CN114390270B - Real-time intelligent site panorama exploration method and device and electronic equipment - Google Patents
Real-time intelligent site panorama exploration method and device and electronic equipment Download PDFInfo
- Publication number
- CN114390270B CN114390270B CN202011112049.8A CN202011112049A CN114390270B CN 114390270 B CN114390270 B CN 114390270B CN 202011112049 A CN202011112049 A CN 202011112049A CN 114390270 B CN114390270 B CN 114390270B
- Authority
- CN
- China
- Prior art keywords
- survey
- machine room
- pole
- task
- environment
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/275—Image signal generators from 3D object models, e.g. computer-generated stereoscopic image signals
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/204—Image signal generators using stereoscopic image cameras
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/204—Image signal generators using stereoscopic image cameras
- H04N13/239—Image signal generators using stereoscopic image cameras using two 2D image sensors having a relative position equal to or related to the interocular distance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
The embodiment of the invention provides a real-time intelligent site panoramic investigation method, a device and electronic equipment, wherein the method comprises the following steps: receiving a survey task, wherein the survey task comprises machine room internal survey modeling, pole surrounding environment modeling and pole large-scale environment modeling; acquiring images of the survey targets corresponding to the survey tasks, wherein the acquisition equipment and the acquisition mode for acquiring the images of the survey targets corresponding to the survey tasks are determined based on the natural space conditions of the predetermined survey targets; and carrying out three-dimensional model recovery based on the image, and sending the three-dimensional model as a task result to a survey platform for release. The method, the device and the electronic equipment provided by the embodiment of the invention realize the high efficiency, low labor cost and large information quantity of the site panoramic survey result, and are easy to display and convenient to share.
Description
Technical Field
The invention relates to the technical field of site survey, in particular to a real-time intelligent site panorama survey method, a device and electronic equipment.
Background
The communication station comprises a machine room and a holding pole, indoor machine room information and outdoor surrounding environments of the holding pole need to be collected for panoramic investigation of the station, the internal information of the machine room comprises machine room internal investigation information, machine room equipment information and machine room cabinet vacancy conditions, the surrounding environments of the holding pole are divided into a holding pole surrounding environment (namely a small range, which is closer to the holding pole) and a holding pole large-range environment (namely a large range, which is farther from the holding pole), and the small range and the large range are set according to the scale of the station. The existing site survey method needs to measure the sizes of all facility equipment, record the numbers of all equipment and draw drawings, is completed manually, has large workload, low efficiency and high difficulty, cannot intuitively show the condition of the site, and is inconvenient to propagate and share because the drawings only comprise two-dimensional information.
Therefore, how to avoid the situations of low efficiency and high labor cost caused by manually surveying the site, and the trouble that the surveying result in the form of drawing has small information quantity and is inconvenient to share is still a problem to be solved by the technicians in the field.
Disclosure of Invention
The embodiment of the invention provides a real-time intelligent site panoramic investigation method, a device and electronic equipment, which are used for solving the problems of low efficiency, high labor cost, small information quantity of investigation results in a drawing form and inconvenience in sharing caused by the fact that the site is subjected to the investigation by adopting a manual method in the prior art.
In a first aspect, an embodiment of the present invention provides a real-time smart site panorama exploration method, including:
receiving a survey task, wherein the survey task comprises machine room internal survey modeling, pole surrounding environment modeling and pole large-scale environment modeling;
acquiring images of the survey targets corresponding to the survey tasks, wherein acquisition equipment and acquisition modes for acquiring the images of the survey targets corresponding to the survey tasks are determined based on the predetermined natural space conditions of the survey targets;
and carrying out three-dimensional model recovery based on the image, and sending the three-dimensional model as a task result to an exploration platform for release.
Preferably, in the method, further comprising:
if the exploration target is the inside of the machine room, the natural space condition is natural light intensity and equipment texture richness;
if the exploration target is the surrounding environment of the holding pole, the natural space condition is the surrounding rain and fog condition of the holding pole;
if the exploration target is a pole large-range environment, the natural space condition is the volume of an object in the pole large-range environment.
Preferably, in the method, the acquisition device and the acquisition mode for acquiring the image of the survey target corresponding to the survey task are determined based on a predetermined natural space condition of the survey target, and specifically include:
when the survey task models a machine room interior survey,
if the natural light intensity is low and the equipment texture is lacking, moving and shooting in a machine room by using the SLAM robot to carry a structured light depth camera;
if the natural light intensity is proper and the equipment texture is rich, the SLAM robot is used for carrying a binocular camera to shoot in a machine room in a moving way;
if any condition is not met, the SLAM robot is used for carrying a camera and a laser radar to shoot in a machine room in a moving way;
when the survey task models the surrounding environment of the pole,
if no rain and fog exist, the unmanned aerial vehicle is used for carrying a camera and a laser radar to fly around the pole and shoot;
when the survey task models a wide range of pole environments,
if the object volume is larger in the wide-range environment of the holding pole, using the unmanned aerial vehicle to carry a camera to fly around and shoot in the wide-range environment of the holding pole;
if the object volume is smaller in the wide-range environment of the holding pole, the unmanned aerial vehicle is used for carrying the camera and the laser radar to fly around and shoot in the wide-range environment of the holding pole.
Preferably, in the method, the three-dimensional model recovery based on the image specifically includes:
performing feature matching on the image based on a SIFT operator to obtain a matched feature point pair;
computing a basic matrix for the matched characteristic point pairs by adopting a RANSAC eight-point method, and eliminating the matched characteristic point pairs which do not meet the basic matrix;
and then reconstructing the matched characteristic point pairs after being removed by using CMVS and PMVS algorithms to obtain a three-dimensional model.
In a second aspect, an embodiment of the present invention provides a real-time smart site panorama survey apparatus, including:
the receiving unit is used for receiving survey tasks, wherein the survey tasks comprise machine room internal survey modeling, pole surrounding environment modeling and pole large-scale environment modeling;
the acquisition unit is used for acquiring images of the survey targets corresponding to the survey tasks, wherein the acquisition equipment and the acquisition mode for acquiring the images of the survey targets corresponding to the survey tasks are determined based on the predetermined natural space conditions of the survey targets;
and the computing unit is used for recovering the three-dimensional model based on the image and sending the three-dimensional model to the exploration platform as a task result for release.
Preferably, the device further comprises:
if the exploration target is the inside of the machine room, the natural space condition is natural light intensity and equipment texture richness;
if the exploration target is the surrounding environment of the holding pole, the natural space condition is the surrounding rain and fog condition of the holding pole;
if the exploration target is a pole large-range environment, the natural space condition is the volume of an object in the pole large-range environment.
Preferably, in the apparatus, the acquisition device and the acquisition mode for acquiring the image of the survey target corresponding to the survey task are determined based on a predetermined natural space condition of the survey target, and specifically include:
when the survey task models a machine room interior survey,
if the natural light intensity is low and the equipment texture is lacking, moving and shooting in a machine room by using the SLAM robot to carry a structured light depth camera;
if the natural light intensity is proper and the equipment texture is rich, the SLAM robot is used for carrying a binocular camera to shoot in a machine room in a moving way;
if any condition is not met, the SLAM robot is used for carrying a camera and a laser radar to shoot in a machine room in a moving way;
when the survey task models the surrounding environment of the pole,
if no rain and fog exist, the unmanned aerial vehicle is used for carrying a camera and a laser radar to fly around the pole and shoot;
when the survey task models a wide range of pole environments,
if the object volume is larger in the wide-range environment of the holding pole, using the unmanned aerial vehicle to carry a camera to fly around and shoot in the wide-range environment of the holding pole;
if the object volume is smaller in the wide-range environment of the holding pole, the unmanned aerial vehicle is used for carrying the camera and the laser radar to fly around and shoot in the wide-range environment of the holding pole.
Preferably, in the apparatus, the three-dimensional model restoration based on the image specifically includes:
performing feature matching on the image based on a SIFT operator to obtain a matched feature point pair;
computing a basic matrix for the matched characteristic point pairs by adopting a RANSAC eight-point method, and eliminating the matched characteristic point pairs which do not meet the basic matrix;
and then reconstructing the matched characteristic point pairs after being removed by using CMVS and PMVS algorithms to obtain a three-dimensional model.
In a third aspect, an embodiment of the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the real-time smart site panorama investigation method as provided in the first aspect when the program is executed.
In a fourth aspect, embodiments of the present invention provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the real-time smart site panoramic investigation method as provided in the first aspect.
The method, the device and the electronic equipment provided by the embodiment of the invention receive the exploration task, wherein the exploration task comprises the internal exploration modeling of a machine room, the surrounding environment modeling of the holding pole and the large-scale environment modeling of the holding pole; acquiring images of the survey targets corresponding to the survey tasks, wherein acquisition equipment and acquisition modes for acquiring the images of the survey targets corresponding to the survey tasks are determined based on the predetermined natural space conditions of the survey targets; and carrying out three-dimensional model recovery based on the image, and sending the three-dimensional model as a task result to an exploration platform for release. Therefore, according to different types of the survey task and different selection of natural space conditions of the survey target corresponding to the survey task, the image acquisition equipment and the method are suitable, finally, the recognition result or the three-dimensional modeling obtained by recognition or three-dimensional modeling based on the acquired image is returned as the result of the survey task, the automation of the survey flow and the automatic return sharing of the result are realized, and the three-dimensional model serving as the completion result of the task can provide more information for convenient display. Therefore, the real-time intelligent site panoramic investigation method, the device and the electronic equipment provided by the embodiment of the invention realize the high efficiency, low labor cost, large investigation result information quantity, easy display and convenient sharing of site panoramic investigation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below of the drawings required for the embodiments or the prior art descriptions, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a real-time intelligent site panoramic investigation method provided by an embodiment of the invention;
fig. 2 is a schematic structural diagram of a real-time intelligent site panorama survey device according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without any inventive effort, are intended to be within the scope of the invention.
The existing method for surveying and mapping sites by adopting manual measurement and mapping generally has the problems of low efficiency, high labor cost, small information quantity of surveying and mapping results in a drawing form and inconvenience in sharing. In this regard, the embodiment of the present invention provides a method for guaranteeing consistency of a telecommunication service contract based on a blockchain, where an execution subject of the method is an authoritative service device. Fig. 1 is a flow chart of a real-time intelligent site panorama exploration method according to an embodiment of the present invention, as shown in fig. 1, the method includes:
step 110, a survey task is received, wherein the survey task comprises machine room internal survey modeling, pole surrounding environment modeling and pole large-scale environment modeling.
Specifically, a survey task is received, and then a survey task class and a corresponding survey target are determined, wherein the survey task class is divided into three classes: the machine room internal survey modeling, the pole surrounding environment modeling and the pole large-scale environment modeling are respectively carried out on the survey targets corresponding to the three types of survey tasks: inside the computer lab, pole surrounding environment and pole wide range environment. All the tasks need to be returned to be a three-dimensional model, namely, three-dimensional modeling is carried out on an exploration target, and then the three-dimensional model is returned as an exploration result. After the survey task is received, the task type and the corresponding survey target can be obtained through analysis of the task.
Step 120, acquiring an image of the survey target corresponding to the survey task, wherein an acquisition device and an acquisition mode for acquiring the image of the survey target corresponding to the survey task are determined based on a predetermined natural space condition of the survey target.
Specifically, the site panoramic investigation method provided by the embodiment of the invention is fully automatic, so that the measurement and drawing of the investigation target do not need to be manually carried out, and the acquired images are uniformly adopted and then the acquired images are processed to obtain the corresponding three-dimensional model. Since the survey tasks include machine room internal survey modeling, pole surrounding environment modeling and pole wide range environment modeling, different survey tasks and different environmental conditions of the survey targets require selection of appropriate image acquisition equipment and methods. Especially for site environment modeling, because the three-dimensional model needs to be restored based on the image, and the three-dimensional model needs rich image information, the requirement on the acquired image is higher, so that the natural light intensity and the equipment texture richness in the machine room can influence the equipment and the acquisition method for acquiring the images in the machine room during the machine room internal survey modeling, and the space environment conditions (such as weather conditions and the volume of objects in the environment) of the surrounding of the holding pole and the large-scale environment of the holding pole can also influence the modeling of the surrounding environment of the holding pole. For different light conditions, the inside of a machine room with different texture conditions and outdoor environments with different weather conditions, corresponding image acquisition technologies can be selected, for example, a structured light depth camera is more suitable for close-range shooting with general light and lacking texture of object equipment, a binocular camera is more suitable for close-range shooting with rich texture of an object, a camera and a laser radar are suitable for any situation only with higher cost, and outdoor image acquisition is usually carried by an unmanned aerial vehicle to fly around and then shoot. Therefore, the method adopting different equipment and the mode of collecting images is more suitable for the exploration target, and the trouble that the image shooting effect is poor and finally a powerful image processing algorithm is required to process images with different qualities due to the use of unified collecting equipment is avoided.
And 130, recovering the three-dimensional model based on the image, and sending the three-dimensional model to a survey platform as a task result for release.
Specifically, for the above survey task, after the image acquisition equipment and the image acquisition method adapted to the survey target are determined, image acquisition is performed, the three-dimensional model reconstruction process is performed on the acquired image, generally, point cloud data is obtained based on depth data, point cloud registration and fusion are performed, finally, the surface is generated, and finally, the generated three-dimensional model is transmitted to the viewing platform as a task result for release. Specifically, the server is set up on the intranet, the three-dimensional model is uploaded to the server, and then a person who needs to view the three-dimensional model can log in the server website to view the three-dimensional model without downloading, for example: the registers 360 and TrueView Enterprise are used for automatic stitching, distance measurement and release of results. When a person needing to check the three-dimensional model logs in the server website, the model to be checked is selected, a mouse roller can be used for zooming in and out, a visual angle is adjusted by moving the mouse, the jump is realized by clicking the acquisition point, the distance measuring function is selected from a menu, then any two points except sky in the model are clicked, and the distance and the distances of an X axis, a Y axis and a Z axis can be measured.
The method provided by the embodiment of the invention receives the exploration task, wherein the exploration task comprises the internal exploration modeling of a machine room, the surrounding environment modeling of the holding pole and the large-scale environment modeling of the holding pole; acquiring images of the survey targets corresponding to the survey tasks, wherein acquisition equipment and acquisition modes for acquiring the images of the survey targets corresponding to the survey tasks are determined based on the predetermined natural space conditions of the survey targets; and carrying out three-dimensional model recovery based on the image, and sending the three-dimensional model as a task result to an exploration platform for release. Therefore, according to different types of the survey task and different selection of natural space conditions of the survey target corresponding to the survey task, the image acquisition equipment and the method are suitable, finally, the recognition result or the three-dimensional modeling obtained by recognition or three-dimensional modeling based on the acquired image is returned as the result of the survey task, the automation of the survey flow and the automatic return sharing of the result are realized, and the three-dimensional model serving as the completion result of the task can provide more information for convenient display. Therefore, the real-time intelligent site panoramic investigation method provided by the embodiment of the invention realizes the high efficiency, low labor cost, large investigation result information quantity, easy display and convenient sharing of site panoramic investigation.
Based on the above embodiment, the method further includes:
if the exploration target is the inside of the machine room, the natural space condition is natural light intensity and equipment texture richness;
if the exploration target is the surrounding environment of the holding pole, the natural space condition is the surrounding rain and fog condition of the holding pole;
if the exploration target is a pole large-range environment, the natural space condition is the volume of an object in the pole large-range environment.
Specifically, for different survey targets, the natural space conditions that may be affected by the acquisition equipment and the acquisition mode for image acquisition are also different. When the exploration target is in a machine room, the influence of natural light intensity and equipment texture richness on image acquisition is mainly considered, when the exploration target is in a pole surrounding environment, the influence of weather conditions around the pole is mainly considered, and when the exploration target is in a pole large-range environment, the influence of the volume of objects in the pole large-range environment is mainly considered. The above-mentioned natural space conditions are all state data which can be directly acquired, predetermined and then stored.
Based on any of the foregoing embodiments, in the method, the capturing device and the capturing manner for capturing the image of the survey target corresponding to the survey task are determined based on a predetermined natural spatial condition of the survey target, and specifically include:
the method specifically comprises the following steps:
when the survey task models a machine room interior survey,
if the natural light intensity is low and the equipment texture is lacking, moving and shooting in a machine room by using the SLAM robot to carry a structured light depth camera;
if the natural light intensity is proper and the equipment texture is rich, the SLAM robot is used for carrying a binocular camera to shoot in a machine room in a moving way;
if any condition is not met, the SLAM robot is used for carrying a camera and a laser radar to shoot in a machine room in a moving way;
when the survey task models the surrounding environment of the pole,
if no rain and fog exist, the unmanned aerial vehicle is used for carrying a camera and a laser radar to fly around the pole and shoot;
when the survey task models a wide range of pole environments,
if the object volume is larger in the wide-range environment of the holding pole, using the unmanned aerial vehicle to carry a camera to fly around and shoot in the wide-range environment of the holding pole;
if the object volume is smaller in the wide-range environment of the holding pole, the unmanned aerial vehicle is used for carrying the camera and the laser radar to fly around and shoot in the wide-range environment of the holding pole.
Specifically, when the survey task is to model the survey in the machine room, if the natural light intensity is low and the equipment texture is lacking, the SLAM robot is used for carrying the structured light depth camera to shoot the movement in the machine room. The natural light intensity is low, and the equipment texture lack is a pre-determined natural space condition which can be directly obtained, namely, the natural light intensity and the equipment texture richness in the machine room are determined in advance through the intensity detection of the natural light and the detection and the determination of the equipment texture richness, and the detection and the determination methods are various and common and are not specifically described herein. The moving shooting of the SLAM robot carrying structured light depth camera in the machine room refers to moving shooting of the robot carrying structured light depth camera in the machine room by using an SLAM (Simultaneous Localization And Mapping, synchronous positioning and mapping) algorithm, which is originally applied to the field of robots, and aims to construct a surrounding environment map according to sensor data without any prior knowledge, and meanwhile, presume the position of the robot carrying sensor (camera) in an unknown environment according to the map, and the moving moment t=1, 2, …, k corresponds to the positions x1, x2, i. Assuming that the map consists of n roadmap y1, y2, yn, each time instant camera will measure a portion of the roadmap data, solving the localization problem (estimate x) and mapping problem (estimate y) by motion measurement and sensor readings. When the robot shoots in a machine room in a moving way, a preset route and the stay time of the acquisition points are used for shooting in the moving way, usually, the acquisition points are selected on the ground between cabinets, important equipment needs to be close to the ground, the distance between every two acquisition points cannot exceed the measurement distance of a camera, the whole machine room can be covered by adding up the measurement ranges of all the acquisition point cameras, the more the number of the acquisition points, the more accurate the generated three-dimensional model is, and according to the measurement distance of the cameras and the complexity of the environment of the machine room, the stay time of each point is generally within one minute, and the whole acquisition process generally needs within ten minutes. When the survey task is the survey modeling in the machine room, if the natural light intensity is low and the equipment texture is lack, the SLAM robot is used for carrying the structured light depth camera to shoot in the machine room in a moving way, the preset route and the stay time of the collection points are used for shooting in a moving way, usually, the collection points are generally selected on the ground between the machine cabinets and need to be close to important equipment, the distance between every two collection points cannot exceed the measurement distance of the camera, the whole machine room can be covered by adding up the measurement ranges of all the collection point cameras, the more the number of the collection points, the more accurate the generated three-dimensional model is, and according to the measurement distance of the camera and the complexity of the machine room environment, each point generally stays for a plurality of minutes, and the whole collection process generally needs half an hour to one hour. When the surveying task is modeling of surveying in a machine room, the SLAM robot is used for carrying a camera and a laser radar to shoot in the machine room, wherein the natural space condition is not low in natural light intensity and lack of equipment textures, and the natural space condition is not proper in natural light intensity and rich in equipment textures. The laser radar is more suitable for being used as the acquisition equipment of depth information under the condition that natural environment is bad, the preset route and the stay time of acquisition points are used for carrying out movement shooting, in general, the selection of the acquisition points is on the ground between cabinets, important equipment needs to be close to, the distance between every two acquisition points cannot exceed the measurement distance of a camera and the laser radar, the measurement ranges of the camera and the laser radar at all the acquisition points can be added up to cover the whole machine room, the more the number of the acquisition points is, the more accurate the generated three-dimensional model is, the stay time of each point is generally within one minute according to the measurement distance of the camera and the laser radar and the complexity of the machine room environment, and the whole acquisition process generally needs to be within ten minutes. When the survey task is modeling of surrounding environment of the holding pole, if no rain and fog exist, the unmanned aerial vehicle is used for carrying a camera and a laser radar to fly around the periphery of the holding pole and shoot; if rain or fog exists, the weather is bad, and image acquisition cannot be performed, so that the investigation task cannot be performed, and only the weather is restored to be normal, and then the acquisition is continued. When the survey task is modeling of the wide-range environment of the holding pole, if the object volume in the wide-range environment of the holding pole is large, the unmanned aerial vehicle carrying camera is used for carrying out winding flight and shooting in the wide-range environment of the holding pole, the object volume is large, the object can be identified even if the common camera is used for shooting, particularly under the condition of low modeling precision requirement, the unmanned aerial vehicle carrying camera is used for carrying out winding flight and shooting in the wide-range environment of the holding pole, and the range size acquired according to the requirement is in the air of tens of meters to fly until all parts in the environment are covered, and the winding flight is needed for many times; if the object volume is smaller in the pole-holding large-scale environment, the unmanned aerial vehicle is used for carrying the camera and the laser radar to fly around and shoot in the pole-holding large-scale environment, the object volume is small, namely the camera and the laser radar are needed to be added, especially under the condition that the modeling precision requirement is high, the unmanned aerial vehicle is used for carrying the camera and the laser radar to fly around and shoot in the pole-holding environment, the acquired range size is in the air of tens of meters according to the requirement, and the unmanned aerial vehicle flies around for many times until all parts in the environment are covered.
Based on any one of the foregoing embodiments, in the method, the performing three-dimensional model restoration based on the image specifically includes:
performing feature matching on the image based on a SIFT operator to obtain a matched feature point pair;
computing a basic matrix for the matched characteristic point pairs by adopting a RANSAC eight-point method, and eliminating the matched characteristic point pairs which do not meet the basic matrix;
and then reconstructing the matched characteristic point pairs after being removed by using CMVS and PMVS algorithms to obtain a three-dimensional model.
Specifically, image feature extraction and matching are performed first: the method mainly uses a Scale Invariant Feature Transform (SIFT) operator for extraction, SIFT features are independent of the size and rotation of an image based on interest points of some local appearances on an object, have scale and rotation invariance, have quite high tolerance to light, noise and micro-view change, have strong robustness, are suitable for extracting various picture feature point information of scale transformation and rotation angle, and have strong accuracy; secondly, performing sparse point cloud reconstruction: for reconstruction, the erroneous matches in the matching points are first removed. In order to solve the situation that one characteristic point in an image is possibly matched with a plurality of characteristic points, a situation of many-to-one exists, the characteristic points are in one-to-one correspondence in reality, a sampling consistency algorithm RANSAC eight-point method is adopted for the matched points to calculate a basic matrix, matching pairs which do not meet the basic matrix are removed, after one pair of correct matched points exist, depth information of corresponding three-dimensional points can be restored by a triangulation method, more images are added, matching is carried out with the previous images, three-dimensional point information is calculated, and therefore sparse point cloud is formed; finally, dense point cloud reconstruction is performed: after the sparse point cloud reconstruction, CMVS (clustering multi-view stereoo) and PMVS (patch-based multi-view stereoo) are generally used for dense point cloud reconstruction, and more three-dimensional information is recovered so as to better establish a three-dimensional model, wherein the CMVS filters out images with higher overlapping degree through an image clustering algorithm, the number of images required to be processed by a subsequent PMVS algorithm is reduced, and the PMVS obtains the final dense point cloud through multi-view matching of small-block images.
Based on any one of the above embodiments, the embodiment of the present invention provides a real-time smart site panoramic survey device, and fig. 2 is a schematic structural diagram of the real-time smart site panoramic survey device provided by the embodiment of the present invention. As shown in fig. 2, the apparatus includes a receiving unit 210, an acquisition unit 220, and a calculation unit 230, wherein,
the receiving unit 210 is configured to receive a survey task, where the survey task includes a machine room interior survey modeling, a pole surrounding environment modeling, and a pole large-scale environment modeling;
the collecting unit 220 is configured to collect an image of the survey target corresponding to the survey task, where a collecting device and a collecting manner for collecting the image of the survey target corresponding to the survey task are determined based on a predetermined natural space condition of the survey target;
the computing unit 230 is configured to perform three-dimensional model restoration based on the image, and send the three-dimensional model as a task result to a exploration platform for publishing.
The device provided by the embodiment of the invention receives the exploration task, wherein the exploration task comprises the internal exploration modeling of a machine room, the surrounding environment modeling of the holding pole and the large-scale environment modeling of the holding pole; acquiring an image of the survey task corresponding to the survey target, wherein,
the acquisition equipment and the acquisition mode for acquiring the images of the exploration targets corresponding to the exploration tasks are determined based on the predetermined natural space conditions of the exploration targets; and carrying out three-dimensional model recovery based on the image, and sending the three-dimensional model as a task result to an exploration platform for release. Therefore, according to different types of the survey task and different selection of natural space conditions of the survey target corresponding to the survey task, the image acquisition equipment and the method are suitable, finally, the recognition result or the three-dimensional modeling obtained by recognition or three-dimensional modeling based on the acquired image is returned as the result of the survey task, the automation of the survey flow and the automatic return sharing of the result are realized, and the three-dimensional model serving as the completion result of the task can provide more information for convenient display. Therefore, the real-time intelligent site panoramic survey device provided by the embodiment of the invention realizes high efficiency, low labor cost, large information quantity of the survey result, easy display and convenient sharing of site panoramic survey.
Based on any of the foregoing embodiments, the apparatus further includes:
if the exploration target is the inside of the machine room, the natural space condition is natural light intensity and equipment texture richness;
if the exploration target is the surrounding environment of the holding pole, the natural space condition is the surrounding rain and fog condition of the holding pole;
if the exploration target is a pole large-range environment, the natural space condition is the volume of an object in the pole large-range environment.
Based on any one of the above embodiments, in the apparatus, the capturing device and the capturing manner for capturing the image of the survey target corresponding to the site environment modeling are determined based on a predetermined natural space condition of the survey target, and specifically include:
when the survey task models a machine room interior survey,
if the natural light intensity is low and the equipment texture is lacking, moving and shooting in a machine room by using the SLAM robot to carry a structured light depth camera;
if the natural light intensity is proper and the equipment texture is rich, the SLAM robot is used for carrying a binocular camera to shoot in a machine room in a moving way;
if any condition is not met, the SLAM robot is used for carrying a camera and a laser radar to shoot in a machine room in a moving way;
when the survey task models the surrounding environment of the pole,
if no rain and fog exist, the unmanned aerial vehicle is used for carrying a camera and a laser radar to fly around the pole and shoot;
when the survey task models a wide range of pole environments,
if the object volume is larger in the wide-range environment of the holding pole, using the unmanned aerial vehicle to carry a camera to fly around and shoot in the wide-range environment of the holding pole;
if the object volume is smaller in the wide-range environment of the holding pole, the unmanned aerial vehicle is used for carrying the camera and the laser radar to fly around and shoot in the wide-range environment of the holding pole.
Based on any of the foregoing embodiments, in the apparatus, the device for acquiring the image of the survey target corresponding to the survey task and the acquisition mode are determined based on a predetermined natural spatial condition of the survey target, and specifically include:
performing feature matching on the image based on a SIFT operator to obtain a matched feature point pair;
computing a basic matrix for the matched characteristic point pairs by adopting a RANSAC eight-point method, and eliminating the matched characteristic point pairs which do not meet the basic matrix;
and then reconstructing the matched characteristic point pairs after being removed by using CMVS and PMVS algorithms to obtain a three-dimensional model.
Fig. 3 is a schematic physical structure of an electronic device according to an embodiment of the present invention, where, as shown in fig. 3, the electronic device may include: processor 301, communication interface (Communications Interface) 302, memory (memory) 303 and communication bus 304, wherein processor 301, communication interface 302, memory 303 accomplish the communication between each other through communication bus 304. The processor 301 may invoke a computer program stored in the memory 303 and executable on the processor 301 to perform the real-time smart site panorama survey method provided by the above embodiments, including, for example: receiving a survey task, wherein the survey task comprises machine room internal survey modeling, pole surrounding environment modeling and pole large-scale environment modeling; acquiring images of the survey targets corresponding to the survey tasks, wherein acquisition equipment and acquisition modes for acquiring the images of the survey targets corresponding to the survey tasks are determined based on the predetermined natural space conditions of the survey targets; and carrying out three-dimensional model recovery based on the image, and sending the three-dimensional model as a task result to an exploration platform for release.
Further, the logic instructions in the memory 303 may be implemented in the form of software functional units and stored in a computer readable storage medium when sold or used as a stand alone product. Based on such understanding, the technical solution of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art or a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Embodiments of the present invention also provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the real-time smart site panorama investigation method provided by the above embodiments, for example, comprising: receiving a survey task, wherein the survey task comprises machine room internal survey modeling, pole surrounding environment modeling and pole large-scale environment modeling; acquiring images of the survey targets corresponding to the survey tasks, wherein acquisition equipment and acquisition modes for acquiring the images of the survey targets corresponding to the survey tasks are determined based on the predetermined natural space conditions of the survey targets; and carrying out three-dimensional model recovery based on the image, and sending the three-dimensional model as a task result to an exploration platform for release.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A real-time smart site panoramic survey method, comprising:
receiving a survey task, wherein the survey task comprises machine room internal identification and site environment modeling, the machine room internal identification comprises machine room cabinet vacancy identification and machine room equipment identification, and the site environment modeling comprises machine room internal survey modeling, pole surrounding environment modeling and pole large-scale environment modeling;
acquiring images of the exploration targets corresponding to the exploration tasks, wherein acquisition equipment and acquisition modes for acquiring the images of the exploration targets corresponding to the site environment modeling are determined based on the predetermined natural space conditions of the exploration targets;
if the investigation task is the recognition in the machine room, performing character recognition and object recognition on the image, and returning the recognition result as a task result;
if the exploration task is site environment modeling, carrying out three-dimensional model recovery based on the image, and sending the three-dimensional model as a task result to a viewing platform for release;
performing three-dimensional model restoration based on the image, specifically including:
performing feature matching on the image based on a SIFT operator to obtain a matched feature point pair;
computing a basic matrix for the matched characteristic point pairs by adopting a RANSAC eight-point method, and eliminating the matched characteristic point pairs which do not meet the basic matrix;
restoring depth information of the corresponding three-dimensional points of the matched characteristic point pairs after removal by adopting a triangulation method, adding more images, matching with the previous images, calculating three-dimensional point information, and forming a sparse point cloud;
then, reconstructing dense point clouds of the matched characteristic point pairs after being removed by using CMVS and PMVS algorithms to obtain a three-dimensional model;
the CMVS algorithm filters out images with higher overlap ratio through an image clustering algorithm, reduces the number of images to be processed when the PMVS algorithm is used subsequently, and obtains a final dense point cloud through multi-view matching of small images.
2. The real-time smart site panorama survey method according to claim 1, further comprising:
if the exploration target is the inside of the machine room, the natural space condition is natural light intensity and equipment texture richness;
if the exploration target is the surrounding environment of the holding pole, the natural space condition is the surrounding rain and fog condition of the holding pole;
if the exploration target is a pole large-range environment, the natural space condition is the volume of an object in the pole large-range environment.
3. The real-time intelligent site panorama survey method according to claim 2, wherein the capturing device and capturing manner for capturing the image of the site environment modeling corresponding survey target are determined based on a predetermined natural space condition of the survey target, specifically comprising:
when the survey task models a machine room interior survey,
if the natural light intensity is low and the equipment texture is lacking, moving and shooting in a machine room by using the SLAM robot to carry a structured light depth camera;
if the natural light intensity is proper and the equipment texture is rich, the SLAM robot is used for carrying a binocular camera to shoot in a machine room in a moving way;
if any condition is not met, the SLAM robot is used for carrying a camera and a laser radar to shoot in a machine room in a moving way;
when the survey task models the surrounding environment of the pole,
if no rain and fog exist, the unmanned aerial vehicle is used for carrying a camera and a laser radar to fly around the pole and shoot;
when the survey task models a wide range of pole environments,
if the object volume is larger in the wide-range environment of the holding pole, using the unmanned aerial vehicle to carry a camera to fly around and shoot in the wide-range environment of the holding pole;
if the object volume is smaller in the wide-range environment of the holding pole, the unmanned aerial vehicle is used for carrying the camera and the laser radar to fly around and shoot in the wide-range environment of the holding pole.
4. A real-time intelligent site panoramic survey apparatus, comprising:
the system comprises a receiving unit, a storage unit and a storage unit, wherein the receiving unit is used for receiving an exploration task, the exploration task comprises machine room internal identification and station environment modeling, the machine room internal identification comprises machine room cabinet vacancy identification and machine room equipment identification, and the station environment modeling comprises machine room internal exploration modeling, pole surrounding environment modeling and pole large-scale environment modeling;
the acquisition unit is used for acquiring images of the survey targets corresponding to the survey tasks, wherein acquisition equipment and acquisition modes for acquiring the images of the survey targets corresponding to the site environment modeling are determined based on the predetermined natural space conditions of the survey targets;
the computing unit is used for carrying out character recognition and object recognition on the image if the investigation task is recognition in the machine room, and returning the recognition result as a task result; if the exploration task is site environment modeling, carrying out three-dimensional model recovery based on the image, and sending the three-dimensional model as a task result to a viewing platform for release;
performing three-dimensional model restoration based on the image, specifically including:
performing feature matching on the image based on a SIFT operator to obtain a matched feature point pair;
computing a basic matrix for the matched characteristic point pairs by adopting a RANSAC eight-point method, and eliminating the matched characteristic point pairs which do not meet the basic matrix;
restoring depth information of the corresponding three-dimensional points of the matched characteristic point pairs after removal by adopting a triangulation method, adding more images, matching with the previous images, calculating three-dimensional point information, and forming a sparse point cloud;
then, reconstructing dense point clouds of the matched characteristic point pairs after being removed by using CMVS and PMVS algorithms to obtain a three-dimensional model;
the CMVS algorithm filters out images with higher overlap ratio through an image clustering algorithm, reduces the number of images to be processed when the PMVS algorithm is used subsequently, and obtains a final dense point cloud through multi-view matching of small images.
5. The real-time smart site panorama survey apparatus of claim 4, further comprising:
if the exploration target is the inside of the machine room, the natural space condition is natural light intensity and equipment texture richness;
if the exploration target is the surrounding environment of the holding pole, the natural space condition is the surrounding rain and fog condition of the holding pole;
if the exploration target is a pole large-range environment, the natural space condition is the volume of an object in the pole large-range environment.
6. The real-time intelligent site panorama survey apparatus according to claim 5, wherein the capturing device and capturing manner for capturing the site environment modeling image of the corresponding survey target are determined based on a predetermined natural space condition of the survey target, specifically comprising:
when the survey task models a machine room interior survey,
if the natural light intensity is low and the equipment texture is lacking, moving and shooting in a machine room by using the SLAM robot to carry a structured light depth camera;
if the natural light intensity is proper and the equipment texture is rich, the SLAM robot is used for carrying a binocular camera to shoot in a machine room in a moving way;
if any condition is not met, the SLAM robot is used for carrying a camera and a laser radar to shoot in a machine room in a moving way;
when the survey task models the surrounding environment of the pole,
if no rain and fog exist, the unmanned aerial vehicle is used for carrying a camera and a laser radar to fly around the pole and shoot;
when the survey task models a wide range of pole environments,
if the object volume is larger in the wide-range environment of the holding pole, using the unmanned aerial vehicle to carry a camera to fly around and shoot in the wide-range environment of the holding pole;
if the object volume is smaller in the wide-range environment of the holding pole, the unmanned aerial vehicle is used for carrying the camera and the laser radar to fly around and shoot in the wide-range environment of the holding pole.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the real-time smart site panorama investigation method according to any of claims 1-3 when the program is executed by the processor.
8. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the real-time smart site panorama survey method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011112049.8A CN114390270B (en) | 2020-10-16 | 2020-10-16 | Real-time intelligent site panorama exploration method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011112049.8A CN114390270B (en) | 2020-10-16 | 2020-10-16 | Real-time intelligent site panorama exploration method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114390270A CN114390270A (en) | 2022-04-22 |
| CN114390270B true CN114390270B (en) | 2023-08-15 |
Family
ID=81194334
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011112049.8A Active CN114390270B (en) | 2020-10-16 | 2020-10-16 | Real-time intelligent site panorama exploration method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114390270B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006084385A1 (en) * | 2005-02-11 | 2006-08-17 | Macdonald Dettwiler & Associates Inc. | 3d imaging system |
| CN105023291A (en) * | 2015-05-22 | 2015-11-04 | 燕山大学 | Criminal scene reconstructing apparatus and method based on stereoscopic vision |
| CN106485655A (en) * | 2015-09-01 | 2017-03-08 | 张长隆 | A kind of taken photo by plane map generation system and method based on quadrotor |
| CN106780729A (en) * | 2016-11-10 | 2017-05-31 | 中国人民解放军理工大学 | A kind of unmanned plane sequential images batch processing three-dimensional rebuilding method |
| CN108375367A (en) * | 2018-01-25 | 2018-08-07 | 中铁第四勘察设计院集团有限公司 | Combined ground laser radar and the work of oblique photograph point surveying method and system |
| CN108765298A (en) * | 2018-06-15 | 2018-11-06 | 中国科学院遥感与数字地球研究所 | Unmanned plane image split-joint method based on three-dimensional reconstruction and system |
| CN109801358A (en) * | 2018-12-06 | 2019-05-24 | 宁波市电力设计院有限公司 | A kind of substation's three-dimensional investigation method scanning and put cloud visual fusion based on SLAM |
| CN110009218A (en) * | 2019-03-28 | 2019-07-12 | 云南电网有限责任公司临沧供电局 | A kind of intelligent substation safety work management-control method and system |
| CN111696194A (en) * | 2020-05-07 | 2020-09-22 | 广东康云科技有限公司 | Three-dimensional visualization implementation method and system based on field investigation and storage medium |
| CN111695424A (en) * | 2020-05-07 | 2020-09-22 | 广东康云科技有限公司 | Crime scene restoration method, crime scene restoration system and storage medium based on three-dimensional real scene |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9222771B2 (en) * | 2011-10-17 | 2015-12-29 | Kla-Tencor Corp. | Acquisition of information for a construction site |
| US9959625B2 (en) * | 2015-12-29 | 2018-05-01 | The United States Of America As Represented By The Secretary Of The Air Force | Method for fast camera pose refinement for wide area motion imagery |
-
2020
- 2020-10-16 CN CN202011112049.8A patent/CN114390270B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006084385A1 (en) * | 2005-02-11 | 2006-08-17 | Macdonald Dettwiler & Associates Inc. | 3d imaging system |
| CN105023291A (en) * | 2015-05-22 | 2015-11-04 | 燕山大学 | Criminal scene reconstructing apparatus and method based on stereoscopic vision |
| CN106485655A (en) * | 2015-09-01 | 2017-03-08 | 张长隆 | A kind of taken photo by plane map generation system and method based on quadrotor |
| CN106780729A (en) * | 2016-11-10 | 2017-05-31 | 中国人民解放军理工大学 | A kind of unmanned plane sequential images batch processing three-dimensional rebuilding method |
| CN108375367A (en) * | 2018-01-25 | 2018-08-07 | 中铁第四勘察设计院集团有限公司 | Combined ground laser radar and the work of oblique photograph point surveying method and system |
| CN108765298A (en) * | 2018-06-15 | 2018-11-06 | 中国科学院遥感与数字地球研究所 | Unmanned plane image split-joint method based on three-dimensional reconstruction and system |
| CN109801358A (en) * | 2018-12-06 | 2019-05-24 | 宁波市电力设计院有限公司 | A kind of substation's three-dimensional investigation method scanning and put cloud visual fusion based on SLAM |
| CN110009218A (en) * | 2019-03-28 | 2019-07-12 | 云南电网有限责任公司临沧供电局 | A kind of intelligent substation safety work management-control method and system |
| CN111696194A (en) * | 2020-05-07 | 2020-09-22 | 广东康云科技有限公司 | Three-dimensional visualization implementation method and system based on field investigation and storage medium |
| CN111695424A (en) * | 2020-05-07 | 2020-09-22 | 广东康云科技有限公司 | Crime scene restoration method, crime scene restoration system and storage medium based on three-dimensional real scene |
Non-Patent Citations (1)
| Title |
|---|
| 3D face reconstruction and multimodal person identification from video captured using smartphone camera;R. Raghavendra;2013 IEEE International Conference on Technologies for Homeland Security;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114390270A (en) | 2022-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108401461B (en) | Three-dimensional mapping method, device and system, cloud platform, electronic equipment and computer program product | |
| CN110766716B (en) | Method and system for acquiring information of space unknown moving target | |
| CN111199564B (en) | Indoor positioning method and device of intelligent mobile terminal and electronic equipment | |
| CN113592989B (en) | Three-dimensional scene reconstruction system, method, equipment and storage medium | |
| CN109472828B (en) | Positioning method, positioning device, electronic equipment and computer readable storage medium | |
| CN106529538A (en) | Method and device for positioning aircraft | |
| KR102200299B1 (en) | A system implementing management solution of road facility based on 3D-VR multi-sensor system and a method thereof | |
| CN111028358B (en) | Indoor environment augmented reality display method and device and terminal equipment | |
| WO2022077296A1 (en) | Three-dimensional reconstruction method, gimbal load, removable platform and computer-readable storage medium | |
| CN112634370A (en) | Unmanned aerial vehicle dotting method, device, equipment and storage medium | |
| CN111275015A (en) | Unmanned aerial vehicle-based power line inspection electric tower detection and identification method and system | |
| CN110470333A (en) | Scaling method and device, the storage medium and electronic device of sensor parameters | |
| CN106503248A (en) | Ground drawing generating method and map creation device | |
| CN111143489B (en) | Image-based positioning method and device, computer equipment and readable storage medium | |
| CN112348887A (en) | Terminal pose determining method and related device | |
| CN115588144A (en) | Real-time attitude capturing method, device and equipment based on Gaussian dynamic threshold screening | |
| CN114972646A (en) | Method and system for extracting and modifying independent ground objects of live-action three-dimensional model | |
| WO2022025283A1 (en) | Measurement processing device, method, and program | |
| CN114882106A (en) | Pose determination method and device, equipment and medium | |
| CN113987246A (en) | Automatic picture naming method, device, medium and electronic equipment for unmanned aerial vehicle inspection | |
| CN114390270B (en) | Real-time intelligent site panorama exploration method and device and electronic equipment | |
| CN114913246B (en) | Camera calibration method and device, electronic equipment and storage medium | |
| CN116266402A (en) | Automatic object labeling method and device, electronic equipment and storage medium | |
| CN113421332A (en) | Three-dimensional reconstruction method and device, electronic equipment and storage medium | |
| Zhang et al. | Point cloud registration with 2D and 3D fusion information on mobile robot integrated vision system |
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 |