CN112487127B - Crowdsourcing graph building method and device based on color feature distribution and image semantics - Google Patents
Crowdsourcing graph building method and device based on color feature distribution and image semantics Download PDFInfo
- Publication number
- CN112487127B CN112487127B CN202011460638.5A CN202011460638A CN112487127B CN 112487127 B CN112487127 B CN 112487127B CN 202011460638 A CN202011460638 A CN 202011460638A CN 112487127 B CN112487127 B CN 112487127B
- Authority
- CN
- China
- Prior art keywords
- grid
- crowdsourcing
- image
- color
- counted
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Abstract
The invention relates to a crowdsourcing graph establishing method and a crowdsourcing graph establishing device based on color feature distribution and image semantics, wherein the crowdsourcing graph establishing method comprises the following steps: acquiring a crowdsourcing image, and sequentially performing enhancement processing and gray level conversion on the crowdsourcing image to obtain a gray level image; carrying out grid division on the gray level image, and determining a grid to be counted according to semantic information and a dynamic target of the gray level image; counting the color characteristics of the original image corresponding to each grid to be counted, and determining the grids needed by the crowdsourcing graph according to the color characteristics; and constructing a crowdsourcing map according to the image corresponding to the grid of the crowdsourcing map. According to the invention, through the image color feature distribution information, the color statistical information and the semantic information of the image, a judgment basis is provided for the fusion of multiple batches of data with less data volume, and the stability of crowdsourcing map data matching is effectively improved.
Description
Technical Field
The invention belongs to the field of high-precision map making, and particularly relates to a crowd-sourced map building method and device based on color feature distribution and image semantics.
Background
The high-precision map is used as an important data source depending on the automatic driving field, positioning and path planning of automatic driving vehicles can be effectively assisted, but the acquisition and manufacturing period of the professional high-precision map is long, so that data updating is not timely enough, a crowdsourcing layer needs to be established by adopting a crowdsourcing method, and the real-time performance of the high-precision map is improved.
The crowdsourcing map is subjected to three-dimensional reconstruction based on image semantic data of crowdsourcing collection vehicles to generate local map data, and a large number of local maps can be fused to construct the crowdsourcing map. The data fusion process needs to be better matched between local maps, and due to the existence of certain GPS positioning errors, the situation that some local map data are difficult to match occurs.
Disclosure of Invention
In order to solve the problem of poor stability of crowdsourcing map data matching, the invention provides a target detection labeling method in a first aspect, which includes acquiring crowdsourcing images, and sequentially performing enhancement processing and gray level conversion on the crowdsourcing images to obtain gray level images; carrying out grid division on the gray level image, and determining a grid to be counted according to semantic information and a dynamic target of the gray level image; counting the color characteristics of the original image corresponding to each grid to be counted, and determining the grids needed by the crowdsourcing graph according to the color characteristics; and constructing a crowdsourcing map according to the image corresponding to the grid of the crowdsourcing map.
In some embodiments of the present invention, the sequentially performing enhancement processing and gray-scale conversion on the crowdsourced image includes the following steps: enhancing the crowdsourced image according to an edge detection operator; and then carrying out gray level conversion on the enhanced crowdsourcing image to obtain a gray level image.
In some embodiments of the present invention, the grid division of the grayscale image, and determining a grid to be counted according to semantic information and a dynamic target includes the following steps: determining the size of the grid; marking the grid where the dynamic target is located by utilizing semantic information, and calculating the gray level average value of each grid of the rest non-dynamic targets; and traversing and searching the grid position of which the gray value is reduced from the first threshold value to the second threshold value and the reduced value is greater than the jump threshold value, and recursively searching the adjacent grids of which the gray value is less than the second threshold value to record as the grid to be counted.
Further, the step of counting the color features of the original image corresponding to each of the to-be-counted grids and determining the grids required by the crowdsourcing graph according to the color features includes the following steps: dividing the RGB pixel value of the original image corresponding to each grid to be counted into four color intervals; establishing a characteristic color corresponding table according to the four color intervals; if the number of pixels with the same color value in the grid to be counted exceeds a threshold value, determining the grid as a characteristic color grid; if the same characteristic color grid appears in two continuous frames of images, the grid is the grid required by the crowd-sourced graph.
Furthermore, the dividing of the RGB pixel values of the original image corresponding to each of the grids to be counted into four color intervals includes the following steps: dividing the RGB value into four regions of [0-63], [64-127], [ 128-.
Further, if the number of pixels with the same color value in the grid to be counted exceeds a threshold, determining that the grid is a characteristic color grid includes the following steps: and if the number of the pixels with the same color value in the grid to be counted exceeds 50% of the total number of the pixels in the grid, determining the grid as the characteristic color grid.
The invention provides a crowdsourcing image establishing device based on color feature distribution and image semantics, which comprises an acquisition module, a dividing module, a counting module and a construction module, wherein the acquisition module is used for acquiring crowdsourcing images, and sequentially performing enhancement processing and gray level conversion on the crowdsourcing images to obtain gray level images; the dividing module is used for carrying out grid division on the gray level image and determining a grid to be counted according to semantic information and a dynamic target of the gray level image; the statistical module is used for counting the color characteristics of the original image corresponding to each grid to be counted and determining the grids needed by the crowdsourcing graph according to the color characteristics; the construction module is used for constructing the crowdsourcing map according to the image corresponding to the grid of the crowdsourcing map.
Further, the statistical module comprises an establishing module, a first determining module and a second determining module, wherein the establishing module is used for dividing the RGB pixel value of the original image corresponding to each grid to be counted into four color intervals, and establishing a characteristic color corresponding table according to the four color intervals; the first determining module is used for determining the grid as a characteristic color grid if the number of pixels with the same color value in the grid to be counted exceeds a threshold value, and the second determining module is used for determining the grid as a grid required by crowdsourcing drawing if the same characteristic color grid appears in two continuous frames of images.
In a third aspect of the present invention, there is provided an electronic device comprising: one or more processors; the storage device is configured to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method for tagging object detection provided by the first aspect of the present invention.
In a fourth aspect of the present invention, a computer-readable medium is provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements an annotation method for object detection provided in the first aspect of the present invention.
The invention has the beneficial effects that:
1. according to the invention, through the image color feature distribution information, the color statistical information and the semantic information of the image, a judgment basis is provided for the fusion of multiple batches of data with less data volume, and the stability of crowdsourcing map data matching is effectively improved.
Drawings
FIG. 1 is a basic flow diagram of a crowd-sourced graph construction method based on color feature distribution and image semantics in some embodiments of the invention;
FIG. 2 is a flow diagram illustrating a method for crowd-sourced rendering based on color feature distribution and image semantics in some embodiments of the invention;
FIG. 3 is a diagram illustrating the effect of meshing in some embodiments of the present invention;
FIG. 4 is a diagram illustrating the effect of tagging dynamic objects with semantic information in some embodiments of the invention;
FIG. 5 is a basic block diagram of a crowd-sourced rendering device based on color feature distribution and image semantics in some embodiments of the invention;
FIG. 6 is a basic block diagram of an electronic device in some embodiments of the invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1 and fig. 2, in a first aspect of the present invention, a crowd-sourced mapping method based on color feature distribution and image semantics is provided, including: s101, acquiring a crowdsourcing image, and sequentially performing enhancement processing and gray level conversion on the crowdsourcing image to obtain a gray level image; s102, carrying out grid division on the gray level image, and determining a grid to be counted according to semantic information and a dynamic target of the gray level image; s103, counting the color characteristics of the original image corresponding to each grid to be counted, and determining grids needed by crowdsourcing graph establishment according to the color characteristics; and S104, constructing a crowdsourcing map according to the image corresponding to the grid of the crowdsourcing map.
In step S101 of some embodiments of the present invention, the sequentially performing enhancement processing and grayscale conversion on the crowdsourcing image includes the following steps: enhancing the crowdsourced image according to an edge detection operator; and then carrying out gray level conversion on the enhanced crowdsourcing image to obtain a gray level image.
Specifically, in order to reduce interference of dynamic objects such as ground vehicles, only the upper half of the picture of the vehicle-end camera is processed. Then, enhancing the image edge of the crowdsourced image according to an edge detection operator; and then carrying out gray level conversion on the enhanced crowdsourcing image to obtain a gray level image. The edge detection operator at least comprises one of Roberts, Sobel, Prewitt, Laplacian, Log/Marr, Canny, Kirsch and Nevitia; preferably, the present invention employs the Laplacian operator (Laplacian).
It can be understood that the image enhancement algorithm also includes adjusting the brightness, contrast, saturation, hue, etc. of the image, increasing its definition, reducing noise, etc.; the image enhancement is usually performed by combining a plurality of algorithms, for example, the image drying is equal to a low-pass filter, the image sharpness is increased by a high-pass filter, and naturally, the enhancement of one image is mainly used for finally obtaining useful information of the image. A general algorithm flow may be: the method comprises the following steps of image drying removal, definition (contrast) increase, gray level adjustment, image edge feature acquisition, image convolution, binarization and the like, wherein the four steps can be realized through different steps.
In step S102 of some embodiments of the present invention, the grid-dividing the grayscale image, and determining a grid to be counted according to the semantic information and the dynamic target includes the following steps: determining the size of the grid; marking the grid where the dynamic target is located by utilizing semantic information, and calculating the gray level average value of each grid of the rest non-dynamic targets; and traversing and searching the grid position of which the gray value is reduced from the first threshold value to the second threshold value and the reduced value is greater than the jump threshold value, and recursively searching the adjacent grids of which the gray value is less than the second threshold value to record as the grid to be counted.
Referring to fig. 3 and 4, specifically, the grayscale image is divided into grids according to a size of 20 × 20 pixels (which may be adjusted according to the size of the acquired image), the grids where the dynamic objects are located are marked by using semantic information, a grayscale average value of each grid of the remaining non-dynamic objects is calculated, a grayscale jump threshold is set to 40, grid positions where the grayscale value is decreased from G1 (a first threshold) to G2 and the decreased value is greater than the jump threshold are searched in a traversal manner, and adjacent grids smaller than the grayscale value G2 (a second threshold) are searched in a recursive manner and recorded as the to-be-counted grids.
Further, in S103 according to some embodiments of the present invention, the counting color features of the original image corresponding to each of the to-be-counted grids, and determining the grid required for the crowd-sourcing graph according to the color features includes the following steps: dividing the RGB pixel value of the original image corresponding to each grid to be counted into four color intervals; establishing a characteristic color corresponding table according to the four color intervals; if the number of pixels with the same color value in the grid to be counted exceeds a threshold value, determining the grid as a characteristic color grid; if the same characteristic color grid appears in two continuous frames of images, the grid is the grid required by the crowd-sourced graph.
Furthermore, the dividing of the RGB pixel values of the original image corresponding to each of the grids to be counted into four color intervals includes the following steps: dividing the RGB value into four regions of [0-63], [64-127], [ 128-.
Further, if the number of pixels with the same color value in the grid to be counted exceeds a threshold, determining the grid as the characteristic color grid includes the following steps:
and if the number of the pixels with the same color value in the grid to be counted exceeds 50% of the total number of the pixels in the grid, determining the grid as the characteristic color grid. Preferably, if the number of the pixel points with the same color value in the grid to be counted accounts for 50% -70% of the total number, the grid is determined to be the characteristic color grid.
It should be noted that, the above feature color information may be matched with GPS position information and image semantic information corresponding to the original image, so as to further improve the stability of crowdsourcing map data fusion acquired multiple times.
Referring to fig. 5, in a second aspect of the present invention, a crowd-sourced image creating apparatus 1 based on color feature distribution and image semantics is provided, including an obtaining module 11, a dividing module 12, a statistics module 13, and a building module 14, where the obtaining module 11 is configured to obtain a crowd-sourced image, and sequentially perform enhancement processing and grayscale conversion on the crowd-sourced image to obtain a grayscale image; the dividing module 12 is configured to perform mesh division on the grayscale image, and determine a mesh to be counted according to semantic information and a dynamic target of the grayscale image; the statistical module 13 is configured to count color features of the original image corresponding to each grid to be counted, and determine a grid required by the crowdsourcing graph according to the color features; the constructing module 14 is configured to construct a crowdsourcing map according to an image corresponding to a grid of the crowdsourcing map.
Further, the statistical module 13 includes an establishing module, a first determining module, and a second determining module, where the establishing module is configured to divide RGB pixel values of the original image corresponding to each grid to be statistically calculated into four color intervals, and establish a characteristic color correspondence table according to the four color intervals; the first determining module is used for determining the grid as a characteristic color grid if the number of pixels with the same color value in the grid to be counted exceeds a threshold value, and the second determining module is used for determining the grid as a grid required by crowdsourcing drawing if the same characteristic color grid appears in two continuous frames of images.
In a third aspect of the present invention, there is provided an electronic device comprising: one or more processors; a storage device, configured to store one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the customized compiling method for high-precision maps provided by the first aspect of the present invention.
Referring to fig. 6, an electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM502, and the RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following devices may be connected to the I/O interface 505 in general: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; a storage device 508 including, for example, a hard disk; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 6 may represent one device or may represent multiple devices as desired.
In particular, according to an embodiment 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 via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program, when executed by the processing device 501, performs the above-described functions defined in the methods of embodiments of the present disclosure. It should be noted that the computer readable medium described in the embodiments of the present disclosure may 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 embodiments of the disclosure, 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 embodiments of the present disclosure, however, a computer readable signal medium may comprise 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: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may be separate and not incorporated into the electronic device. The computer-readable medium carries one or more computer programs which, when executed by the electronic device, cause the electronic device to:
computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, Python, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
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 disclosure. 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 and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (7)
1. A crowd-sourced graph building method based on color feature distribution and image semantics is characterized by comprising the following steps:
acquiring a crowdsourcing image, and sequentially performing enhancement processing and gray level conversion on the crowdsourcing image to obtain a gray level image;
carrying out grid division on the gray level image, and determining a grid to be counted according to semantic information and a dynamic target of the gray level image; marking the grid where the dynamic target is located by utilizing semantic information, and calculating the gray level average value of each grid of the rest non-dynamic targets; traversing and searching grid positions of which the gray values are reduced from the first threshold value to the second threshold value and the reduction values are greater than the jump threshold value, and recursively searching adjacent grids of which the gray values are less than the second threshold value and recording the grids as grids to be counted;
counting the color characteristics of the original image corresponding to each grid to be counted, and determining the grids required by crowdsourcing drawing according to the color characteristics, namely dividing the RGB pixel value of the original image corresponding to each grid to be counted into four color intervals; establishing a characteristic color corresponding table according to the four color intervals; if the number of pixels with the same color value in the grid to be counted exceeds a threshold value, determining the grid as a characteristic color grid; if the same characteristic color grid appears in two continuous frames of images, the grid is the grid required by the crowdsourcing drawing;
and constructing a crowdsourcing map according to the image corresponding to the grid of the crowdsourcing map.
2. The method as claimed in claim 1, wherein the step of sequentially performing enhancement processing and gray scale conversion on the crowdsourced image comprises the steps of:
enhancing the crowdsourced image according to an edge detection operator;
and then carrying out gray level conversion on the enhanced crowdsourcing image to obtain a gray level image.
3. The method as claimed in claim 1, wherein the step of dividing RGB pixel values of the original image corresponding to each of the meshes to be counted into four color intervals comprises the steps of:
dividing the RGB value into four regions of [0-63], [64-127], [ 128-.
4. The method as claimed in claim 1, wherein if the number of pixels with the same color value in the to-be-counted mesh exceeds a threshold, determining the mesh as a feature color mesh comprises:
and if the number of the pixels with the same color value in the grid to be counted exceeds 50% of the total number of the pixels in the grid, determining the grid as the characteristic color grid.
5. A crowdsourcing graph establishing device based on color feature distribution and image semantics is characterized by comprising an acquisition module, a division module, a statistic module and a construction module,
the acquisition module is used for acquiring a crowdsourcing image, and sequentially performing enhancement processing and gray level conversion on the crowdsourcing image to obtain a gray level image;
the dividing module is used for carrying out grid division on the gray level image, determining a grid to be counted according to semantic information and a dynamic target of the gray level image, and determining the size of the grid; marking the grids where the dynamic targets are located by utilizing semantic information, and calculating the gray level average value of each grid of the rest non-dynamic targets; traversing and searching grid positions of which the gray values are reduced from the first threshold value to the second threshold value and the reduction values are greater than the jump threshold value, and recursively searching adjacent grids of which the gray values are less than the second threshold value and recording the grids as grids to be counted;
the statistical module is used for counting the color characteristics of the original image corresponding to each grid to be counted and determining the grids required by the crowdsourcing graph according to the color characteristics, namely dividing the RGB pixel value of the original image corresponding to each grid to be counted into four color intervals; establishing a characteristic color corresponding table according to the four color intervals; if the number of pixels with the same color value in the grid to be counted exceeds a threshold value, determining the grid as a characteristic color grid; if the same characteristic color grid appears in two continuous frames of images, the grid is the grid required by the crowdsourcing drawing;
the construction module is used for constructing the crowdsourcing map according to the image corresponding to the grid of the crowdsourcing map.
6. An electronic device, comprising: one or more processors; storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to carry out the method according to any one of claims 1-4.
7. A computer-readable medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, carries out the method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011460638.5A CN112487127B (en) | 2020-12-12 | 2020-12-12 | Crowdsourcing graph building method and device based on color feature distribution and image semantics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011460638.5A CN112487127B (en) | 2020-12-12 | 2020-12-12 | Crowdsourcing graph building method and device based on color feature distribution and image semantics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112487127A CN112487127A (en) | 2021-03-12 |
| CN112487127B true CN112487127B (en) | 2022-06-17 |
Family
ID=74916814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011460638.5A Active CN112487127B (en) | 2020-12-12 | 2020-12-12 | Crowdsourcing graph building method and device based on color feature distribution and image semantics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112487127B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777269A (en) * | 2016-12-28 | 2017-05-31 | 深圳市佳都实业发展有限公司 | For the method that the robot and robot that build dynamic map build dynamic map |
| CN108428254A (en) * | 2018-03-15 | 2018-08-21 | 斑马网络技术有限公司 | The construction method and device of three-dimensional map |
| CN111314614A (en) * | 2020-03-11 | 2020-06-19 | 北京字节跳动网络技术有限公司 | Image processing method and device, readable medium and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10504267B2 (en) * | 2017-06-06 | 2019-12-10 | Adobe Inc. | Generating a stylized image or stylized animation by matching semantic features via an appearance guide, a segmentation guide, and/or a temporal guide |
-
2020
- 2020-12-12 CN CN202011460638.5A patent/CN112487127B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777269A (en) * | 2016-12-28 | 2017-05-31 | 深圳市佳都实业发展有限公司 | For the method that the robot and robot that build dynamic map build dynamic map |
| CN108428254A (en) * | 2018-03-15 | 2018-08-21 | 斑马网络技术有限公司 | The construction method and device of three-dimensional map |
| CN111314614A (en) * | 2020-03-11 | 2020-06-19 | 北京字节跳动网络技术有限公司 | Image processing method and device, readable medium and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 全息高精度导航地图: 概念及理论模型;余卓渊等;《地球信息科学》;20200425;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112487127A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106997466B (en) | Method and device for detecting road | |
| US9842386B2 (en) | Image filtering based on image gradients | |
| CN110705583A (en) | Cell detection model training method and device, computer equipment and storage medium | |
| CN112258519B (en) | Automatic extraction method and device for way-giving line of road in high-precision map making | |
| JP7390497B2 (en) | Image processing methods, apparatus, computer programs, and electronic devices | |
| CN111950543A (en) | Target detection method and device | |
| CN110062157B (en) | Method and device for rendering image, electronic equipment and computer readable storage medium | |
| CN111563517B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN113033715B (en) | Target detection model training method and target vehicle detection information generation method | |
| CN112150491B (en) | Image detection method, device, electronic equipment and computer readable medium | |
| CN114202476A (en) | Infrared image enhancement method, device, equipment and computer readable medium | |
| CN114119854A (en) | Shadow rendering method, game file packaging method and corresponding devices | |
| CN116563172B (en) | VR globalization online education interaction optimization enhancement method and device | |
| CN112487127B (en) | Crowdsourcing graph building method and device based on color feature distribution and image semantics | |
| CN110288691B (en) | Method, apparatus, electronic device and computer-readable storage medium for rendering image | |
| CN111091506A (en) | Image processing method and device, storage medium and electronic equipment | |
| CN112330602B (en) | Intelligent trapping direction judgment method and device | |
| CN114241044A (en) | Loop detection method, device, electronic equipment and computer readable medium | |
| CN111815656B (en) | Video processing method, apparatus, electronic device and computer readable medium | |
| CN112435224B (en) | Confidence evaluation method and device for stop line extraction | |
| CN111369676A (en) | Map image processing method and device and vehicle-mounted equipment | |
| CN116993637B (en) | Image data processing method, device, equipment and medium for lane line detection | |
| CN114299127B (en) | Oral cavity image registration method and device, electronic equipment and computer storage medium | |
| CN117649613B (en) | Optical remote sensing image optimization method and device, storage medium and electronic equipment | |
| CN111383337B (en) | Method and device for identifying objects |
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 |