\u201c\u5f00\u6e90\u8f6f\u4ef6\u4f9b\u5e94\u94fe\u70b9\u4eae\u8ba1\u5212-\u6691\u671f2020\u201d\uff08\u4ee5\u4e0b\u7b80\u79f0 \u6691\u671f2020\uff09\u662f\u7531\u4e2d\u79d1\u9662\u8f6f\u4ef6\u6240\u4e0e openEuler \u793e\u533a\u5171\u540c\u4e3e\u529e\u7684\u4e00\u9879\u9762\u5411\u9ad8\u6821\u5b66\u751f\u7684\u6691\u671f\u6d3b\u52a8\uff0c\u5c06\u8054\u5408\u5404\u5927\u5f00\u6e90\u793e\u533a\u9488\u5bf9\u91cd\u8981\u5f00\u6e90\u8f6f\u4ef6\u7684\u5f00\u53d1\u4e0e\u7ef4\u62a4\u63d0\u4f9b mini \u9879\u76ee\uff0c\u5b66\u751f\u53ef\u81ea\u4e3b\u9009\u62e9\u7533\u8bf7\u611f\u5174\u8da3\u7684\u9879\u76ee\uff0c\u4e2d\u9009\u540e\u83b7\u5f97\u8be5\u8f6f\u4ef6\u8d44\u6df1\u7ef4\u62a4\u8005\uff08\u5bfc\u5e08\uff09\u4eb2\u81ea\u6307\u5bfc\u5b8c\u6210\u9879\u76ee\u3002<\/p>\n\n\n\n
OpenCV China\u793e\u533a\u53c2\u4e0e\u4e86\u6691\u671f2020\uff0c\u6211\u4eec\u6709\u5982\u4e0bOpenCV\u9879\u76ee\u4efb\u52a1\u6b22\u8fce\u611f\u5174\u8da3\u7684\u540c\u5b66\u7533\u8bf7\uff1a<\/p>\n\n\n\n
\u8d44\u6e90\uff1a<\/strong> \u611f\u5174\u8da3\u7684\u540c\u5b66\u53ef\u53d1\u90ae\u4ef6\u81f3admin@opencv.org.cn<\/strong>\u4e0e\u6211\u4eec\u6c9f\u901a\u9879\u76ee\u7ec6\u8282\u548c\u65b9\u6848\uff0c\u6807\u9898\u8bf7\u6ce8\u660e\u201c\u6691\u671f2020+\u59d3\u540d+\u7533\u8bf7\u9879\u76ee<\/strong>\u201d\u3002\u5177\u4f53\u62a5\u540d\u6d41\u7a0b\u8bf7\u53c2\u8003\u5b66\u751f\u5982\u4f55\u62a5\u540d<\/a><\/strong>\u3002<\/p>\n\n\n\n \u6ce8\uff1a\u622a\u81f3\u76ee\u524d\uff0c\u7533\u8bf7\u540c\u5b66\u7684\u610f\u5411\u96c6\u4e2d\u5728\u9879\u76eeQR code\u548cData Augmentation\uff0c\u5c24\u5176\u96c6\u4e2d\u5728QR code\u3002 \u6691\u671f2020\u7ec4\u59d4\u4f1a\u89c4\u5b9a\u6bcf\u4e2a\u9879\u76ee\u4ec5\u4e00\u540d\u5b9e\u4e60\u751f\u3002<\/p>\n\n\n\n \u7533\u8bf7\u7ed3\u679c<\/strong><\/p>\n\n\n\n \u7ed3\u9879\u901a\u8fc7\u7ed3\u679c<\/strong><\/p>\n\n\n\n \u201c\u5f00\u6e90\u8f6f\u4ef6\u4f9b\u5e94\u94fe\u70b9\u4eae\u8ba1\u5212-\u6691\u671f2020\u201d\uff08\u4ee5\u4e0b\u7b80\u79f0 \u6691\u671f2020\uff09\u662f\u7531\u4e2d\u79d1\u9662\u8f6f\u4ef6\u6240\u4e0e openEuler \u793e\u533a\u5171\u540c\u4e3e\u529e\u7684\u4e00\u9879\u9762\u5411\u9ad8\u6821\u5b66\u751f\u7684\u6691\u671f\u6d3b\u52a8\uff0c\u5c06\u8054\u5408\u5404\u5927\u5f00\u6e90\u793e\u533a\u9488\u5bf9\u91cd\u8981\u5f00\u6e90\u8f6f\u4ef6\u7684\u5f00\u53d1\u4e0e\u7ef4\u62a4\u63d0\u4f9b mini \u9879\u76ee\uff0c\u5b66\u751f\u53ef\u81ea\u4e3b\u9009\u62e9\u7533\u8bf7\u611f\u5174\u8da3\u7684\u9879\u76ee\uff0c\u4e2d\u9009\u540e\u83b7\u5f97\u8be5\u8f6f\u4ef6\u8d44\u6df1\u7ef4\u62a4\u8005\uff08\u5bfc\u5e08\uff09\u4eb2\u81ea\u6307\u5bfc\u5b8c\u6210\u9879\u76ee\u3002 OpenCV China\u793e\u533a\u53c2\u4e0e\u4e86\u6691\u671f2020\uff0c\u6211\u4eec\u6709\u5982\u4e0bOpenCV\u9879\u76ee\u4efb\u52a1\u6b22\u8fce\u611f\u5174\u8da3\u7684\u540c\u5b66\u7533\u8bf7\uff1a \u8d44\u6e90\uff1a– \u5f00\u6e90\u8f6f\u4ef6\u4f9b\u5e94\u94fe\u70b9\u4eae\u8ba1\u5212-\u6691\u671f2020\u5b98\u7f51 – OpenCV\u5b98\u7f51– OpenCV wiki– \u5982\u4f55pull request\/\u5982\u4f55\u8d21\u732e\u4ee3\u7801– \u6e90\u4ee3\u7801\u5730\u5740GitHub\/opencv\u548cGitHub\/opencv_contrib 1. IDEA: Write a tutorial about using universal intrinsics and cv::parallel_for_ for efficient cross-platform algorithm implementation DescriptionUniversal intrinsics is OpenCV way to write cross-platform and yet very efficient code on a variety of platforms. The technique is widely used inside OpenCV,…<\/p>\n
– \u5f00\u6e90\u8f6f\u4ef6\u4f9b\u5e94\u94fe\u70b9\u4eae\u8ba1\u5212-\u6691\u671f2020\u5b98\u7f51<\/a>
– OpenCV\u5b98\u7f51<\/a>
– OpenCV wiki<\/a>
– \u5982\u4f55pull request\/\u5982\u4f55\u8d21\u732e\u4ee3\u7801<\/a>
– \u6e90\u4ee3\u7801\u5730\u5740GitHub\/opencv<\/a>\u548cGitHub\/opencv_contrib<\/a> <\/p>\n\n\n\n1. IDEA: Write a tutorial about using universal intrinsics and <\/strong>
cv::parallel_for_<\/strong><\/code> for efficient cross-platform algorithm implementation<\/strong><\/h4>\n\n\n\n
Universal intrinsics is OpenCV way to write cross-platform and yet very efficient code on a variety of platforms. The technique is widely used inside OpenCV, but it’s not well-known to many OpenCV users, including contributors, who are supposed to provide high-quality fast code into OpenCV. This tutorial should fill this important missing part of the documentation.<\/li>
good experience in C++, some experience with code optimization. Very good English.<\/li>2. IDEA: Create nuget package for OpenCV and OpenCV contrib.<\/strong><\/h4>\n\n\n\n
Nuget is the standard Microsoft package manager. If done properly, it can become the most convenient way to install OpenCV on Windows. We can also create opencv_contrib nuget package, and thus provide a convenient way for OpenCV users to install experimental OpenCV functionality on Windows.<\/li>
good expertise in C++ and Windows development. good English.<\/li>3. IDEA: Support Audio IO module<\/strong><\/h4>\n\n\n\n
At the moment, OpenCV can works with inference deep neural network with help DNN module. But DNN module has limitation, it work with only images. In addition, exist much network which work with audio. That why proposed support audio input\/output in OpenCV for extension functionality of library and more specifically extension functionality of DNN module.<\/li>
Participant is expected to support audio input\/output module for Windows or MacOS family operating system. Will require a study Windows Core Audio APIs (WASAPI) and MacOS Core Audio.<\/li>
experienced in C++, experience in computer vision and OpenCV library. good English.<\/li>4. IDEA: Implementation of QR-codes decoder and encoder<\/strong><\/h4>\n\n\n\n
OpenCV has well-working QR codes detection and decoding algorithm. Currently it uses third party library for decoding and doesn\u2019t have functionality for creation of QR-codes. The first task will be implementation decoder with help of OpenCV functionality. This will help to solve second task \u2013 QR-code encoder (tasks are interconnected). Student will need to research QR-codes decoding algorithms, error correction rules, data character encoding methods and to program decoder and encoder.<\/li>
experienced in C++, OOP, experience of using OpenCV library. good English. <\/li>5. IDEA: Data Augmentation<\/strong><\/h4>\n\n\n\n
Deep learning networks are hungry for data and data augmentation is one of the easiest ways to increase data variation. Augmentation could be as simple image flipping, cropping and scaling on up to more complicated transformations such style transfer using another deep learning network. For computer vision problems, OpenCV is often used for reading images in most of training scenarios, so why we’d like to enhance data reading with simple to use data augmentation techniques as well.<\/li>datasets<\/code> or dnn<\/code>?) with at least the following functionality:
Experience in image processing and deep learning networks training for computer vision problems. good English. <\/li>6. IDEA: Incremental and Batch Simplification of Point Clouds<\/strong><\/h4>\n\n\n\n
With a rapid growth of computer vision application areas such as robotics, self-driving cars, drones, as well as augmented reality, and with increasing availability of various depth sensors, there is also more demand in software that would be able to process point clouds coming from these sensors efficiently in realtime on low-power processors. And so the efficient cloud processing becomes one of OpenCV strategic directions. Reducing the number of points in a point cloud prior to triangulation can be used to simultaneously improve the quality of point clouds and reduce the memory footprint. This project aims at an efficient implementation of the “Incremental and Batch Planar Simplification of Dense Point Cloud Maps paper” (see link in Resources).<\/li>
Extensive experience coding in C++. Prior work with point clouds and libraries such as pcl library<\/a> is a plus. Good English.<\/li>