CN113129369A - Point cloud map initialization method and device - Google Patents
Point cloud map initialization method and device Download PDFInfo
- Publication number
- CN113129369A CN113129369A CN202010048424.0A CN202010048424A CN113129369A CN 113129369 A CN113129369 A CN 113129369A CN 202010048424 A CN202010048424 A CN 202010048424A CN 113129369 A CN113129369 A CN 113129369A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- bag
- sub
- image
- current
- 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.)
- Pending
Links
- 238000011423 initialization method Methods 0.000 title claims abstract description 15
- 239000013598 vector Substances 0.000 claims abstract description 81
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 240000004050 Pentaglottis sempervirens Species 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
- G06V10/464—Salient features, e.g. scale invariant feature transforms [SIFT] using a plurality of salient features, e.g. bag-of-words [BoW] representations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a point cloud map initialization method and device, and relates to the technical field of computers. One specific implementation mode of the method comprises the steps of obtaining point cloud data of a current frame, generating a current image and calculating a current bag-of-words vector; and respectively calculating the similarity with the current bag-of-words vector based on the bag-of-words vector corresponding to each sub-image of the point cloud map so as to determine the sub-image serving as an initialization area and further obtain the pose of the current frame. Therefore, the method and the device for initializing the point cloud map can solve the problems that the existing point cloud map is low in initialization positioning efficiency and difficult to maintain.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a point cloud map initialization method and device.
Background
In the field of automatic driving, the initial positioning in a point cloud map plays an extremely important role, for example, a violent point cloud matching method, a position memory method and the like are adopted.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:
the existing initialization positioning has some defects, and the time consumption is serious when the violent point cloud matching method is large in point cloud map range. The position memory method is simple and easy, but cannot solve the problem of binding (namely, the position is moved in a power-off state and the position is initialized in a power-on state), and is inconvenient for later maintenance.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for initializing a point cloud map, which can solve the problems of low efficiency and difficult maintenance of the existing initialization positioning in the point cloud map.
In order to achieve the above object, according to an aspect of the embodiments of the present invention, there is provided a point cloud map initialization method, including obtaining point cloud data of a current frame, generating a current image, and calculating a current bag-of-words vector; and respectively calculating the similarity with the current bag-of-words vector based on the bag-of-words vector corresponding to each sub-image of the point cloud map so as to determine the sub-image serving as an initialization area and further obtain the pose of the current frame.
Optionally, before respectively calculating similarity to the current bag-of-words vector based on the bag-of-words vector corresponding to each sub-image of the point cloud map, the method includes:
and acquiring a point cloud map to project all point cloud data onto a plane to generate a corresponding image, further dividing the image into a plurality of sub-images, and calculating bag-of-word vectors corresponding to the sub-images.
Optionally, after acquiring the point cloud map, the method includes:
and acquiring all point cloud data in the point cloud map so as to perform downsampling on the point cloud data.
Optionally, downsampling the point cloud data includes:
and calculating the geometric center of the point cloud within a preset range, taking the geometric center as a representative point of the range, and removing other point cloud data within the range.
Optionally, segmenting the image into several subgraphs, including:
and generating the resolution ratio of the current image based on the point cloud data of the current frame, and dividing the image into a plurality of sub-images.
Optionally, calculating a bag-of-words vector corresponding to each sub-graph includes:
extracting feature points from each subgraph and calculating a descriptor of each subgraph;
and calculating corresponding bag-of-word vectors through the descriptors based on the feature points of each subgraph.
Optionally, calculating a corresponding bag-of-words vector through the descriptor based on the feature points of each sub-graph, including:
characteristic points in each subgraph are extracted by using ORB characteristics in a visual library, a descriptor consisting of 256 bits is calculated, and then a bag-of-word vector uniquely corresponding to the subgraph is calculated by the descriptor by using a DBoW2 library.
Optionally, respectively calculating similarity to the current bag-of-words vector based on the bag-of-words vector corresponding to each sub-image of the point cloud map, including:
and respectively calculating the similarity of the current bag-of-words vector based on the bag-of-words vector corresponding to each sub-image of the point cloud map by adopting a sparse rule operator.
Optionally, determining a sub-graph as an initialization region, and further obtaining a pose of the current frame, includes:
and matching the point cloud data of the current frame with the point cloud data corresponding to the sub-image serving as the initialization area through a closest point iterative algorithm to iteratively solve the pose of the current frame.
In addition, the invention also provides a point cloud map initialization device, which comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring the point cloud data of the current frame and generating a current image so as to calculate the current bag-of-word vector; and the processing module is used for respectively calculating the similarity between the word bag vector and the current word bag vector based on the word bag vector corresponding to each sub-image of the point cloud map so as to determine the sub-image serving as the initialization area and further obtain the pose of the current frame.
One embodiment of the above invention has the following advantages or benefits: because the point cloud data of the current frame is obtained, the current image is generated to calculate the current bag-of-word vector; based on the bag-of-word vectors corresponding to the sub-images of the point cloud map, similarity between the bag-of-word vectors and the current bag-of-word vectors is calculated respectively, so that the sub-images serving as initialization areas are determined, and the pose of the current frame is obtained.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
fig. 1 is a schematic diagram of a main flow of a point cloud map initialization method according to a first embodiment of the invention;
FIG. 2 is a schematic diagram of a main process of a point cloud map initialization method according to a second embodiment of the invention;
FIG. 3 is a schematic diagram of the main modules of a point cloud map initialization apparatus according to an embodiment of the present invention;
FIG. 4 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 5 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram of a main flow of a point cloud map initialization method according to a first embodiment of the present invention, as shown in fig. 1, the point cloud map initialization method includes:
step S101, point cloud data of a current frame is obtained, and a current image is generated to calculate a current bag-of-words vector.
In some embodiments, when computing the current bag-of-words vector, feature points may be extracted from the current image and a descriptor computed. Then, based on the feature points, bag-of-words vectors are calculated by descriptors.
In a further embodiment, the ORB features in OpenCV are used to extract feature points in the current image, and a descriptor consisting of 256 bits is calculated, and then a bag-of-words vector uniquely corresponding to the current image is calculated from the descriptor using the DBoW2 library.
And S102, respectively calculating the similarity of the word bag vector corresponding to each sub-image of the point cloud map and the current word bag vector to determine the sub-image serving as an initialization area, and further obtaining the pose of the current frame.
In some embodiments, a sparse rule operator (i.e., L1 norm) is used to separately compute the similarity to the current bag-of-words vector based on the bag-of-words vector corresponding to each sub-graph.
In other embodiments, the point cloud data of the current frame and the point cloud data corresponding to the sub-image serving as the initialization region are matched through a closest point iterative algorithm (i.e., ICP) to iteratively solve the pose of the current frame.
In still other embodiments, before step S102 is executed, a point cloud map may be obtained to project all point cloud data onto a plane, generate a corresponding image, further segment the image into a plurality of sub-images, and calculate bag-of-word vectors corresponding to the sub-images.
In some embodiments, after the point cloud map is acquired, all the point cloud data in the point cloud map needs to be acquired to downsample the point cloud data. In a further embodiment, the geometric center of the point cloud within the preset range is calculated, the geometric center is used as a representative point of the range, and other point cloud data within the range are removed, so that point cloud data are down-sampled, a large number of invalid points (such as ground points) are reduced, the density of the point cloud map is reduced, and the calculation scale is reduced.
Preferably, the geometric center of the point cloud within a certain range (e.g., 15 cm) can be calculated by downsampling using a voxel filter.
As further embodiments, the resolution at which the current image is generated based on the point cloud data of the current frame is segmented into several sub-images. For example: the resolution of the image generated by the point cloud map is 10000 multiplied by 10000, the resolution of the current image generated by the point cloud data of the current frame is 100 multiplied by 100, and then the image generated by the point cloud map is divided into 10000 sub-images according to 100 multiplied by 100.
As still other embodiments, when calculating the bag-of-word vector corresponding to each sub-graph, feature points may be extracted from each sub-graph, and a descriptor of each sub-graph may be calculated. And then, calculating a corresponding bag-of-word vector through the descriptor based on the characteristic points of each subgraph.
In a further embodiment, the ORB features in OpenCV (OpenCV is a cross-platform computer vision library based on BSD licensing) (ORB features are a feature point detection and description algorithm for visual information) are used to extract feature points in each subgraph, and a descriptor consisting of 256 bits is calculated, and then a DBoW2 library (DBoW2 is an open source software library) is used to calculate a bag-of-word vector uniquely corresponding to the subgraph from the descriptor.
The specific implementation process comprises the following steps: assuming that 500 feature points are extracted from the sub-graph, 500 descriptors can be generated. The DBoW2 library can provide a N-level K-ary tree with M nodes at each level, and then a total of M nodesNAnd (4) a leaf node. Each intermediate node has a corresponding key value, each descriptor of each sub-graph is compared with each intermediate node respectively, deep search is carried out until a corresponding leaf node is found, and each sub-graph can be uniquely described by a 01 vector formed by the existence of the leaf nodes, namely the bag-of-word vector corresponding to the sub-graph.
In summary, the point cloud map initialization method provided by the invention screens out the area of the current frame point cloud in the point cloud map by utilizing image similarity evaluation, namely, the point cloud is converted into an image, and the most similar area is screened out by using a bag-of-words matching method of the image, so that the blind matching solution of a violence matching method is avoided, and time resources are wasted.
Meanwhile, the initialization area can be quickly and accurately determined, so that the solution space during the matching of the violent point clouds is greatly reduced, and the pose resolving efficiency and accuracy are improved. In addition, the visual bag-of-words information does not need to be independently constructed and stored, so that too many computing resources and storage resources are not occupied. In addition, the method has universality, and the problem of later maintenance of the memory position method can not occur.
Fig. 2 is a schematic diagram of a main flow of a point cloud map initialization method according to a second embodiment of the present invention, which may include:
step S201, acquiring all point cloud data in the point cloud map to perform downsampling on the point cloud data.
Preferably, the geometric center of the point cloud within the preset range is calculated, the geometric center is used as a representative point of the range, and other point cloud data within the range are removed.
Step S202, projecting the point cloud data onto a plane to generate a corresponding aerial view.
Preferably, all the point cloud data are projected on an x-y plane of z-z 1, so as to generate a bird's eye view corresponding to the point cloud map. Wherein z1 is a preset fixed value.
Step S203, generating the resolution ratio of the current aerial view based on the point cloud data of the current frame, and dividing the aerial view into a plurality of sub-images.
And step S204, calculating the bag-of-word vector corresponding to each subgraph.
Preferably, feature points are extracted from each sub-graph, and descriptors for each sub-graph are computed. And then calculating a corresponding bag-of-word vector through the descriptor based on the characteristic points of each subgraph.
Step S205, point cloud data of the current frame is obtained, and a current aerial view is generated to calculate a current bag-of-words vector.
Preferably, the point cloud data of the current frame is projected onto an x-y plane of z-z 1, thereby generating the current bird's eye view. Wherein z1 is a preset fixed value.
Step S206, based on the bag-of-word vectors corresponding to the sub-images, respectively calculating the similarity with the current bag-of-word vector.
Preferably, a sparse rule operator (i.e., L1 norm) is used to calculate the similarity between each subgraph and the current bag-of-word vector based on the bag-of-word vector corresponding to each subgraph.
Preferably, assuming that the bag-of-word vector of the current bird's-eye view is a and the bag-of-word vector of a certain bird's-eye view is b, the L1 norm thereof is defined as:
in step S207, the subgraph with the highest similarity is used as the subgraph of the initialization region.
And S208, matching the point cloud data of the current frame with the point cloud data corresponding to the sub-image serving as the initialization area to iteratively solve the pose of the current frame.
Preferably, the point cloud data of the current frame and the point cloud data corresponding to the sub-image serving as the initialization area are matched through a closest point iterative algorithm ICP, so that the pose of the current frame is solved in an iterative manner.
It should be noted that steps S201 to S204 may be executed simultaneously with step S205, or step S201 to step S204 are executed first and then step S205 is executed, or step S205 is executed first and then step S201 to step S204 are executed.
Fig. 3 is a schematic diagram of main modules of a point cloud map initialization apparatus according to an embodiment of the present invention, and as shown in fig. 3, the point cloud map initialization apparatus 300 includes an acquisition module 301 and a processing module 302. The obtaining module 301 obtains point cloud data of a current frame, generates a current image, and calculates a current bag-of-words vector; the processing module 302 calculates similarity between the current bag-of-words vector and the bag-of-words vector based on the bag-of-words vector corresponding to each sub-image of the point cloud map, so as to determine the sub-image as an initialization area, and further obtain the pose of the current frame.
In a preferred embodiment, the obtaining module 301 is further configured to: and acquiring a point cloud map to project all point cloud data onto a plane to generate a corresponding image, further dividing the image into a plurality of sub-images, and calculating bag-of-word vectors corresponding to the sub-images.
In some embodiments, after the acquisition module 301 acquires the point cloud map, all the point cloud data in the point cloud map may be acquired to downsample the point cloud data.
In a further embodiment, the obtaining module 301 down-samples the point cloud data, including: and calculating the geometric center of the point cloud within a preset range, taking the geometric center as a representative point of the range, and removing other point cloud data within the range.
As further embodiments, the obtaining module 301 segments the image into several sub-images, including: and generating the resolution ratio of the current image based on the point cloud data of the current frame, and dividing the image into a plurality of sub-images.
As still other embodiments, the obtaining module 301 calculates a bag-of-word vector corresponding to each sub-graph, including: extracting feature points from each subgraph and calculating a descriptor of each subgraph; and calculating corresponding bag-of-word vectors through the descriptors based on the feature points of each subgraph.
In a preferred embodiment, the obtaining module 301 calculates a corresponding bag-of-word vector through the descriptor based on the feature points of each sub-graph, including:
characteristic points in each subgraph are extracted by using ORB characteristics in a visual library, a descriptor consisting of 256 bits is calculated, and then a bag-of-word vector uniquely corresponding to the subgraph is calculated by the descriptor by using a DBoW2 library.
In other embodiments, the processing module 302 uses a sparse rule operator to calculate the similarity between the current bag-of-word vector and the bag-of-word vector based on the bag-of-word vector corresponding to each sub-image of the point cloud map.
As still other embodiments, the processing module 302 determines a sub-graph as an initialization region, and then obtains the pose of the current frame, including: and matching the point cloud data of the current frame with the point cloud data corresponding to the sub-image serving as the initialization area through a closest point iterative algorithm to iteratively solve the pose of the current frame.
It should be noted that the point cloud map initialization method and the point cloud map initialization apparatus according to the present invention have a corresponding relationship in the specific implementation contents, and therefore the repeated contents are not described again.
Fig. 4 shows an exemplary system architecture 400 to which the point cloud map initialization method or the point cloud map initialization apparatus of the embodiments of the invention may be applied.
As shown in fig. 4, the system architecture 400 may include terminal devices 401, 402, 403, a network 404, and a server 405. The network 404 serves as a medium for providing communication links between the terminal devices 401, 402, 403 and the server 405. Network 404 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.
A user may use terminal devices 401, 402, 403 to interact with a server 405 over a network 404 to receive or send messages or the like. The terminal devices 401, 402, 403 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 401, 402, 403 may be various electronic devices having a point cloud map initialization screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 405 may be a server providing various services, such as a background management server (for example only) providing support for shopping websites browsed by users using the terminal devices 401, 402, 403. The backend management server may analyze and perform other processing on the received data such as the product information query request, and feed back a processing result (for example, target push information, product information — just an example) to the terminal device.
It should be noted that the point cloud map initialization method provided by the embodiment of the present invention is generally executed by the server 405, and accordingly, the computing device is generally disposed in the server 405.
It should be understood that the number of terminal devices, networks, and servers in fig. 4 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 5, shown is a block diagram of a computer system 500 suitable for use with a terminal device implementing an embodiment of the present invention. The terminal device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU)501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data necessary for the operation of the computer system 500 are also stored. The CPU501, ROM502, and RAM503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output section 507 including a display such as a Cathode Ray Tube (CRT), a liquid crystal point cloud map initializer (LCD), and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 501.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes an acquisition module and a processing module. Wherein the names of the modules do not in some cases constitute a limitation of the module itself.
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to include obtaining point cloud data for a current frame, generating a current image, to calculate a current bag-of-words vector; and respectively calculating the similarity with the current bag-of-words vector based on the bag-of-words vector corresponding to each sub-image of the point cloud map so as to determine the sub-image serving as an initialization area and further obtain the pose of the current frame.
According to the technical scheme of the embodiment of the invention, the problems of low efficiency and difficult maintenance of the conventional initialized positioning in the point cloud map can be solved.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (12)
1. A point cloud map initialization method is characterized by comprising the following steps:
acquiring point cloud data of a current frame, and generating a current image to calculate a current bag-of-words vector;
and respectively calculating the similarity with the current bag-of-words vector based on the bag-of-words vector corresponding to each sub-image of the point cloud map so as to determine the sub-image serving as an initialization area and further obtain the pose of the current frame.
2. The method of claim 1, wherein before calculating the similarity with the current bag-of-words vector based on the bag-of-words vector corresponding to each sub-image of the point cloud map, respectively, comprises:
and acquiring a point cloud map to project all point cloud data onto a plane to generate a corresponding image, further dividing the image into a plurality of sub-images, and calculating bag-of-word vectors corresponding to the sub-images.
3. The method of claim 2, wherein after obtaining the point cloud map, comprising:
and acquiring all point cloud data in the point cloud map so as to perform downsampling on the point cloud data.
4. The method of claim 3, wherein down-sampling the point cloud data comprises:
and calculating the geometric center of the point cloud within a preset range, taking the geometric center as a representative point of the range, and removing other point cloud data within the range.
5. The method of claim 2, wherein segmenting the image into sub-images comprises:
and generating the resolution ratio of the current image based on the point cloud data of the current frame, and dividing the image into a plurality of sub-images.
6. The method of claim 2, wherein computing a bag-of-words vector for each sub-graph comprises:
extracting feature points from each subgraph and calculating a descriptor of each subgraph;
and calculating corresponding bag-of-word vectors through the descriptors based on the feature points of each subgraph.
7. The method of claim 6, wherein computing a corresponding bag of words vector by a descriptor based on the feature points of each sub-graph comprises:
characteristic points in each subgraph are extracted by using ORB characteristics in a visual library, a descriptor consisting of 256 bits is calculated, and then a bag-of-word vector uniquely corresponding to the subgraph is calculated by the descriptor by using a DBoW2 library.
8. The method of claim 1, wherein calculating the similarity with the current bag-of-word vector based on the bag-of-word vectors corresponding to the sub-images of the point cloud map comprises:
and respectively calculating the similarity of the current bag-of-words vector based on the bag-of-words vector corresponding to each sub-image of the point cloud map by adopting a sparse rule operator.
9. The method according to any one of claims 1 to 8, wherein determining a sub-graph as an initialization region to obtain the pose of the current frame comprises:
and matching the point cloud data of the current frame with the point cloud data corresponding to the sub-image serving as the initialization area through a closest point iterative algorithm to iteratively solve the pose of the current frame.
10. A point cloud map initialization device is characterized by comprising:
the acquisition module is used for acquiring point cloud data of a current frame and generating a current image so as to calculate a current bag-of-word vector;
and the processing module is used for respectively calculating the similarity between the word bag vector and the current word bag vector based on the word bag vector corresponding to each sub-image of the point cloud map so as to determine the sub-image serving as the initialization area and further obtain the pose of the current frame.
11. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-9.
12. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010048424.0A CN113129369A (en) | 2020-01-16 | 2020-01-16 | Point cloud map initialization method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010048424.0A CN113129369A (en) | 2020-01-16 | 2020-01-16 | Point cloud map initialization method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113129369A true CN113129369A (en) | 2021-07-16 |
Family
ID=76771760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010048424.0A Pending CN113129369A (en) | 2020-01-16 | 2020-01-16 | Point cloud map initialization method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113129369A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107160395A (en) * | 2017-06-07 | 2017-09-15 | 中国人民解放军装甲兵工程学院 | Map constructing method and robot control system |
| CN107796397A (en) * | 2017-09-14 | 2018-03-13 | 杭州迦智科技有限公司 | A kind of Robot Binocular Vision localization method, device and storage medium |
| WO2018048353A1 (en) * | 2016-09-09 | 2018-03-15 | Nanyang Technological University | Simultaneous localization and mapping methods and apparatus |
| CN108648240A (en) * | 2018-05-11 | 2018-10-12 | 东南大学 | Based on a non-overlapping visual field camera posture scaling method for cloud characteristics map registration |
| CN109816769A (en) * | 2017-11-21 | 2019-05-28 | 深圳市优必选科技有限公司 | Scene based on depth camera ground drawing generating method, device and equipment |
| CN110009029A (en) * | 2019-03-28 | 2019-07-12 | 北京智行者科技有限公司 | Feature matching method based on point cloud segmentation |
| DE102019104482A1 (en) * | 2018-02-23 | 2019-08-29 | GM Global Technology Operations LLC | MASS-SCANNING DOT CLOUD CARD |
| WO2019169540A1 (en) * | 2018-03-06 | 2019-09-12 | 斯坦德机器人（深圳）有限公司 | Method for tightly-coupling visual slam, terminal and computer readable storage medium |
-
2020
- 2020-01-16 CN CN202010048424.0A patent/CN113129369A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018048353A1 (en) * | 2016-09-09 | 2018-03-15 | Nanyang Technological University | Simultaneous localization and mapping methods and apparatus |
| CN107160395A (en) * | 2017-06-07 | 2017-09-15 | 中国人民解放军装甲兵工程学院 | Map constructing method and robot control system |
| CN107796397A (en) * | 2017-09-14 | 2018-03-13 | 杭州迦智科技有限公司 | A kind of Robot Binocular Vision localization method, device and storage medium |
| CN109816769A (en) * | 2017-11-21 | 2019-05-28 | 深圳市优必选科技有限公司 | Scene based on depth camera ground drawing generating method, device and equipment |
| DE102019104482A1 (en) * | 2018-02-23 | 2019-08-29 | GM Global Technology Operations LLC | MASS-SCANNING DOT CLOUD CARD |
| WO2019169540A1 (en) * | 2018-03-06 | 2019-09-12 | 斯坦德机器人（深圳）有限公司 | Method for tightly-coupling visual slam, terminal and computer readable storage medium |
| CN108648240A (en) * | 2018-05-11 | 2018-10-12 | 东南大学 | Based on a non-overlapping visual field camera posture scaling method for cloud characteristics map registration |
| CN110009029A (en) * | 2019-03-28 | 2019-07-12 | 北京智行者科技有限公司 | Feature matching method based on point cloud segmentation |
Non-Patent Citations (3)
| Title |
|---|
| 刘智杰: "基于卷积神经网络的语义同时定位以及地图构建方法", 《科学技术与工程》 * |
| 李少朋;张涛;: "深度学习在视觉SLAM中应用综述", 空间控制技术与应用, no. 02 * |
| 马跃龙;曹雪峰;万刚;李登峰;: "一种基于深度相机的机器人室内导航点云地图生成方法", 测绘工程, no. 03 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229419B (en) | Method and apparatus for clustering images | |
| CN110632608B (en) | Target detection method and device based on laser point cloud | |
| US10282636B2 (en) | System, method, and recording medium for efficient cohesive subgraph identification in entity collections for inlier and outlier detection | |
| CN111815738B (en) | Method and device for constructing map | |
| CN109118456B (en) | Image processing method and device | |
| CN110288625B (en) | Method and apparatus for processing image | |
| CN111274341A (en) | Site selection method and device for network points | |
| US20220335635A1 (en) | Method and system for location detection of photographs using topographic techniques | |
| CN112860993A (en) | Method, device, equipment, storage medium and program product for classifying points of interest | |
| CN110633716A (en) | Target object detection method and device | |
| CN115937546A (en) | Image matching method, three-dimensional image reconstruction method, image matching device, three-dimensional image reconstruction device, electronic apparatus, and medium | |
| CN115170815A (en) | Method, device and medium for processing visual task and training model | |
| CN113657411A (en) | Neural network model training method, image feature extraction method and related device | |
| CN108734718B (en) | Processing method, device, storage medium and equipment for image segmentation | |
| CN113837194A (en) | Image processing method, image processing apparatus, electronic device, and storage medium | |
| CN110377776B (en) | Method and device for generating point cloud data | |
| CN113362090A (en) | User behavior data processing method and device | |
| CN110634155A (en) | Target detection method and device based on deep learning | |
| CN112256254A (en) | Method and device for generating layout code | |
| CN113129369A (en) | Point cloud map initialization method and device | |
| CN113761090B (en) | Positioning method and device based on point cloud map | |
| CN113742485A (en) | Method and device for processing text | |
| CN111428729A (en) | Target detection method and device | |
| CN109657523B (en) | Driving region detection method and device | |
| CN111783572A (en) | Text detection method and device |
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 |