WO2019200807A1 - Appareil et procédé de synthèse d'image et support d'informations lisible par ordinateur - Google Patents

Appareil et procédé de synthèse d'image et support d'informations lisible par ordinateur Download PDF

Info

Publication number
WO2019200807A1
WO2019200807A1 PCT/CN2018/102402 CN2018102402W WO2019200807A1 WO 2019200807 A1 WO2019200807 A1 WO 2019200807A1 CN 2018102402 W CN2018102402 W CN 2018102402W WO 2019200807 A1 WO2019200807 A1 WO 2019200807A1
Authority
WO
WIPO (PCT)
Prior art keywords
matching
feature point
images
panoramic image
point pairs
Prior art date
Application number
PCT/CN2018/102402
Other languages
English (en)
Chinese (zh)
Inventor
王义文
王健宗
肖京
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2019200807A1 publication Critical patent/WO2019200807A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/14—Transformations for image registration, e.g. adjusting or mapping for alignment of images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images

Definitions

  • the present application relates to the field of computer technologies, and in particular, to a panoramic image synthesizing apparatus, method, and computer readable storage medium.
  • the existing splicing technology of panoramic images generally uses the feature matching algorithm to match the same feature points between the photos, and then splicing and merging the photos according to the matching results, but the existing image splicing process lacks the elimination measures of mismatch points.
  • mismatched point in the matching result there will be many defects in the splicing. For example, there are obvious splicing marks at the fused boundary, and the splicing is misaligned, which causes the splicing effect of the entire panoramic image to be poor.
  • the present application provides a panoramic image synthesizing apparatus, method, and computer readable storage medium, the main purpose of which is to improve the panoramic image stitching effect.
  • the present application provides a panoramic image synthesizing apparatus including a memory and a processor in which a panoramic image synthesizing program executable on the processor is stored, the panoramic image synthesizing program being The processor implements the following steps when executed:
  • the images with the matching relationship are merged and processed into a panoramic image
  • the present application further provides a method for synthesizing a panoramic image, the method comprising:
  • the images with the matching relationship are merged and processed into a panoramic image
  • the present application further provides a computer readable storage medium having a panoramic image synthesis program stored thereon, the panoramic image synthesis program being executable by one or more processors, To achieve the steps of the panoramic image synthesis method as described above.
  • FIG. 1 is a schematic diagram of a preferred embodiment of a panoramic image synthesizing apparatus of the present application
  • FIG. 2 is a schematic diagram of a program module of a panoramic image synthesizing program in an embodiment of a panoramic image synthesizing apparatus of the present application;
  • FIG. 3 is a flowchart of a first embodiment of a method for synthesizing a panoramic image according to the present application.
  • the application provides a panoramic image synthesizing device.
  • FIG. 1 a schematic diagram of a preferred embodiment of a panoramic image synthesizing apparatus of the present application is shown.
  • the panoramic image synthesizing device may be a PC (Personal Computer), or may be a terminal device such as a smart phone, a tablet computer, or a portable computer.
  • PC Personal Computer
  • the panoramic image synthesizing device may be a PC (Personal Computer), or may be a terminal device such as a smart phone, a tablet computer, or a portable computer.
  • the panoramic image synthesizing apparatus 1 includes at least a memory 11, a processor 12, a communication bus 13, and a network interface 14.
  • the memory 11 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (for example, an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like.
  • the memory 11 may be an internal storage unit of the panoramic image synthesis device 1, such as a hard disk of the panoramic image synthesis device 1, in some embodiments.
  • the memory 11 may also be an external storage device of the panoramic image synthesizing device 1 in other embodiments, such as a plug-in hard disk equipped on the panoramic image synthesizing device 1, a smart memory card (SMC), and a secure digital (Secure) Digital, SD) cards, flash cards, etc.
  • the memory 11 may also include both an internal storage unit of the panoramic image synthesizing device 1 and an external storage device.
  • the memory 11 can be used not only for storing application software installed in the panoramic image synthesizing device 1 and various types of data, such as codes of the panoramic image synthesizing program 01, but also for temporarily storing data that has been output or is to be output.
  • the processor 12 in some embodiments, may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data processing chip for running program code or processing stored in the memory 11.
  • the data is, for example, a panoramic image synthesis program 01 or the like.
  • Communication bus 13 is used to implement connection communication between these components.
  • the network interface 14 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), and is typically used to establish a communication connection between the device 1 and other electronic devices.
  • a standard wired interface such as a WI-FI interface
  • Figure 1 shows only the panoramic image synthesizing device 1 with the components 11-14 and the panoramic image synthesizing program 01, but it should be understood that not all of the illustrated components are required to be implemented, and more or less may be implemented instead. Component.
  • the device 1 may further include a user interface
  • the user interface may include a display
  • an input unit such as a keyboard
  • the optional user interface may further include a standard wired interface and a wireless interface.
  • the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch sensor, or the like.
  • the display may also be appropriately referred to as a display screen or a display unit for displaying information processed in the panoramic image synthesizing device 1 and a user interface for displaying visualization.
  • the panoramic image synthesis program 01 is stored in the memory 11; when the processor 12 executes the panoramic image synthesis program 01 stored in the memory 11, the following steps are implemented:
  • the client in the following embodiment is an application software that establishes a communication connection with the panoramic image synthesizing device, and the application software can be run on a device such as a mobile phone or a tablet computer, and the user can enter the image capturing mode through the client to collect multiple angles of view.
  • the two-dimensional image uploads the acquired plurality of images to the panoramic image synthesizing device, and simultaneously transmits the panoramic image synthesizing request to the panoramic image synthesizing device.
  • the panoramic image synthesizing device preprocesses the received plurality of images, mainly including performing basic operations of digital image processing such as histogram matching, smoothing filtering, and enhanced transform on the original image, improving image quality, and preparing for subsequent image stitching.
  • the pre-processed multiple images are matched by a preset feature matching algorithm.
  • the preset feature matching algorithm may be an ORB (Oriented FAST and Rotated BRIEF) algorithm, and the ORB algorithm is a fast feature point extraction and The described algorithm is capable of detecting and matching feature points of the two facial images to find matching feature point pairs in the two images.
  • a SIFT (Scale-invariant feature transform) algorithm may also be used to perform feature pair calculation.
  • Determining whether there is a matching relationship between the two images by the number of feature point pairs matched by the algorithm for example, if the number of matching feature point pairs between the two images is less than the first preset threshold, determining the two images There is no matching relationship between them; if the number of matching feature point pairs between the two images is greater than the first preset threshold, it is determined that there is a matching relationship between the two images.
  • the same feature matching algorithm and the preset feature point screening algorithm are used to iteratively match and filter the images with matching relationship.
  • the two matching images with matching relationship are matched according to the feature matching algorithm to obtain matching feature points.
  • the preset feature point screening algorithm the acquired feature point pairs are filtered to delete the feature point pairs that match the errors, and the correct matching feature point pairs are reserved.
  • the two matching images with matching relationship are matched according to the feature matching algorithm to obtain matching feature point pairs; according to the preset feature point screening algorithm, it is determined whether the feature point pairs are correctly matched, so as to filter out the correct matching feature point pairs.
  • the feature point pairs matched according to the preset feature matching algorithm are counted to determine whether the matching result is correct. If the number of statistical feature point pairs in a neighborhood of a feature point is less than a third preset threshold, the feature point is determined to be a pair of feature points that match the error.
  • the statistical feature point pair If a feature point is in a neighborhood of the feature point, the statistical feature point pair If the number is greater than or less than the third preset threshold, then the feature point is determined to be the correct feature point pair.
  • the third preset threshold may be set to a reasonable value according to actual conditions.
  • the number of correct feature point pairs after matching is determined, and it is determined whether it is greater than the second preset threshold. If it is less than the second preset threshold, the feature matching is performed according to the preset feature matching algorithm again, and the matching result is filtered again. According to this process, the calculation is iteratively repeated until the number of pairs of correct feature points is greater than the second predetermined threshold.
  • the number of iteration calculations may be set in advance. In the actual calculation process, the number of iteration calculations is counted. When the number of iterations reaches a preset number of times, the iteration is stopped, and the matching of the complete feature point pairs is performed. And screening.
  • a new processing method for feature point matching is adopted, and the matching and screening of feature points are performed iteratively according to the algorithm, the feature points of each matching error are deleted, the accuracy of feature point matching is improved, and the feature is improved.
  • the matching in the neighborhood of all the feature points is performed by using the mesh division method. According to the statistical result, it is judged whether the matching point is correct, and the number of matching feature point pairs obtained by this method is more than the existing one.
  • There are more algorithms in the algorithm so that the accuracy of the determined registration line is higher when the subsequent images are spliced, so that the splicing occurs at the splicing place, and a good splicing effect can be obtained.
  • the images with matching relationship are merged and combined into a panoramic image.
  • the registration line and the overlapping area between the adjacent two images are determined, and the registration line and the overlapping area can uniquely determine the positions of the two images, and the plurality of images are determined in this manner.
  • the positional relationship is smoothed by the overlapping area between the images to generate a fused image, and the fused image is subjected to ghosting removal to improve image quality.
  • the image display mode is carried in the request, and the image display mode includes a 360-degree panoramic display and a 720-degree panoramic display.
  • the stitched panoramic image is processed by the krpano engine.
  • An html (HyperText Markup Language) page for displaying the panoramic image is generated, and when the user accesses the panoramic image on the client, the html page is sent to the client for display; for the 720 degree panoramic display
  • the stitching result is directly sent to the client, and the client uses the open source OpenGL (Open Graphics Library) technology to display the stitching result.
  • OpenGL Open Graphics Library
  • the panoramic image synthesizing device of the embodiment when receiving the panoramic image synthesis request sent by the client, acquires multiple images corresponding to the request, preprocesses the multiple images, and performs multiple images according to a preset feature matching algorithm. Perform pairwise matching to determine the matching relationship between multiple images, match the two images with matching relationship according to the feature matching algorithm, obtain matching feature point pairs, and select the acquired features according to the preset feature point filtering algorithm. The point pairs are filtered to delete the matching feature point pairs, and the correct matching feature point pairs are retained. According to the matching correct feature point pairs, the matching images are merged and processed into a panoramic image, which is synthesized according to the panoramic image.
  • the method for determining the panoramic image display manner is to send the panoramic image to the client for display.
  • the present application filters the matched feature point pairs, extracts the feature point pairs that match the errors, improves the accuracy of the feature point matching, and reduces the flaws at the splicing.
  • the synthesized panoramic image has a better stitching effect.
  • the panoramic image synthesis program may also be divided into one or more modules, one or more modules are stored in the memory 11 and are composed of one or more processors (this embodiment) Illustrated by the processor 12) to complete the application, a module referred to herein refers to a series of computer program instruction segments capable of performing a particular function for describing the execution of a panoramic image synthesis program in a panoramic image synthesis device.
  • FIG. 2 it is a schematic diagram of a program module of a panoramic image synthesizing program in an embodiment of the panoramic image synthesizing apparatus of the present application.
  • the panoramic image synthesizing program may be divided into an image acquiring module 10 and an image matching module. 20.
  • the feature point screening module 30, the image splicing module 40, and the image sending module 50 are exemplarily:
  • the image obtaining module 10 is configured to: when receiving a panoramic image synthesis request sent by the client, acquire a plurality of images corresponding to the request;
  • the image matching module 20 is configured to: perform pre-processing on the multiple images, and perform pairwise matching on the multiple images according to a preset feature matching algorithm to determine a matching relationship between the multiple images;
  • the feature point screening module 30 is configured to: match the two images having the matching relationship according to the feature matching algorithm, obtain matching feature point pairs, and filter the acquired feature point pairs according to a preset feature point screening algorithm. To delete the feature point pairs that match the error, and keep matching the correct feature point pairs;
  • the image splicing module 40 is configured to: after matching the correct feature point pairs, and merging the images having the matching relationship into a panoramic image;
  • the image sending module 50 is configured to: determine a panoramic image display manner according to the panoramic image synthesis request, and send the synthesized panoramic image to the client display according to the panoramic image display manner.
  • the present application also provides a panoramic image synthesis method.
  • FIG. 3 it is a flowchart of the first embodiment of the panoramic image synthesis method of the present application.
  • the method can be performed by a device that can be implemented by software and/or hardware.
  • the panoramic image synthesis method includes:
  • Step S10 When receiving the panoramic image synthesis request sent by the client, acquire a plurality of images corresponding to the request.
  • Step S20 preprocessing the plurality of images, and performing pairwise matching on the plurality of images according to a preset feature matching algorithm to determine a matching relationship between the plurality of images.
  • the client in the following embodiment is an application software that establishes a communication connection with the panoramic image synthesizing device, and the application software can be run on a device such as a mobile phone or a tablet computer, and the user can enter the image capturing mode through the client to collect multiple angles of view.
  • the two-dimensional image uploads the acquired plurality of images to the panoramic image synthesizing device, and simultaneously transmits the panoramic image synthesizing request to the panoramic image synthesizing device.
  • the panoramic image synthesizing device preprocesses the received plurality of images, mainly including performing basic operations of digital image processing such as histogram matching, smoothing filtering, and enhanced transform on the original image, improving image quality, and preparing for subsequent image stitching.
  • the pre-processed multiple images are matched by a preset feature matching algorithm.
  • the preset feature matching algorithm may be an ORB (Oriented FAST and Rotated BRIEF) algorithm, and the ORB algorithm is a fast feature point extraction and The described algorithm is capable of detecting and matching feature points of the two facial images to find matching feature point pairs in the two images.
  • a SIFT (Scale-invariant feature transform) algorithm may also be used to perform feature pair calculation.
  • Determining whether there is a matching relationship between the two images by the number of feature point pairs matched by the algorithm for example, if the number of matching feature point pairs between the two images is less than the first preset threshold, determining the two images There is no matching relationship between them; if the number of matching feature point pairs between the two images is greater than the first preset threshold, it is determined that there is a matching relationship between the two images.
  • Step S30 Perform matching on the two images having the matching relationship according to the feature matching algorithm, obtain matching feature point pairs, and filter the acquired feature point pairs according to a preset feature point screening algorithm to delete the matching error. Feature point pairs, retain matching the correct feature point pairs.
  • the same feature matching algorithm and the preset feature point screening algorithm are used to iteratively match and filter the images with matching relationship.
  • the two matching images with matching relationship are matched according to the feature matching algorithm to obtain matching feature points.
  • the preset feature point screening algorithm the acquired feature point pairs are filtered to delete the feature point pairs that match the errors, and the correct matching feature point pairs are reserved.
  • the two matching images with matching relationship are matched according to the feature matching algorithm to obtain matching feature point pairs; according to the preset feature point screening algorithm, it is determined whether the feature point pairs are correctly matched, so as to filter out the correct matching feature point pairs.
  • the feature point pairs matched according to the preset feature matching algorithm are counted to determine whether the matching result is correct. If the number of statistical feature point pairs in a neighborhood of a feature point is less than a third preset threshold, the feature point is determined to be a pair of feature points that match the error.
  • the statistical feature point pair If a feature point is in a neighborhood of the feature point, the statistical feature point pair If the number is greater than or less than the third preset threshold, then the feature point is determined to be the correct feature point pair.
  • the third preset threshold may be set to a reasonable value according to the actual situation.
  • the number of correct feature point pairs after matching is determined, and it is determined whether it is greater than the second preset threshold. If it is less than the second preset threshold, the feature matching is performed according to the preset feature matching algorithm again, and the matching result is filtered again. According to this process, the calculation is iteratively repeated until the number of pairs of correct feature points is greater than the second predetermined threshold.
  • the number of iteration calculations may be set in advance. In the actual calculation process, the number of iteration calculations is counted. When the number of iterations reaches a preset number of times, the iteration is stopped, and the matching of the complete feature point pairs is performed. And screening.
  • a new processing method for feature point matching is adopted, and the matching and screening of feature points are performed iteratively according to the algorithm, the feature points of each matching error are deleted, the accuracy of feature point matching is improved, and the feature is improved.
  • the matching in the neighborhood of all the feature points is performed by using the mesh division method. According to the statistical result, it is judged whether the matching point is correct, and the number of matching feature point pairs obtained by this method is more than the existing one.
  • There are more algorithms in the algorithm so that the accuracy of the determined registration line is higher when the subsequent images are spliced, so that the splicing occurs at the splicing place, and a good splicing effect can be obtained.
  • step S40 the images having the matching relationship are merged according to the correct matching feature point pairs, and then synthesized into a panoramic image.
  • Step S50 Determine a panoramic image display manner according to the panoramic image synthesis request, and send the synthesized panoramic image to the client display according to the panoramic image display manner.
  • the registration line and the overlapping area between the adjacent two images are determined, and the registration line and the overlapping area can uniquely determine the positions of the two images, and the plurality of images are determined in this manner.
  • the positional relationship is smoothed by the overlapping area between the images to generate a fused image, and the fused image is subjected to ghosting removal to improve image quality.
  • the image display mode is carried in the request, and the image display mode includes a 360-degree panoramic display and a 720-degree panoramic display.
  • the stitched panoramic image is processed by the krpano engine.
  • An html (HyperText Markup Language) page for displaying the panoramic image is generated, and when the user accesses the panoramic image on the client, the html page is sent to the client for display; for the 720 degree panoramic display
  • the stitching result is directly sent to the client, and the client uses the open source OpenGL (Open Graphics Library) technology to display the stitching result.
  • OpenGL Open Graphics Library
  • the panoramic image synthesis method of the embodiment when receiving the panoramic image synthesis request sent by the client, acquires multiple images corresponding to the request, preprocesses the multiple images, and performs multiple images according to a preset feature matching algorithm. Perform pairwise matching to determine the matching relationship between multiple images, match the two images with matching relationship according to the feature matching algorithm, obtain matching feature point pairs, and select the acquired features according to the preset feature point filtering algorithm. The point pairs are filtered to delete the matching feature point pairs, and the correct matching feature point pairs are retained. According to the matching correct feature point pairs, the matching images are merged and processed into a panoramic image, which is synthesized according to the panoramic image.
  • the method for determining the panoramic image display manner is to send the panoramic image to the client for display.
  • the present application filters the matched feature point pairs, extracts the feature point pairs that match the errors, improves the accuracy of the feature point matching, and reduces the flaws at the splicing.
  • the synthesized panoramic image has a better stitching effect.
  • the embodiment of the present application further provides a computer readable storage medium, where the panoramic image synthesis program is stored, and the panoramic image synthesis program can be executed by one or more processors to implement the following operating:
  • the images with the matching relationship are merged and processed into a panoramic image
  • the technical solution of the present application which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM as described above). , a disk, an optical disk, including a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in the various embodiments of the present application.
  • a terminal device which may be a mobile phone, a computer, a server, or a network device, etc.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)
  • Studio Devices (AREA)

Abstract

La présente invention concerne un appareil de synthèse d'image panoramique, comprenant une mémoire et un processeur, la mémoire stockant un programme de synthèse d'image panoramique pouvant s'exécuter sur le processeur. Les étapes suivantes sont mises en œuvre lorsque le programme est exécuté par le processeur : lorsqu'une demande de synthèse d'image panoramique envoyée par un client est reçue, l'acquisition de multiples images correspondant à la demande ; le prétraitement des multiples images et l'appariement par paires des multiples images selon un algorithme prédéfini d'appariement de caractéristiques afin de déterminer une relation d'appariement entre les multiples images ; et l'appariement de deux images ayant la relation d'appariement selon l'algorithme d'appariement pour acquérir des paires de points de caractéristique appariées, le filtrage des paires de points de caractéristique acquises selon un algorithme prédéfini de filtrage de point de caractéristique et, selon des paires de points de caractéristique correctement appariées, la fusion d'images ayant la relation d'appariement pour former une image panoramique et l'envoi de celle-ci au client à des fins de présentation. La présente invention concerne en outre un procédé de synthèse d'image panoramique et un support d'informations lisible par ordinateur. La présente invention améliore l'effet de juxtaposition pour une image panoramique.
PCT/CN2018/102402 2018-04-20 2018-08-27 Appareil et procédé de synthèse d'image et support d'informations lisible par ordinateur WO2019200807A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810360566.3 2018-04-20
CN201810360566.3A CN108805799B (zh) 2018-04-20 2018-04-20 全景图像合成装置、方法及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2019200807A1 true WO2019200807A1 (fr) 2019-10-24

Family

ID=64093713

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/102402 WO2019200807A1 (fr) 2018-04-20 2018-08-27 Appareil et procédé de synthèse d'image et support d'informations lisible par ordinateur

Country Status (2)

Country Link
CN (1) CN108805799B (fr)
WO (1) WO2019200807A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112991208A (zh) * 2021-03-11 2021-06-18 Oppo广东移动通信有限公司 图像处理方法及装置、计算机可读介质和电子设备

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111291768B (zh) * 2020-02-17 2023-05-30 Oppo广东移动通信有限公司 图像特征匹配方法及装置、设备、存储介质
CN112308782B (zh) * 2020-11-27 2024-06-28 深圳开立生物医疗科技股份有限公司 一种全景图像拼接方法、装置及超声设备和存储介质
CN112991175B (zh) * 2021-03-18 2024-04-02 中国平安人寿保险股份有限公司 一种基于单ptz摄像头的全景图片生成方法及设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101984463A (zh) * 2010-11-02 2011-03-09 中兴通讯股份有限公司 全景图合成方法及装置
US20130076856A1 (en) * 2010-12-24 2013-03-28 Fujifilm Corporation Stereoscopic panorama image creating apparatus, stereoscopic panorama image creating method, stereoscopic panorama image reproducing apparatus, stereoscopic panorama image reproducing method, and recording medium
CN103886569A (zh) * 2014-04-03 2014-06-25 北京航空航天大学 连续帧多特征点无人机侦察图像并行与匹配精度约束的拼接方法
CN104992408A (zh) * 2015-06-30 2015-10-21 百度在线网络技术（北京）有限公司 用于用户终端的全景图像生成方法和装置
CN107392878A (zh) * 2017-05-30 2017-11-24 深圳晨芯时代科技有限公司 一种全景相机的图像融合方法
CN107578373A (zh) * 2017-05-27 2018-01-12 深圳先进技术研究院 全景图像拼接方法、终端设备及计算机可读存储介质

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102750537B (zh) * 2012-05-08 2015-01-07 中国矿业大学 一种高精度图像自动配准方法
CN102819835A (zh) * 2012-07-26 2012-12-12 中国航天科工集团第三研究院第八三五七研究所 一种图像拼接中筛选特征点匹配对的方法
CN105225211A (zh) * 2014-06-19 2016-01-06 中国航天科工集团第三研究院第八三五七研究所 一种基于振动提高视频分辨率的方法
CN104036480B (zh) * 2014-06-20 2017-03-08 天津大学 基于surf算法的快速消除误匹配点方法
CN105389787A (zh) * 2015-09-30 2016-03-09 华为技术有限公司 一种全景图像拼接方法及装置
CN107330436B (zh) * 2017-06-13 2020-07-28 哈尔滨工程大学 一种基于尺度判据的全景图像sift优化方法
CN107833179A (zh) * 2017-09-05 2018-03-23 云南电网有限责任公司昆明供电局 一种红外图像的快速拼接方法及系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101984463A (zh) * 2010-11-02 2011-03-09 中兴通讯股份有限公司 全景图合成方法及装置
US20130076856A1 (en) * 2010-12-24 2013-03-28 Fujifilm Corporation Stereoscopic panorama image creating apparatus, stereoscopic panorama image creating method, stereoscopic panorama image reproducing apparatus, stereoscopic panorama image reproducing method, and recording medium
CN103886569A (zh) * 2014-04-03 2014-06-25 北京航空航天大学 连续帧多特征点无人机侦察图像并行与匹配精度约束的拼接方法
CN104992408A (zh) * 2015-06-30 2015-10-21 百度在线网络技术（北京）有限公司 用于用户终端的全景图像生成方法和装置
CN107578373A (zh) * 2017-05-27 2018-01-12 深圳先进技术研究院 全景图像拼接方法、终端设备及计算机可读存储介质
CN107392878A (zh) * 2017-05-30 2017-11-24 深圳晨芯时代科技有限公司 一种全景相机的图像融合方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112991208A (zh) * 2021-03-11 2021-06-18 Oppo广东移动通信有限公司 图像处理方法及装置、计算机可读介质和电子设备
CN112991208B (zh) * 2021-03-11 2024-05-07 Oppo广东移动通信有限公司 图像处理方法及装置、计算机可读介质和电子设备

Also Published As

Publication number Publication date
CN108805799A (zh) 2018-11-13
CN108805799B (zh) 2021-04-23

Similar Documents

Publication Publication Date Title
WO2019196308A1 (fr) Dispositif et procédé de génération de modèle de reconnaissance faciale, et support d'informations lisible par ordinateur
WO2019200807A1 (fr) Appareil et procédé de synthèse d'image et support d'informations lisible par ordinateur
US10037581B1 (en) Methods systems and computer program products for motion initiated document capture
US11423633B2 (en) Image processing to detect a rectangular object
US10410053B2 (en) Method, apparatus, system, and storage medium for detecting information card in image
US10146795B2 (en) Systems and methods for mobile image capture and processing
US20170111532A1 (en) Real-time processing of video streams captured using mobile devices
US10165201B2 (en) Image processing method and apparatus and terminal device to obtain a group photo including photographer
WO2016127478A1 (fr) Procédé et dispositif de traitement d'image, ainsi que terminal
US10223812B2 (en) Image validation
WO2019052534A1 (fr) Procédé et dispositif d'assemblage d'images et support d'images
WO2022105415A1 (fr) Procédé, appareil et système pour l'acquisition d'image de trame clé, et procédé de reconstruction tridimensionnelle
US9679218B2 (en) Method and apparatus for image matching
US20140198177A1 (en) Realtime photo retouching of live video
CN111062374A (zh) 身份证信息的识别方法、装置、系统、设备及可读介质
US11216961B2 (en) Aligning digital images by selectively applying pixel-adjusted-gyroscope alignment and feature-based alignment models
JP6794284B2 (ja) カメラ機能を有する携帯可能な情報処理装置、その表示制御方法、及びプログラム
JP6669390B2 (ja) 情報処理装置、情報処理方法、及びプログラム
WO2023142732A1 (fr) Procédé et appareil de traitement d'image, et dispositif électronique
US9721371B2 (en) Systems and methods for stitching metallographic and stereoscopic images
WO2019179023A1 (fr) Procédé de traitement d'image d'intérieur, serveur, et support de stockage lisible par ordinateur
US20240202940A1 (en) Feature Detection for Image-Based Augmented Reality
JP7505635B2 (ja) 連続する動的スキャンのセグメンテーション
JP6937282B2 (ja) アノテーション支援システム、アノテーション支援装置およびアノテーション支援方法
CN116778467A (zh) 远距离车牌识别方法、系统、摄像头及可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18915667

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18915667

Country of ref document: EP

Kind code of ref document: A1