtain the detection data, and the data acquisition module to process the detection data and then transmit the detection data to the terminal system specifically includes the following substeps:
a1, transmitting a linear frequency modulation continuous sawtooth wave signal by a radar transmitting antenna; receiving echo signals scattered by the detection area by a receiving antenna; the radar sensor obtains an IQ baseband signal containing detection information by mixing the echo signals; and transmitting to a data acquisition module;
a2, a data acquisition module receives IQ baseband signals generated by a radar sensor; carrying out signal conditioning and ADC sampling on the IQ baseband signal; acquiring LVDS parallel signals;
a3, receiving LVDS parallel signals by the FPGA device, and transmitting the LVDS parallel signals to the first wireless communication module through the network port;
a4, the first wireless communication module transmits the received LVDS parallel signal to the second wireless communication module of the terminal system.
In a possible embodiment, step S3 specifically includes the following sub-steps:
s31, after the wireless communication module of the terminal system receives the detection data transmitted by the data acquisition module, forming an IQ baseband signal three-dimensional matrix containing all sampling directions;
and S32, forming a distance unit set along the visual axis direction of the antenna beam in all sampling orientations by the data processing module of the terminal system by using a signal processing technology, thereby generating a three-dimensional image of the surface of the building outer wall.
In one possible embodiment, for the building wall portion, a high cleaning priority is set; if the window area is the window area, setting the window area as a low cleaning priority; if the cleaning forbidden zone is formed, the cleaning operation is forbidden.
In a possible embodiment, the first detection area is one of an upper left corner, an upper right corner, a lower left corner or a lower right corner of an exterior wall of the building.
The invention relates to a building outer wall cleaning detection and planning device, which comprises:
the detection unmanned aerial vehicle comprises a sensing detection module, adopts a single-channel millimeter wave radar sensor and is used for detecting the outer wall of the building;
the terminal system comprises a data processing module, a display module and a display module, wherein the data processing module is used for forming a three-dimensional image of the surface of the building outer wall through a signal processing technology;
the data acquisition module is used for receiving and processing signals of the radar sensor;
the first wireless communication module is used for receiving the signal of the data acquisition module and is in communication connection with the second wireless communication module;
the flight power module is used for providing flight power and attitude control for the detection unmanned aerial vehicle;
the navigation positioning module is used for determining and feeding back the position of each detection and sampling of the detection unmanned aerial vehicle;
the control module is used for sending action instructions to the detection unmanned aerial vehicle;
and the second wireless communication module is used for receiving the signal sent by the first communication module.
In the unmanned detection vehicle, a sensing detection module adopts a single-channel millimeter wave radar sensor, and the apparent axis direction of a radar antenna beam is vertical to the plane of a detected building; a radar transmitting antenna transmits a linear frequency modulation continuous sawtooth wave signal; the receiving antenna receives an echo signal scattered by a single detection area outside the building; the radar sensor obtains an IQ baseband signal containing outer wall detection information by mixing the echo signals.
The specific embodiment is as follows:
in the embodiment of the invention, the working parameters of the radar sensor are set as follows: the carrier frequency modulation scanning range is 122-123 GHz; the sweep frequency period is 80 us; the transmit and receive antenna beam center gain is 18 dBi and the E/H plane beam width is 5 °.
In the unmanned aerial vehicle for detection, the data acquisition module mainly comprises an analog-to-digital converter (ADC), a Field Programmable Gate Array (FPGA) device and an external interface.
Specifically, the peripheral interfaces include SPI, I2C, gigabit ports, and the like.
The data acquisition module receives IQ baseband signals generated by the radar sensor, and performs signal conditioning and ADC sampling; the FPGA device receives LVDS parallel signals generated by the ADC and transmits the LVDS parallel signals through a gigabit network port; the wireless communication module receives the sampled detection data and transmits the data to the terminal system through Wi-Fi, so that one-time detection of the outer wall of the building is completed.
The parameters of the data acquisition module are set as follows: ADC sampling frequency is 8 Msps, the number of conversion bits is 16, and the number of sampling points is 512; LVDS transmission rate 600 Mbps; the Wi-Fi of the wireless communication module selects a 2400-2483.5 MHz or 5725-5850 MHz frequency band according to a working scene.
As shown in fig. 1, after the sensing and detecting module completes the first detection area at the upper right corner, the detecting unmanned aerial vehicle keeps the distance to the outer wall of the building unchanged, and moves the horizontal sampling interval dx along the horizontal direction to hover to the next detection area; after M times of horizontal movement and detection are carried out, the detection of the building external area in the same height is finished, the vertical sampling interval dy is moved in the vertical direction to hover to the next height, the horizontal detection and sampling process is repeated, and scanning detection is finished after N times of vertical height movement, so that all areas outside the building are ensured to be detected.
In the detection unmanned aerial vehicle, the navigation positioning module determines and feeds back the orientation of the unmanned aerial vehicle for each detection and sampling so as to
Is represented by, wherein the horizontal coordinate is subscript
Subscript of vertical coordinate
(ii) a The flight power module provides flight power and attitude control for unmanned aerial vehicle, ensures to survey that unmanned aerial vehicle gesture is stable and transmission and receiving antenna beam visual axis direction perpendicular to surveys the building plane.
In the embodiment of the invention, a radar sensor is arranged to keep the distance R0 to the outer wall of a building to be 1.5 meters, the horizontal distance of a detection target building range is 20 meters, and the vertical distance is 30 meters;
according to the radar azimuth resolution formula, the azimuth resolution da is determined by the antenna beam width Θ a and the radar-to-building facade distance R0:
since the E/H plane antenna beam widths are both 5 °, the calculated azimuth resolution da is about 0.13 m in both the horizontal and vertical directions. Since the beam widths of the E/H plane antennas are the same, both the horizontal sampling interval and the vertical sampling interval are set to 0.13 m. Therefore, the number of horizontal sampling times is approximately set to 154, and the vertical sampling interval is 231.
In the terminal system, referring to fig. 2, the wireless communication module receives all sampled external wall detection data transmitted back by the detection unmanned aerial vehicle through Wi-Fi to form a position containing all samples
The IQ baseband signal three-dimensional matrix of the digital signal; the data processing module forms all sampling directions by utilizing signal processing technologies such as Fourier transform, constant false alarm rate detection, distance compensation correction and the like
The distance units along the visual axis direction of the antenna wave beam are collected, so that a three-dimensional image of the surface of the building outer wall is generated, a cleaning target area and a forbidden area of the building outer wall are judged and decided according to the image characteristics, and the cleaning priority and the cleaning forbidden area are determinedPlanning a cleaning path; the control module is responsible for sending action instructions to the detection unmanned aerial vehicle, and the action instructions comprise starting tasks, ending tasks, setting sensor parameters, detecting track single moving distance and the like.
And the data processing module is used for executing direct region judgment on the buildings with regular external surface shapes according to the image characteristics. If the image characteristics show that the detection distance and the fluctuation of the scattering intensity of the echo signal are generally kept consistent, judging that the building outer wall part needs to be cleaned; if the image characteristics are that the detection distances are consistent, but the signal amplitude is obviously enhanced and a closed shape is formed, judging that the window frame is a window frame, and taking the enclosed area as a window area; and if the image characteristics are regions with obvious abrupt change of distance and all signal detection distances in the regions are consistent, determining that the forbidden region is clean.
Specifically, if the building outer wall part is a building outer wall part, a high cleaning priority is set, or cleaning in daily working time is planned; if the window area is the window area, setting the window area as a low cleaning priority, or planning cleaning in the dining time and the off-duty time so as to reduce the interference of cleaning operation on workers in the building; if the window is a cleaning forbidden area, such as an air conditioner outdoor unit, a window area pushed outwards and the like, cleaning operation is forbidden, and the problems of equipment failure, building internal environment pollution and the like are avoided.
For buildings with complex external surface shape characteristics, the data processing module needs to acquire external detection data of various buildings in the region in advance, and adds labels for classification to form a sub-classification data set; building a characteristic training network, extracting the scattering image characteristics of areas such as building outer walls, windows and the like in each data set through model training of each sub-classification data set, and generating a corresponding characteristic model library; and finally, according to the belonged classification of the target detection building, importing the corresponding trained feature model library to finish the distinguishing of the clean area and the forbidden area of the target building and finish the planning of the clean path, thereby improving the efficiency and the accuracy of the distinguishing of the clean area outside the building.
In particular, the dataset classification tags may include: building functions, such as residential housing quarters, industrial parks, business office buildings, and the like; the building styles of the developers such as antique and modern; administrative divisions such as city centers, perimeter counties, etc.
The embodiment of the building outer wall cleaning detection and planning device can be applied to any equipment with data processing capability, such as computers and other equipment or devices. The apparatus embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. The software implementation is taken as an example, and as a logical device, the device is formed by reading corresponding computer program instructions in the nonvolatile memory into the memory for running through the processor of any device with data processing capability. From a hardware aspect, as shown in fig. 3, a hardware structure diagram of any device with data processing capability where the building outer wall cleaning detection and planning apparatus of the present invention is located is shown, except for the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 3, in the embodiment, any device with data processing capability where the apparatus is located may also include other hardware generally according to the actual function of the any device with data processing capability, which is not described again. The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the invention. One of ordinary skill in the art can understand and implement without inventive effort.
An embodiment of the present invention further provides a computer-readable storage medium, on which a program is stored, and when the program is executed by a processor, the apparatus for detecting and planning the cleaning of the exterior wall of a building in the above-mentioned embodiment is implemented.
The computer readable storage medium may be an internal storage unit, such as a hard disk or a memory, of any data processing capability device described in any of the foregoing embodiments. The computer readable storage medium may also be any external storage device of a device with data processing capabilities, such as a plug-in hard disk, a Smart Media Card (SMC), an SD Card, a Flash memory Card (Flash Card), etc. provided on the device. Further, the computer readable storage medium may include both an internal storage unit and an external storage device of any data processing capable device. The computer-readable storage medium is used for storing the computer program and other programs and data required by the arbitrary data processing-capable device, and may also be used for temporarily storing data that has been output or is to be output.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents or improvements made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (8)
1. A method for detecting and planning the cleanness of an outer wall of a building is characterized by comprising the following operations:
s1, determining the azimuth resolution of the radar sensor according to the parameters of the radar sensor; determining a horizontal sampling interval and a vertical sampling interval according to the azimuth resolution;
s2, controlling the detection unmanned aerial vehicle to hover to the outside of the outer wall of the building, and detecting the outer wall of the building through the radar sensor to obtain detection data; the detection data are processed by the data acquisition module and then transmitted to the terminal system;
the specific process of step S2 is as follows:
s21, controlling the detection unmanned aerial vehicle to hover to a first detection area of the outer wall of the building; detecting the detection area through a radar sensor to obtain detection data, processing the detection data through a data acquisition module, and transmitting the detection data to a terminal system;
s22, controlling the detection unmanned aerial vehicle to keep the distance from the unmanned aerial vehicle to the outer wall of the building unchanged, moving the horizontal sampling interval along the horizontal direction, and hovering the unmanned aerial vehicle to the next detection area; detecting the detection area through a radar sensor to obtain detection data, processing the detection data through a data acquisition module, and transmitting the detection data to a terminal system; repeating the step S22 to finish the detection of the building outer wall at the same height;
s23, controlling the detection unmanned aerial vehicle to keep the distance from the unmanned aerial vehicle to the outer wall of the building unchanged, and hovering the unmanned aerial vehicle to the next height after moving the vertical sampling interval in the vertical direction; repeating the step S22; completing the detection of the building outer wall in the height;
s24, repeating the step S23 to finish the detection of the building outer wall;
s3, after receiving the detection data transmitted by the data acquisition module, the terminal system generates a three-dimensional image of the surface of the building outer wall through the data processing module;
s4, judging and deciding a building outer wall cleaning target area and a forbidden area according to the three-dimensional image characteristics, determining a cleaning priority and planning a cleaning path; the specific operation is as follows:
s41, for the buildings with regular shapes on the outer wall surface, performing direct area judgment according to the characteristics of the three-dimensional image; the specific operation is as follows: if the three-dimensional image features show that the detection distance and the fluctuation of the scattering intensity of the echo signal are generally kept consistent, judging that the three-dimensional image features are a building wall part; if the three-dimensional image features are consistent in detection distance, but the amplitude of the echo signal is obviously enhanced and forms a closed shape, judging as a window area; if the three-dimensional image features are areas with abrupt changes of obvious distances and the detection distances of all echo signals in the areas are consistent, judging that the three-dimensional image features are clean forbidden areas;
s42, for buildings with complex external surface shape characteristics, acquiring external detection data of various buildings in the region in advance, adding labels for classification, and forming a sub-classification data set; building a characteristic training network, extracting the scattering image characteristics of the building wall surface part and the window area in each data set through model training of each sub-classification data set, and generating a corresponding characteristic model library; finally, according to the belonged classification of the target detection building, importing the corresponding feature model library which is trained, and finishing the distinguishing of the clean area and the forbidden area of the target building;
the method comprises the following steps of detecting through the outer wall of the radar sensor building to obtain detection data, processing the detection data through a data acquisition module, and transmitting the processed detection data to a terminal system, wherein the sub-steps comprise:
a1, transmitting a linear frequency modulation continuous sawtooth wave signal by a radar transmitting antenna; receiving echo signals scattered by the detection area by a receiving antenna; the radar sensor obtains an IQ baseband signal containing detection information by mixing the echo signals; and transmitting to a data acquisition module;
a2, a data acquisition module receives IQ baseband signals generated by a radar sensor; carrying out signal conditioning and ADC sampling on the IQ baseband signal; obtaining LVDS parallel signals;
a3, receiving LVDS parallel signals by the FPGA device, and transmitting the LVDS parallel signals to the first wireless communication module through the network port;
a4, the first wireless communication module transmits the received LVDS parallel signal to the second wireless communication module of the terminal system.
2. The method for detecting and planning the cleaning of the exterior wall of the building as claimed in claim 1, wherein: the azimuth resolution of the radar sensor in step S1 is determined by the E/H-plane antenna beam width and the distance from the radar to the outer wall of the building, and the horizontal sampling interval and the vertical sampling interval are determined by the azimuth resolution.
3. The method for detecting and planning the cleaning of the exterior wall of the building as claimed in claim 1, wherein the step S3 comprises the following steps:
s31, after the wireless communication module of the terminal system receives the detection data transmitted by the data acquisition module, forming an IQ baseband signal three-dimensional matrix containing all sampling directions;
and S32, forming a distance unit set along the visual axis direction of the antenna beam in all sampling orientations by the data processing module of the terminal system by using a signal processing technology, thereby generating a three-dimensional image of the surface of the building outer wall.
4. The method for detecting and planning the cleaning of the exterior walls of a building according to claim 1, wherein a high cleaning priority is set for the wall surface portion of the building; if the window area is the window area, setting the window area as a low cleaning priority; if the cleaning forbidden zone is formed, the cleaning operation is forbidden.
5. The method for detecting and planning the cleaning of the exterior wall of the building as claimed in claim 1, wherein: the first detection area is one of the upper left corner, the upper right corner, the lower left corner or the lower right corner of the outer wall of the building.
6. An apparatus for using the method for detecting and planning the cleaning of the exterior walls of buildings according to any of claims 1 to 5, characterized in that: the system comprises a detection unmanned aerial vehicle and a terminal system, wherein the detection unmanned aerial vehicle mainly comprises a sensing detection module and a single-channel millimeter wave radar sensor and is used for detecting the outer wall of a building; the data acquisition module is used for receiving and processing signals of the radar sensor; the first wireless communication module is used for receiving the signal of the data acquisition module and is in communication connection with the second wireless communication module; the flight power module is used for providing flight power and attitude control for the detection unmanned aerial vehicle; the navigation positioning module is used for determining and feeding back the position of each detection and sampling of the detection unmanned aerial vehicle; the terminal system comprises a data processing module, a display module and a display module, wherein the data processing module is used for forming a three-dimensional image of the surface of the building outer wall through a signal processing technology; the control module is used for sending action instructions to the detection unmanned aerial vehicle, and the second wireless communication module is used for receiving signals sent by the first communication module.
7. An apparatus for detecting and planning the cleaning of the exterior wall of a building, comprising a memory and one or more processors, wherein the memory stores executable code, and the one or more processors, when executing the executable code, implement a method for detecting and planning the cleaning of the exterior wall of a building according to any one of claims 1-5.
8. A computer-readable storage medium characterized by: stored thereon a program which, when executed by a processor, implements a method of cleaning and planning exterior walls of a building as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210817939.1A CN114895304B (en) | 2022-07-13 | 2022-07-13 | Method, equipment and device for cleaning, detecting and planning building outer wall |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210817939.1A CN114895304B (en) | 2022-07-13 | 2022-07-13 | Method, equipment and device for cleaning, detecting and planning building outer wall |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114895304A CN114895304A (en) | 2022-08-12 |
| CN114895304B true CN114895304B (en) | 2022-09-27 |
Family
ID=82730182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210817939.1A Active CN114895304B (en) | 2022-07-13 | 2022-07-13 | Method, equipment and device for cleaning, detecting and planning building outer wall |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114895304B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117031986B (en) * | 2023-10-10 | 2023-12-15 | 江苏通创现代建筑产业技术研究院有限公司 | Control method and system for automatic cleaning of building curtain wall |
| CN117252399B (en) * | 2023-11-15 | 2024-01-23 | 南京特沃斯高科技有限公司 | Digital ecological cleaning data processing method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105517476A (en) * | 2014-09-03 | 2016-04-20 | 深圳市大疆创新科技有限公司 | UAV and wall cleaning method thereof, and wall cleaning system using same |
| WO2018000736A1 (en) * | 2016-06-28 | 2018-01-04 | 深圳市元征科技股份有限公司 | External wall cleaning method based on unmanned aerial vehicle, and unmanned aerial vehicle |
| CN110269540A (en) * | 2018-03-15 | 2019-09-24 | 谢苏琨 | A kind of UAV system of cleaning of buildings metope |
| CN113433971A (en) * | 2021-07-09 | 2021-09-24 | 深圳大学 | Method, device, equipment and storage medium for acquiring data of high-rise building exterior wall |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210132213A1 (en) * | 2019-10-31 | 2021-05-06 | Samsung Electronics Co., Ltd. | Apparatus and methods for multi-sensor slam systems |
-
2022
- 2022-07-13 CN CN202210817939.1A patent/CN114895304B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105517476A (en) * | 2014-09-03 | 2016-04-20 | 深圳市大疆创新科技有限公司 | UAV and wall cleaning method thereof, and wall cleaning system using same |
| WO2018000736A1 (en) * | 2016-06-28 | 2018-01-04 | 深圳市元征科技股份有限公司 | External wall cleaning method based on unmanned aerial vehicle, and unmanned aerial vehicle |
| CN110269540A (en) * | 2018-03-15 | 2019-09-24 | 谢苏琨 | A kind of UAV system of cleaning of buildings metope |
| CN113433971A (en) * | 2021-07-09 | 2021-09-24 | 深圳大学 | Method, device, equipment and storage medium for acquiring data of high-rise building exterior wall |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114895304A (en) | 2022-08-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114895304B (en) | Method, equipment and device for cleaning, detecting and planning building outer wall | |
| US10402999B2 (en) | Method, apparatus and terminal device for constructing map | |
| EP3913328B1 (en) | Vehicle positioning system and method, and vehicle | |
| CN106291517A (en) | The indoor cloud robot angle localization method optimized with visual information based on position | |
| US20230244828A1 (en) | Method and apparatus for associating digital content with wireless transmission nodes in a wireless communication area | |
| CN1578530A (en) | System and methods for determining the location dynamics of a portable computing device | |
| EP3447729B1 (en) | 2d vehicle localizing using geoarcs | |
| WO2019006289A1 (en) | Systems and methods for improvements in scanning and mapping | |
| CN111060869B (en) | Positioning method and system of intelligent storage UHFRFID label | |
| WO2021087701A1 (en) | Terrain prediction method and apparatus for undulating ground, and radar, unmanned aerial vehicle and operating control method | |
| WO2021087702A1 (en) | Sloped terrain prediction method and device, radar, unmanned aerial vehicle, and operation control method | |
| Schouten et al. | RadarSLAM: Biomimetic SLAM using ultra-wideband pulse-echo radar | |
| WO2022036332A1 (en) | Method and system for radar-based odometry | |
| Duecker et al. | Embedded spherical localization for micro underwater vehicles based on attenuation of electro-magnetic carrier signals | |
| TW202104929A (en) | Measurement apparatus and measurement system | |
| CN111563934B (en) | Monocular vision odometer scale determination method and device | |
| CN111290434B (en) | Unmanned aerial vehicle guiding method, system, equipment and storage medium | |
| CN112098926A (en) | Intelligent angle measurement training sample generation method using unmanned aerial vehicle platform | |
| CN115902786A (en) | Acoustic tracking and anti-braking interception device, system and method for invading unmanned aerial vehicle | |
| WO2022083529A1 (en) | Data processing method and apparatus | |
| WO2019167210A1 (en) | Control device, mobile body, and program | |
| Chen et al. | ConservationBots: Autonomous aerial robot for fast robust wildlife tracking in complex terrains | |
| CN109458979B (en) | Antenna downward inclination angle measurement method based on unmanned aerial vehicle visual analysis | |
| CN114758364A (en) | Industrial Internet of things scene fusion positioning method and system based on deep learning | |
| WO2021087785A1 (en) | Terrain detection method, movable platform, control device and system, and storage medium |
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 |