CN113592865A - Quality inspection method and equipment for three-dimensional map and storage medium - Google Patents
Quality inspection method and equipment for three-dimensional map and storage medium Download PDFInfo
- Publication number
- CN113592865A CN113592865A CN202111147721.1A CN202111147721A CN113592865A CN 113592865 A CN113592865 A CN 113592865A CN 202111147721 A CN202111147721 A CN 202111147721A CN 113592865 A CN113592865 A CN 113592865A
- Authority
- CN
- China
- Prior art keywords
- quality inspection
- elements
- target
- frame
- original
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Abstract
The embodiment of the application provides a quality inspection method, equipment and a storage medium of a three-dimensional map, wherein the method comprises the steps of selecting a quality inspection frame from a plurality of image building frames before a current image building frame, wherein the image building frame is used for building the three-dimensional map; determining a search range according to the coordinates of the quality inspection frame, searching a plurality of map elements from the current three-dimensional map according to the search range, back-projecting the map elements to obtain a plurality of target elements back-projected into the quality inspection frame, matching the target elements with a plurality of original elements in the quality inspection frame, and determining a quality inspection result of the quality inspection frame according to a matching result to determine the quality inspection result of the three-dimensional map. According to the embodiment of the application, automatic quality inspection of the three-dimensional map is realized, unnecessary cost is not required to be invested to purchase advanced equipment, and the labor cost of manual quality inspection is saved.
Description
Technical Field
The embodiment of the application relates to the technical field of navigation and unmanned driving, in particular to a quality inspection method and equipment of a three-dimensional map and a storage medium.
Background
The high-precision map is an important technology for realizing automatic driving, and the high-precision map data can be acquired and fused in real time in a crowdsourcing mode in the manufacturing process of the high-precision map. The high-precision map obtained by fusion also needs to pass through a quality inspection link so as to ensure the quality of the high-precision map.
In the prior art, a manual quality inspection mode can be adopted, more advanced equipment can be adopted to construct a three-dimensional map, and the constructed three-dimensional map is used as a true value and is compared with the high-precision map obtained by the fusion to obtain a quality inspection result.
However, the inventors found in the invention study that the prior art has at least the following problems: higher cost is required for purchasing advanced equipment, and labor cost is wasted and efficiency is lower in manual quality inspection.
Disclosure of Invention
The embodiment of the application provides a quality inspection method, equipment and a storage medium of a three-dimensional map, so that map quality inspection can be automatically completed on the premise of ensuring low cost, and the quality inspection efficiency is improved.
In a first aspect, an embodiment of the present application provides a quality inspection method for a three-dimensional map, including:
selecting a quality inspection frame from a plurality of image building frames before the current image building frame; the map building frame is used for building a three-dimensional map;
determining a search range according to the coordinates of the quality inspection frame, and searching a plurality of map elements from the current three-dimensional map according to the search range;
carrying out back projection on the map elements to obtain a plurality of target elements which are back projected into the quality inspection frame;
and matching the target elements with the original elements in the quality inspection frame, and determining the quality inspection result of the quality inspection frame according to the matching result so as to determine the quality inspection result of the three-dimensional map.
In one possible design, the selecting a quality inspection frame from a plurality of mapping frames before the current mapping frame includes:
determining corresponding track distances between a plurality of image building frames before the current image building frame and the current image building frame;
and selecting the image building frame before the current image building frame with the track distance greater than or equal to a first preset distance as the quality inspection frame.
In one possible design, the determining a search range according to the coordinates of the quality inspection frame includes:
and determining a range in which the distance between the front of the center and the center is less than or equal to a second preset distance as the search range by taking the coordinate of the quality inspection frame as the center and the acquisition direction of the quality inspection frame as the front.
In one possible design, the back-projecting the plurality of map elements to obtain a plurality of target elements back-projected into the quality inspection frame includes:
converting coordinates of a plurality of the map elements from a world coordinate system to a camera coordinate system;
according to an internal reference matrix of a camera, carrying out back projection on the map elements after coordinate conversion to a plane where the quality inspection frame is located, and obtaining pixel coordinates of the map elements after back projection;
and screening the plurality of target elements from the plurality of map elements after the back projection according to the pixel coordinates of the boundary of the quality inspection frame.
In one possible design, the matching the plurality of target elements with the plurality of original elements in the quality inspection frame includes:
calculating a first pixel distance between each original element and each target element;
and if the minimum distance in the first pixel distances is smaller than a third preset distance, judging that the target element corresponding to the minimum distance is successfully matched with the original element.
In one possible design, the target elements are linear elements, and the calculating a first pixel distance between each of the target elements and each of the original elements includes:
constructing a k-dimensional tree according to each target element;
according to the k-dimensional tree, calculating second pixel distances from each point in the original elements to the target elements to obtain a plurality of second pixel distances;
determining the first pixel distance between the original element and the target element according to a plurality of the second pixel distances.
In one possible design, the target elements are planar elements, and the calculating a first pixel distance between each of the original elements and each of the target elements includes:
screening target points outside the boundary of the target element from each point in the original element;
for each target point, calculating a third pixel distance of the target point to the boundary of the target element;
determining the first pixel distance between the original element and the target element according to a plurality of the third pixel distances.
In one possible design, before calculating, for each of the original elements, a first pixel distance between the original element and each of the target elements, the method further includes:
dividing a plurality of original elements and a plurality of target elements into a plurality of target categories according to semantic information of the plurality of target elements and semantic information of the plurality of original elements;
for each original element, calculating a first pixel distance between the original element and each target element respectively includes:
for a plurality of target original elements and a plurality of target elements in each target category, calculating a first pixel distance between each original element and each target element.
In a possible design, if a minimum distance among the plurality of first pixel distances is smaller than a third preset distance, determining the minimum distance as a matching distance, and determining a quality inspection result of the quality inspection frame according to the matching result, includes:
determining the completeness corresponding to the quality inspection frame according to the number of the successfully matched original elements and the total amount of the plurality of original elements;
determining the accuracy corresponding to the quality inspection frame according to the number of the successfully matched original elements and the total amount of the plurality of target elements;
determining the corresponding precision of the quality inspection frame according to the plurality of matching distances and the total amount of the plurality of matching distances;
and determining the completeness, accuracy and precision corresponding to the quality inspection frame as the quality inspection result.
In a second aspect, an embodiment of the present application provides a quality inspection apparatus for a three-dimensional map, including:
the selection module is used for selecting a quality inspection frame from a plurality of image establishing frames before the current image establishing frame; the map building frame is used for building a three-dimensional map;
the searching module is used for determining a searching range according to the coordinates of the quality inspection frame and searching a plurality of map elements from the current three-dimensional map according to the searching range;
the back projection module is used for back projecting the map elements to obtain a plurality of target elements back projected into the quality inspection frame;
and the matching module is used for matching the target elements with the original elements in the quality inspection frame and determining the quality inspection result of the quality inspection frame according to the matching result so as to determine the quality inspection result of the three-dimensional map.
In a third aspect, an embodiment of the present application provides a quality inspection apparatus for a three-dimensional map, including: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executes computer-executable instructions stored by the memory to cause the at least one processor to perform the method as set forth in the first aspect above and in various possible designs of the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the method according to the first aspect and various possible designs of the first aspect are implemented.
In the quality inspection method, the quality inspection equipment and the storage medium of the three-dimensional map provided by the embodiment, the quality inspection frame is selected from a plurality of image-creating frames before the current image-creating frame, and the image-creating frame is used for constructing the three-dimensional map; determining a search range according to the coordinates of the quality inspection frame, searching a plurality of map elements from the current three-dimensional map according to the search range, back-projecting the map elements to obtain a plurality of target elements back-projected into the quality inspection frame, matching the target elements with a plurality of original elements in the quality inspection frame, and determining a quality inspection result of the quality inspection frame according to a matching result to determine the quality inspection result of the three-dimensional map.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a schematic diagram illustrating a principle of a quality inspection method of a three-dimensional map according to an embodiment of the present application;
fig. 2 is a first flowchart illustrating a quality inspection method for a three-dimensional map according to an embodiment of the present disclosure;
FIG. 3 is a diagram of a quality inspection frame including a back projected target element and an original element according to an embodiment of the present disclosure;
fig. 4 is a flowchart illustrating a second method for quality inspection of a three-dimensional map according to an embodiment of the present disclosure;
fig. 5 is a third schematic flowchart of a quality inspection method for a three-dimensional map according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a quality inspection apparatus for a three-dimensional map according to an embodiment of the present disclosure;
fig. 7 is a schematic hardware structure diagram of a quality inspection apparatus for a three-dimensional map according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
High-precision maps are important technologies for realizing automatic driving. The traditional method for manufacturing the high-precision map comprises an external operation part and an internal operation part. The external operation refers to acquiring original data of the high-precision map through a professional acquisition vehicle and is called external operation, and the internal operation refers to fusing the original data to generate the high-precision map and performing quality inspection on the fused high-precision map. The internal work may adopt an off-line mode in which quality inspection is performed manually. The method comprises the steps of acquiring a three-dimensional map, acquiring a high-precision map data, and establishing a crowd-sourcing mode, wherein the crowd-sourcing mode is used for acquiring and fusing the high-precision map data in real time. The crowdsourcing mode can improve the efficiency of high-precision map production.
However, the high-precision map obtained by the traditional production method or the later production method of the crowdsourcing mode depends on manpower in the quality inspection link, so that the labor cost is increased, and the efficiency is low. Although, for the crowdsourcing mode, a higher-precision map can be made by introducing more advanced software and hardware as a true value to perform quality inspection on the high-precision map obtained by the crowdsourcing mode, the software and hardware costs of the crowdsourcing scheme are undoubtedly and greatly increased.
In order to solve the above technical problem, the inventor has studied and found that, in the crowdsourcing mode, as image frame acquisition is increased, a three-dimensional map is also built more and more abundantly as more elements of a close-range part in a mapping frame are added, and the three-dimensional map includes more elements, at this time, various aspects of the three-dimensional map can be checked through various original elements (whether a far-range element or a close-range element used for building the three-dimensional map) included in a certain image frame (which may be named a quality inspection frame) acquired previously, for example, whether various original elements in a quality inspection frame are completely included in a current three-dimensional map can be detected. Based on this, the embodiment of the application provides a quality inspection method for a three-dimensional map, which can realize automatic quality inspection of the three-dimensional map, does not need to invest redundant cost to purchase advanced equipment, and saves the labor cost of manual quality inspection.
Fig. 1 is a schematic diagram illustrating a principle of a quality inspection method of a three-dimensional map according to an embodiment of the present application. As shown in fig. 1, as the acquisition device travels along the track indicated by the dotted line in fig. 1, a plurality of map frames (map frame 1, map frame 2, map frame 3, … …, map frame m-1, map frame m +1, … …, map frame n-1, and map frame n) are sequentially acquired, and when one map frame is acquired, part of elements (for example, a plurality of elements in a close view) in the map frame are added to the three-dimensional map, and the elements in the three-dimensional map are more and more abundant through the construction of the continuously acquired map frames. When the image frame n is acquired, namely the image frame n is the current image frame, at this time, a certain image frame before the image frame n can be selected, for example, the image frame m can be selected as a quality inspection frame, and the quality inspection result of the quality inspection frame is obtained by checking the matching condition of each original element in the quality inspection frame and each map element in the range of the quality inspection frame back projected in the current three-dimensional map, so that the quality inspection result of the three-dimensional map is obtained.
The technical solution of the present application will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
Fig. 2 is a first flowchart of a quality inspection method for a three-dimensional map according to an embodiment of the present disclosure. As shown in fig. 2, the method includes:
201. selecting a quality inspection frame from a plurality of image building frames before the current image building frame; and the map building frame is used for building a three-dimensional map.
The execution subject of the embodiment may be a device with data processing capability, such as a computer, a tablet, a mobile phone terminal, and a medical device, and the device may be disposed on a collection vehicle as shown in fig. 1.
In a specific implementation process, the acquisition device performs image acquisition in the advancing process, and the acquired image frames are image building frames which are used for building a map, such as a three-dimensional point cloud map. After the plurality of mapping frames are acquired, one mapping frame can be selected from a plurality of mapping frames before the current mapping frame to serve as a quality inspection frame. By matching each original element in the quality inspection frame with each map element in the current three-dimensional map which can be back-projected into the range of the quality inspection frame, each aspect of quality inspection of the map elements can be performed on the part corresponding to the quality inspection frame in the current three-dimensional map according to the matching result.
In this embodiment, there are multiple manners of selecting the quality inspection frame, and in an implementation manner, the quality inspection frame may be selected according to: firstly, determining track distances of acquisition equipment corresponding to a plurality of image building frames before a current image building frame and the current image building frame, and then selecting the image building frame before the current image building frame with the track distance being more than or equal to a first preset distance as the quality inspection frame. Specifically, the acquisition of the mapping frame by the acquisition device is performed in the driving process, different track distances exist between the current mapping frame and each mapping frame before, and the track distance between the current mapping frame and each mapping frame before is the distance between the position of the acquisition device corresponding to the acquisition time of the mapping frame before and the position of the acquisition device corresponding to the acquisition time of the mapping frame before. In the process of constructing the three-dimensional map, elements of a near view with higher precision in a currently acquired mapping frame are usually added into the current three-dimensional map, the elements of a far view in the mapping frame need to continuously acquire more mapping frames along with continuous forward driving of acquisition equipment, and the elements of the near view in the more mapping frames are added into the three-dimensional map so as to be seen in the three-dimensional map. That is, the construction of map elements in the three-dimensional map (elements selected from each mapping frame in the close view with higher precision for adding into the three-dimensional map) lags behind the acquisition time of each original element in the mapping frame (including elements in the close view and elements in the distant view), so that the mapping frame with the track distance greater than or equal to the first preset distance can be selected as the quality inspection frame. For example, the first preset distance may be set to a value of 100 m or more. In another implementation, the xth frame before the current frame may be selected as the quality inspection frame. The value of X can be set according to the travel speed of the acquisition device and the image acquisition frequency. As long as each original element in the selected quality inspection frame is constructed into the current three-dimensional map, that is, each original element in the quality inspection frame can be searched in each map element of the current three-dimensional map, and the specific selection manner of the quality inspection frame is not limited in this embodiment.
202. And determining a search range according to the coordinates of the quality inspection frame, and searching a plurality of map elements from the current three-dimensional map according to the search range.
In this embodiment, the map elements of the three-dimensional map refer to elements which are selected from each mapping frame and used for adding into the three-dimensional map in a close view with higher precision.
In this embodiment, there are various determination manners of the search range, and in an implementation manner, a circle may be drawn by taking a coordinate where the acquisition device is located when acquiring the quality inspection frame as a center and taking the second preset distance as a radius, and a range of the circle may be taken as the search range. In another implementation manner, considering that each original element in the quality inspection frame needs to be further acquired through each mapping frame after the quality inspection frame to be built into the three-dimensional map, a search range may be defined only after the quality inspection frame, that is, in a direction forward from the acquisition direction, and specifically, a range in which a distance between the front of the center and the center is less than or equal to a second preset distance may be determined as the search range by taking the coordinate of the quality inspection frame as the center and the acquisition direction of the quality inspection frame as the front. The setting of the second preset distance may be empirically set, and may be equal to or greater than 50 meters for example. The present embodiment does not limit the determination method of the search range.
In practical applications, after the search range is selected, all map elements within the search range are searched for in the three-dimensional map. Of course, some map elements may be selected from all map elements as the plurality of map elements according to actual needs.
203. And carrying out back projection on the map elements to obtain a plurality of target elements which are back projected into the quality inspection frame.
In this embodiment, the process of obtaining a plurality of target elements back-projected into the quality inspection frame may include the following steps: converting coordinates of a plurality of the map elements from a world coordinate system to a camera coordinate system; according to an internal reference matrix of a camera, carrying out back projection on the map elements after coordinate conversion to a plane where the quality inspection frame is located, and obtaining pixel coordinates of the map elements after back projection; and screening the plurality of target elements from the plurality of map elements after the back projection according to the pixel coordinates of the boundary of the quality inspection frame. The world coordinate system can be a coordinate system of a three-dimensional world defined by a user and used for describing the position of a target object in the real world, and the unit can be meter; the camera coordinate system is a coordinate system established on the camera, can describe the position of a target object from the angle of the camera, and is used as a middle ring for communicating a world coordinate system and a pixel coordinate system, and the unit can be meter; the pixel coordinate system is introduced for describing the coordinates of the image point imaged by the target object on the digital image, and is the coordinate system where the image information read from the camera is located. The unit is one (number of pixels).
Specifically, for each map element, coordinate system conversion can be performed by the following expression (1):
wherein the content of the first and second substances,
are the coordinates of the map elements in the camera coordinate system,
coordinates of the map elements in a world coordinate system;
a rotation matrix from a world coordinate system to a camera coordinate system;
a translation vector from a world coordinate system to a camera coordinate system;
for each map element converted into the camera coordinate system, the map element can be back-projected to the plane of the quality inspection frame through the following expressions (2) to (4):
wherein the content of the first and second substances,
is an internal reference matrix of the camera;
，
respectively, the pixel coordinates of the map elements back projected to the plane where the quality inspection frame is located.
204. And matching the target elements with the original elements in the quality inspection frame, and determining the quality inspection result of the quality inspection frame according to the matching result so as to determine the quality inspection result of the three-dimensional map.
Fig. 3 is a schematic diagram of a quality inspection frame including a back-projected target element and an original element according to an embodiment of the present application. The quality inspection frame may include a plurality of original elements, such as a left edge, a right edge, a center line of a road, and a sign suspended from the road, as shown in fig. 3, the sign corresponds to a first original element of the plurality of original elements, the left edge corresponds to a second original element of the plurality of original elements, a first target element of the plurality of target elements back-projected into the quality inspection frame corresponds to the first original element, and the second target element corresponds to the second original element. In a specific implementation process, a quality inspection result of the quality inspection frame may be determined according to a matching result between the first target element and the first original element, a matching result between the second target element and the second original element, and a matching result between other multiple target elements and multiple original elements. For example, in the matching process, the matching result may be represented by coloring the target element and the original element to improve the visualization effect, for example, if the first original element and the first target element are successfully matched, the first original element and the first target element may be colored green at the same time, and if the second original element and the second target element are successfully matched, the second original element and the second target element may be colored yellow at the same time, so that the matching result of the two elements can be clearly and intuitively represented in the same color.
Illustratively, aspects of quality inspection in quality inspection may include the completeness, accuracy, etc. of the quality inspection frame. The completeness of the quality inspection frame may be defined as whether all the original elements in the quality inspection frame are constructed in the current three-dimensional map, for example, 10 original elements (for example, the original elements corresponding to 2 central dotted lines, the original elements corresponding to 2 central solid lines, the original elements corresponding to 1 left side line, the original elements corresponding to 1 right side line, and the original elements corresponding to 4 signs) are included in the quality inspection frame, and if the number of successful matches between the multiple original elements and the multiple target elements in the quality inspection frame in the matching result is 8, the completeness is 80%. The accuracy of the quality inspection frame can be defined as the ratio between the number of the plurality of original elements in the quality inspection frame successfully matched with the plurality of target elements and the total number of the plurality of target elements back projected into the quality inspection frame. For example, if there are 12 original elements in the quality inspection frame, there are 10 target elements in the quality inspection frame that are back-projected by the three-dimensional map, and the number of successful matches between the original elements and the target elements in the quality inspection frame in the matching result is 8, the accuracy is 80%.
In the quality inspection method for the three-dimensional map provided by the embodiment, a quality inspection frame is selected from a plurality of image building frames before a current image building frame, and the image building frame is used for building the three-dimensional map; determining a search range according to the coordinates of the quality inspection frame, searching a plurality of map elements from the current three-dimensional map according to the search range, back-projecting the map elements to obtain a plurality of target elements back-projected into the quality inspection frame, matching the target elements with a plurality of original elements in the quality inspection frame, and determining a quality inspection result of the quality inspection frame according to a matching result to determine the quality inspection result of the three-dimensional map.
Fig. 4 is a flowchart illustrating a second method for quality inspection of a three-dimensional map according to an embodiment of the present disclosure. As shown in fig. 4, the method includes:
401. selecting a quality inspection frame from a plurality of image building frames before the current image building frame; and the map building frame is used for building a three-dimensional map.
402. And determining a search range according to the coordinates of the quality inspection frame, and searching a plurality of map elements from the current three-dimensional map according to the search range.
403. And carrying out back projection on the map elements to obtain a plurality of target elements which are back projected into the quality inspection frame.
404. And calculating a first pixel distance between each original element and each target element.
In this embodiment, after the map elements are back-projected to the pixel coordinate system of the plane where the quality inspection frame is located, the pixel coordinates of the target elements can be obtained, and then the matching operation can be performed on the target elements and the original elements in the quality inspection frame in the pixel coordinate system where the quality inspection frame is located.
In this embodiment, in order to simplify the calculation, the plurality of original elements selected to participate in matching in the quality inspection frame may be divided according to the shape feature of the target element, and for example, the original elements may be divided into linear elements and planar elements. For example, an element having a large length-width ratio of a maximum circumscribed rectangular frame such as a center line, a side line, and a stop line may be determined as a linear element, and an element having a small length-width ratio of a maximum circumscribed rectangular frame such as a road sign indication board or a traffic light indication board may be determined as a planar element. Different calculation modes are adopted for elements with different shapes, so that the calculation efficiency and the calculation precision can be improved.
In a specific implementation process, if the target elements are linear elements, the step of calculating, for each original element, a first pixel distance between each original element and each target element may include: constructing a k-dimensional tree according to each target element; according to the k-dimensional tree, calculating second pixel distances from each point in the original elements to the target elements to obtain a plurality of second pixel distances; determining the first pixel distance between the original element and the target element according to a plurality of the second pixel distances.
In this embodiment, the k-dimension, also called kd-Tree, is a data structure that organizes points in k-dimension Euclidean space. Constructing the kd-tree is equivalent to continuously segmenting the K-dimensional space by using a hyperplane perpendicular to coordinate axes to form a series of K-dimensional hyper-rectangular areas. Each node of the kd-tree corresponds to a k-dimensional hyper-rectangular region. In this embodiment, by constructing the kd-tree according to the target element, searching for most data points in the target element can be omitted, and the calculation amount of the searching is reduced, thereby improving the efficiency of calculating the second pixel distance.
Specifically, the manner of determining the first pixel distance between the original element and the target element according to the plurality of second pixel distances may be to determine a median of the plurality of second pixel distances as the first pixel distance, and may also determine an average of the plurality of second pixel distances as the first pixel distance, and of course, other manners may also be used for determining the median of the plurality of second pixel distances, which is not limited in this embodiment.
If the target elements are planar elements, in an implementation manner, the step of calculating the first pixel distances between the original elements and the target elements may include: calculating a first coordinate corresponding to the geometric center of gravity of the original element and a second coordinate corresponding to the geometric center of gravity of the target point; determining a distance between the first coordinate and the second coordinate as the first pixel distance. In another implementation manner, to simplify the calculation, the step of calculating the first pixel distance between each of the original elements and each of the target elements may include: screening target points outside the boundary of the target element from each point in the original element; for each target point, calculating a third pixel distance of the target point to the boundary of the target element; determining the first pixel distance between the original element and the target element according to a plurality of the third pixel distances. Specifically, the manner of determining the first pixel distance between the original element and the target element according to the plurality of third pixel distances may be to determine a median of the plurality of third pixel distances as the first pixel distance, and may also determine an average of the plurality of third pixel distances as the first pixel distance, and of course, other manners may also be used for determining the median of the plurality of third pixel distances, which is not limited in this embodiment.
405. Determining whether a minimum distance among the plurality of first pixel distances is smaller than a third preset distance, if so, executing step 406, and if not, executing step 407.
406. And judging that the target element corresponding to the minimum distance is successfully matched with the original element.
407. And judging that the target element corresponding to the minimum distance fails to be matched with the original element.
408. And determining the quality inspection result of the quality inspection frame according to the matching result so as to determine the quality inspection result of the three-dimensional map.
Illustratively, aspects of quality inspection in quality inspection may include the completeness, accuracy, precision, etc. of the quality inspection frame. The completeness of the quality inspection frame may be defined as whether all the original elements in the quality inspection frame are constructed in the current three-dimensional map, for example, 10 original elements exist in the quality inspection frame, and if the number of successful matches between multiple original elements and multiple target elements in the quality inspection frame in the matching result is 8, the completeness is 80%. The accuracy of the quality inspection frame can be defined as the ratio between the number of the plurality of original elements in the quality inspection frame successfully matched with the plurality of target elements and the total number of the plurality of target elements back projected into the quality inspection frame. For example, if there are 12 original elements in the quality inspection frame, there are 10 target elements in the quality inspection frame that are back-projected by the three-dimensional map, and the number of successful matches between the original elements and the target elements in the quality inspection frame in the matching result is 8, the accuracy is 80%. If the minimum distance among the plurality of first pixel distances is smaller than a third preset distance, the minimum distance is determined as a matching distance, and the precision of the quality inspection frame can be defined as the proportion between the plurality of matching distances in the quality inspection frame and the number of successfully matched target elements in the plurality of original elements in the quality inspection frame, namely, the precision of the quality inspection frame is in direct proportion to the distance of the successfully matched elements and in inverse proportion to the number of the successfully matched elements. For example, if the matching distance of a certain successfully matched original element in the quality inspection frame is 10 pixels and the number of successfully matched elements is 100, the accuracy corresponding to the original element in the quality inspection frame is 0.1, and the overall accuracy of the quality inspection frame can be calculated from the accuracies corresponding to the plurality of successfully matched original elements, for example, an average value of the accuracies corresponding to the plurality of successfully matched original elements.
In this embodiment, if a minimum distance among the plurality of first pixel distances is smaller than a third preset distance, the minimum distance is determined as a matching distance, and the step of determining the quality inspection result of the quality inspection frame according to the matching result may include: determining the completeness corresponding to the quality inspection frame according to the number of the successfully matched original elements and the total amount of the plurality of original elements; determining the accuracy corresponding to the quality inspection frame according to the number of the successfully matched original elements and the total amount of the plurality of target elements; determining the corresponding precision of the quality inspection frame according to the plurality of matching distances and the total amount of the plurality of matching distances; and determining the completeness, accuracy and precision corresponding to the quality inspection frame as the quality inspection result.
According to the quality inspection method of the three-dimensional map, the distances between the multiple original elements and the multiple map elements in the quality inspection frame are calculated, the matching results of the multiple original elements and the multiple map elements are determined according to the distances between the elements, the quality inspection result of the quality inspection frame can be conveniently obtained, the quality inspection result of the three-dimensional map is further obtained, the three-dimensional map is further processed according to the quality inspection result, and for example, the corresponding part of the three-dimensional map can be regenerated according to the quality inspection result of the three-dimensional map.
Fig. 5 is a third schematic flow chart illustrating a quality inspection method for a three-dimensional map according to an embodiment of the present application. As shown in fig. 5, the method includes:
501. selecting a quality inspection frame from a plurality of image building frames before the current image building frame; and the map building frame is used for building a three-dimensional map.
502. And determining a search range according to the coordinates of the quality inspection frame, and searching a plurality of map elements from the current three-dimensional map according to the search range.
503. And carrying out back projection on the map elements to obtain a plurality of target elements which are back projected into the quality inspection frame.
504. And dividing the plurality of original elements and the plurality of target elements into a plurality of target categories according to the semantic information of the plurality of target elements and the semantic information of the plurality of original elements.
505. For a plurality of target original elements and a plurality of target elements in each target category, calculating a first pixel distance between each original element and each target element.
In this embodiment, the semantic information of the element may include a function type of the element, for example, the semantic information of the first element is a center line of a road and is a solid line, the semantic information of the second element is a zebra crossing, and the semantic information of the third element is a road signboard.
In practical application, a plurality of target elements and a plurality of original elements can be classified respectively according to semantic information of the elements. For example, 100 target elements, after being classified according to semantic information, 20 target elements classified as a road signboard type, 30 target elements classified as a zebra crossing type, and 50 target elements classified as a dotted centerline type can be obtained. The number of original elements is 120, and after classification according to semantic information, 25 target elements can be obtained and classified into a road signboard type, 45 target elements are classified into a zebra crossing type, and 50 target elements are classified into a dotted central line type. In subsequent calculation, the first pixel distance can be calculated for each type, so that when the first pixel distance between the original element and each target element is calculated, only each target element in the type can be searched, the search range is reduced, and the operation amount is reduced.
506. And judging whether the minimum distance among the first pixel distances is smaller than a third preset distance, if so, executing step 507, and if not, executing step 508.
507. And judging that the target element corresponding to the minimum distance is successfully matched with the original element.
508. And judging that the target element corresponding to the minimum distance fails to be matched with the original element.
509. And determining the quality inspection result of the quality inspection frame according to the matching result so as to determine the quality inspection result of the three-dimensional map.
In the quality inspection method for the three-dimensional map provided in the present embodiment, the plurality of target elements and the plurality of original elements are classified according to the semantic information of the elements, and the target elements and the original elements are matched for each type of element, so that the operation can be simplified and the operation efficiency can be improved.
Fig. 6 is a schematic structural diagram of a quality inspection apparatus of a three-dimensional map according to an embodiment of the present application. As shown in fig. 6, the quality inspection apparatus 60 of the three-dimensional map includes: a selection module 601, a search module 602, a back projection module 603, and a matching module 604.
A selecting module 601, configured to select a quality inspection frame from multiple mapping frames before a current mapping frame; the map building frame is used for building a three-dimensional map;
a searching module 602, configured to determine a searching range according to the coordinates of the quality inspection frame, and search a plurality of map elements from the current three-dimensional map according to the searching range;
a back projection module 603, configured to back project the multiple map elements to obtain multiple target elements back projected into the quality inspection frame;
a matching module 604, configured to match the multiple target elements with the multiple original elements in the quality inspection frame, and determine a quality inspection result of the quality inspection frame according to a matching result, so as to determine a quality inspection result of the three-dimensional map.
According to the quality inspection equipment for the three-dimensional map, a quality inspection frame is selected from a plurality of image building frames before a current image building frame through a selection module 601, and the image building frame is used for building the three-dimensional map; the searching module 602 determines a searching range according to the coordinates of the quality inspection frame, and according to the searching range, the back projection module 603 searches a plurality of map elements from the current three-dimensional map, back projects the plurality of map elements to obtain a plurality of target elements back projected into the quality inspection frame, the matching module 604 matches the plurality of target elements with a plurality of original elements in the quality inspection frame, and determines a quality inspection result of the quality inspection frame according to the matching result to determine a quality inspection result of the three-dimensional map, so that automatic quality inspection of the three-dimensional map is realized, no extra cost is needed to buy advanced equipment, and labor cost of manual quality inspection is saved.
The quality inspection device for the three-dimensional map provided by the embodiment of the application can be used for executing the method embodiment, the implementation principle and the technical effect are similar, and the details are not repeated here.
Fig. 7 is a schematic hardware structure diagram of a quality inspection device of a three-dimensional map according to an embodiment of the present application, where the quality inspection device may be a computer, a messaging device, a tablet device, a medical device, or the like, and the quality inspection device may be disposed on an unmanned vehicle.
The apparatus 70 may include one or more of the following components: processing components 701, memory 702, power components 703, multimedia components 704, audio components 705, input/output (I/O) interfaces 706, sensor components 707, and communication components 708.
The processing component 701 generally controls the overall operation of the device 70, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 701 may include one or more processors 709 to execute instructions to perform all or part of the steps of the methods described above. Further, processing component 701 may include one or more modules that facilitate interaction between processing component 701 and other components. For example, the processing component 701 may include a multimedia module to facilitate interaction between the multimedia component 704 and the processing component 701.
The memory 702 is configured to store various types of data to support operations at the apparatus 70. Examples of such data include instructions for any application or method operating on the device 70, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 702 may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The power supply component 703 provides power to the various components of the device 70. The power components 703 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 70.
The multimedia component 704 includes a screen that provides an output interface between the device 70 and the user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 704 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the device 70 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
The audio component 705 is configured to output and/or input audio signals. For example, the audio component 705 includes a Microphone (MIC) configured to receive external audio signals when the apparatus 70 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 702 or transmitted via the communication component 708. In some embodiments, audio component 705 also includes a speaker for outputting audio signals.
The I/O interface 706 provides an interface between the processing component 701 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
The sensor assembly 707 includes one or more sensors for providing various aspects of state assessment for the device 70. For example, the sensor assembly 707 may detect an open/closed state of the device 70, the relative positioning of the components, such as a display and keypad of the device 70, the sensor assembly 707 may also detect a change in the position of the device 70 or a component of the device 70, the presence or absence of user contact with the device 70, the orientation or acceleration/deceleration of the device 70, and a change in the temperature of the device 70. The sensor assembly 707 may include a proximity sensor configured to detect the presence of a nearby object in the absence of any physical contact. The sensor assembly 707 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 707 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 708 is configured to facilitate communication between the apparatus 70 and other devices in a wired or wireless manner. The device 70 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 708 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 708 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the apparatus 70 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.
In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as the memory 702 including instructions executable by the processor 709 of the device 70 to perform the above-described method. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
The computer-readable storage medium may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium may also reside as discrete components in the apparatus.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
The embodiment of the application also provides a computer program product, which comprises a computer program, and when the computer program is executed by a processor, the quality inspection method of the three-dimensional map executed by the quality inspection equipment of the three-dimensional map is realized.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.
Claims (12)
1. A quality inspection method of a three-dimensional map is characterized by comprising the following steps:
selecting a quality inspection frame from a plurality of image building frames before the current image building frame; the map building frame is used for building a three-dimensional map;
determining a search range according to the coordinates of the quality inspection frame, and searching a plurality of map elements from the current three-dimensional map according to the search range;
carrying out back projection on the map elements to obtain a plurality of target elements which are back projected into the quality inspection frame;
and matching the target elements with the original elements in the quality inspection frame, and determining the quality inspection result of the quality inspection frame according to the matching result so as to determine the quality inspection result of the three-dimensional map.
2. The method of claim 1, wherein selecting a quality inspection frame from a plurality of mapping frames prior to a current mapping frame comprises:
determining corresponding track distances between a plurality of image building frames before the current image building frame and the current image building frame;
and selecting the image building frame before the current image building frame with the track distance greater than or equal to a first preset distance as the quality inspection frame.
3. The method of claim 1, wherein determining a search range from the coordinates of the quality inspection frame comprises:
and determining a range with the coordinate of the quality inspection frame as a center and the distance between the center and the coordinate of the quality inspection frame being less than or equal to a second preset distance as the search range.
4. The method of claim 1, wherein the back-projecting the plurality of map elements to obtain a plurality of target elements back-projected into the quality inspection frame comprises:
converting coordinates of a plurality of the map elements from a world coordinate system to a camera coordinate system;
according to an internal reference matrix of a camera, carrying out back projection on the map elements after coordinate conversion to a plane where the quality inspection frame is located, and obtaining pixel coordinates of the map elements after back projection;
and screening the plurality of target elements from the plurality of map elements after the back projection according to the pixel coordinates of the boundary of the quality inspection frame.
5. The method of any of claims 1-4, wherein matching the plurality of target elements to the plurality of original elements within the quality inspection frame comprises:
calculating a first pixel distance between each original element and each target element;
and if the minimum distance in the first pixel distances is smaller than a third preset distance, judging that the target element corresponding to the minimum distance is successfully matched with the original element.
6. The method according to claim 5, wherein the target elements are linear elements, and the calculating of the first pixel distance between the original element and each target element comprises:
constructing a k-dimensional tree according to each target element;
according to the k-dimensional tree, calculating second pixel distances from each point in the original elements to the target elements to obtain a plurality of second pixel distances;
determining the first pixel distance between the original element and the target element according to a plurality of the second pixel distances.
7. The method according to claim 5, wherein the target elements are planar elements, and the calculating of the first pixel distance between the original element and each target element comprises:
screening target points outside the boundary of the target element from each point in the original element;
for each target point, calculating a third pixel distance of the target point to the boundary of the target element;
determining the first pixel distance between the original element and the target element according to a plurality of the third pixel distances.
8. The method according to claim 5, wherein before calculating, for each of the original elements, a first pixel distance between the original element and each of the target elements, further comprising:
dividing a plurality of original elements and a plurality of target elements into a plurality of target categories according to semantic information of the plurality of target elements and semantic information of the plurality of original elements;
for each original element, calculating a first pixel distance between the original element and each target element respectively includes:
for a plurality of target original elements and a plurality of target elements in each target category, calculating a first pixel distance between each original element and each target element.
9. The method of claim 5, wherein determining a minimum distance of the first pixel distances as a matching distance if the minimum distance is smaller than a third predetermined distance, and determining a quality inspection result of the quality inspection frame according to the matching result comprises:
determining the completeness corresponding to the quality inspection frame according to the number of the successfully matched original elements and the total amount of the plurality of original elements;
determining the accuracy corresponding to the quality inspection frame according to the number of the successfully matched original elements and the total amount of the plurality of target elements;
determining the corresponding precision of the quality inspection frame according to the plurality of matching distances and the total amount of the plurality of matching distances;
and determining the completeness, accuracy and precision corresponding to the quality inspection frame as the quality inspection result.
10. A quality inspection apparatus for a three-dimensional map, comprising:
the selection module is used for selecting a quality inspection frame from a plurality of image establishing frames before the current image establishing frame; the map building frame is used for building a three-dimensional map;
the searching module is used for determining a searching range according to the coordinates of the quality inspection frame and searching a plurality of map elements from the current three-dimensional map according to the searching range;
the back projection module is used for back projecting the map elements to obtain a plurality of target elements back projected into the quality inspection frame;
and the matching module is used for matching the target elements with the original elements in the quality inspection frame and determining the quality inspection result of the quality inspection frame according to the matching result so as to determine the quality inspection result of the three-dimensional map.
11. A quality inspection apparatus for a three-dimensional map, comprising: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the method of quality inspection of a three-dimensional map of any of claims 1-9.
12. A computer-readable storage medium having stored thereon computer-executable instructions that, when executed by a processor, implement the quality inspection method of the three-dimensional map according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111147721.1A CN113592865B (en) | 2021-09-29 | 2021-09-29 | Quality inspection method and equipment for three-dimensional map and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111147721.1A CN113592865B (en) | 2021-09-29 | 2021-09-29 | Quality inspection method and equipment for three-dimensional map and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113592865A true CN113592865A (en) | 2021-11-02 |
| CN113592865B CN113592865B (en) | 2022-01-25 |
Family
ID=78242710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111147721.1A Active CN113592865B (en) | 2021-09-29 | 2021-09-29 | Quality inspection method and equipment for three-dimensional map and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113592865B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6538688B1 (en) * | 1998-07-02 | 2003-03-25 | Terran Interactive | Method and apparatus for performing an automated inverse telecine process |
| US20050100802A1 (en) * | 2002-05-22 | 2005-05-12 | Neal Callan | Method for post-OPC multi layer overlay quality inspection |
| US20100183192A1 (en) * | 2009-01-16 | 2010-07-22 | Honda Research Institute Europe Gmbh | System and method for object motion detection based on multiple 3d warping and vehicle equipped with such system |
| US20150177409A1 (en) * | 2013-12-20 | 2015-06-25 | Visuray Intech Ltd (Bvi) | Methods and Means for Creating Three-Dimensional Borehole Image Data |
| CN105678754A (en) * | 2015-12-31 | 2016-06-15 | 西北工业大学 | Unmanned aerial vehicle real-time map reconstruction method |
| CN108986161A (en) * | 2018-06-19 | 2018-12-11 | 亮风台（上海）信息科技有限公司 | A kind of three dimensional space coordinate estimation method, device, terminal and storage medium |
| CN109635053A (en) * | 2018-10-31 | 2019-04-16 | 百度在线网络技术（北京）有限公司 | Quality detecting method, device, system and the storage medium of map |
| CN109978919A (en) * | 2019-03-22 | 2019-07-05 | 广州小鹏汽车科技有限公司 | A kind of vehicle positioning method and system based on monocular camera |
| CN110782494A (en) * | 2019-10-16 | 2020-02-11 | 北京工业大学 | Visual SLAM method based on point-line fusion |
| CN111045017A (en) * | 2019-12-20 | 2020-04-21 | 成都理工大学 | Method for constructing transformer substation map of inspection robot by fusing laser and vision |
| CN111221808A (en) * | 2019-12-31 | 2020-06-02 | 武汉中海庭数据技术有限公司 | Unattended high-precision map quality inspection method and device |
| CN111780764A (en) * | 2020-06-30 | 2020-10-16 | 杭州海康机器人技术有限公司 | Visual positioning method and device based on visual map |
| EP3731020A1 (en) * | 2019-04-25 | 2020-10-28 | ASML Netherlands B.V. | Metrology method and apparatus, computer program and lithographic system |
| CN113345032A (en) * | 2021-07-07 | 2021-09-03 | 北京易航远智科技有限公司 | Wide-angle camera large-distortion image based initial image construction method and system |
| CN113377890A (en) * | 2021-06-29 | 2021-09-10 | 北京百度网讯科技有限公司 | Map quality inspection method and device, electronic equipment and storage medium |
-
2021
- 2021-09-29 CN CN202111147721.1A patent/CN113592865B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6538688B1 (en) * | 1998-07-02 | 2003-03-25 | Terran Interactive | Method and apparatus for performing an automated inverse telecine process |
| US20050100802A1 (en) * | 2002-05-22 | 2005-05-12 | Neal Callan | Method for post-OPC multi layer overlay quality inspection |
| US20100183192A1 (en) * | 2009-01-16 | 2010-07-22 | Honda Research Institute Europe Gmbh | System and method for object motion detection based on multiple 3d warping and vehicle equipped with such system |
| US20150177409A1 (en) * | 2013-12-20 | 2015-06-25 | Visuray Intech Ltd (Bvi) | Methods and Means for Creating Three-Dimensional Borehole Image Data |
| CN105678754A (en) * | 2015-12-31 | 2016-06-15 | 西北工业大学 | Unmanned aerial vehicle real-time map reconstruction method |
| CN108986161A (en) * | 2018-06-19 | 2018-12-11 | 亮风台（上海）信息科技有限公司 | A kind of three dimensional space coordinate estimation method, device, terminal and storage medium |
| CN109635053A (en) * | 2018-10-31 | 2019-04-16 | 百度在线网络技术（北京）有限公司 | Quality detecting method, device, system and the storage medium of map |
| CN109978919A (en) * | 2019-03-22 | 2019-07-05 | 广州小鹏汽车科技有限公司 | A kind of vehicle positioning method and system based on monocular camera |
| EP3731020A1 (en) * | 2019-04-25 | 2020-10-28 | ASML Netherlands B.V. | Metrology method and apparatus, computer program and lithographic system |
| CN110782494A (en) * | 2019-10-16 | 2020-02-11 | 北京工业大学 | Visual SLAM method based on point-line fusion |
| CN111045017A (en) * | 2019-12-20 | 2020-04-21 | 成都理工大学 | Method for constructing transformer substation map of inspection robot by fusing laser and vision |
| CN111221808A (en) * | 2019-12-31 | 2020-06-02 | 武汉中海庭数据技术有限公司 | Unattended high-precision map quality inspection method and device |
| CN111780764A (en) * | 2020-06-30 | 2020-10-16 | 杭州海康机器人技术有限公司 | Visual positioning method and device based on visual map |
| CN113377890A (en) * | 2021-06-29 | 2021-09-10 | 北京百度网讯科技有限公司 | Map quality inspection method and device, electronic equipment and storage medium |
| CN113345032A (en) * | 2021-07-07 | 2021-09-03 | 北京易航远智科技有限公司 | Wide-angle camera large-distortion image based initial image construction method and system |
Non-Patent Citations (2)
| Title |
|---|
| DONG SHUAI等: "QUALITY INSPECTION AND ANALYSIS OF THREE-DIMENSIONAL GEOGRAPHIC INFORMATION MODEL BASED ON OBLIQUE PHOTOGRAMMETRY", 《THE INTERNATIONAL ARCHIVES OF THE PHOTOGRAMMETRY, REMOTE SENSING AND SPATIAL INFORMATION SCIENCES》 * |
| 李庚勤等: "多角度模式下静态三维地图快速生成方法", 《测绘地理信息》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113592865B (en) | 2022-01-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021164469A1 (en) | Target object detection method and apparatus, device, and storage medium | |
| KR101694643B1 (en) | Method, apparatus, device, program, and recording medium for image segmentation | |
| CN111983635B (en) | Pose determination method and device, electronic equipment and storage medium | |
| US20200327353A1 (en) | Image processing method and apparatus, electronic device, and storage medium | |
| EP3825960A1 (en) | Method and device for obtaining localization information | |
| US20220207910A1 (en) | Face image processing method and apparatus, electronic device, and storage medium | |
| CN111881827B (en) | Target detection method and device, electronic equipment and storage medium | |
| CN110853095A (en) | Camera positioning method and device, electronic equipment and storage medium | |
| CN112767496B (en) | Calibration method, device and system | |
| CN114267041B (en) | Method and device for identifying object in scene | |
| CN111339880A (en) | Target detection method and device, electronic equipment and storage medium | |
| CN110245567B (en) | Obstacle avoidance method and device, storage medium and electronic equipment | |
| CN114972485A (en) | Positioning accuracy testing method, positioning accuracy testing apparatus, storage medium, and program product | |
| CN114677517A (en) | Semantic segmentation network model for unmanned aerial vehicle and image segmentation identification method | |
| WO2022142298A1 (en) | Key point detection method and apparatus, and electronic device and storage medium | |
| CN111433809A (en) | Method, device and system for generating travel route and space model | |
| CN113450459B (en) | Method and device for constructing three-dimensional model of target object | |
| CN113592865B (en) | Quality inspection method and equipment for three-dimensional map and storage medium | |
| CN116824533A (en) | Remote small target point cloud data characteristic enhancement method based on attention mechanism | |
| CN116310169A (en) | Drawing method, device, equipment, medium and program product of high-precision map | |
| CN116359942A (en) | Point cloud data acquisition method, equipment, storage medium and program product | |
| CN111832338A (en) | Object detection method and device, electronic equipment and storage medium | |
| WO2022110801A1 (en) | Data processing method and apparatus, electronic device, and storage medium | |
| CN113052874B (en) | Target tracking method and device, electronic equipment and storage medium | |
| CN114445778A (en) | Counting method and device, electronic equipment 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 |