EmguCV DNN使用 YOLOv3 進行物件偵測

沒想到OpenCV 3.4.2版以上已經開始支援YOLOv3

而目前EmguCV也已經更新到4.3.0版本

以C#開發者來說，這比編譯darknet wrapper還來的更方便啊!!

就來看看怎麼在EmguCV中使用YOLOv3吧!!

Face Recognition with FaceNet

Google在2015年提出透過深度學習的方式處理人臉辨識的系統FaceNet

該論文的連結可參考此處

很快的這個方法就席捲了人臉辨識的應用

許多過去傳統的人臉辨識演算法都不敵FaceNet

在論文中提到，其採用LFW人臉資料庫進行benchmark

並以99.63%的準確率，打破了過去的紀錄

而在YouTubeFaces人臉資料庫也進行了測試

依舊創下高達95.12%的準確率

若是想要研究人臉辨識，一定要認識FaceNet

CPU vs GPU、YOLO-darknet vs tensorflow效能比較

既然手邊剛好有三張不同的顯卡：GTX 1080Ti、RTX 2070、RTX 2080

也實作了YOLO-darknet與tensorflow 的 C# wrapper

那就來測試一下運算效能吧!

C# TensorFlowWrapper：Emgu.TF

C#如果要導入TensorFlow套件

常見的有兩套TensorFlowSharp與Emgu.TF

本篇以Emgu.TF為主來做介紹

C#專案在Gitlab上建立CI/CD機制(下)

上一篇所介紹的

主要是透過gitlab runner CI/CD的流程

建立在windows環境下的build server

接著往下就是要建立測試環境

比較理想的流程就像上圖所示

C#專案在Gitlab上建立CI/CD機制(中)

在Gitlab上C#專案建立CI機制(上)

只介紹建立gitlab server到git runner的連結

要在Build Server上能建置專案

還需要安裝一些套件與一些設定

總結需要安裝的有：

1. git 套件，2. nuget 套件，3. MSBuild 套件

本篇還會提供解決的問題有：

1. gitlab查看runner結果會亂碼的問題

2. MSBuild 建置時無目標版本問題

C#專案在Gitlab上建立CI/CD機制(上)

目前公司採用自建的gitlab作為原始碼管控

陸陸續續開始導入CI/CD的機制

本篇主要著重在windows的環境下建立一個支援gitlab的build server

C#有關async/await的實作方式

先來看一下.NET Doc的說明

" C# 5 引進了一種簡化的方法 (非同步程式設計)

來運用 .NET Framework 4.5 和更新版本

.NET Core 以及 Windows 執行階段中的非同步支援 "

C# YOLOWrapper：Alturos.Yolo

由於主要開發環境為C#

因此一開始是從C#的Wrapper著手

GitHub上有一份介紹還蠻完整的Source：Alturos.Yolo

EmguCV Image Process: Process Video Sequences part 5

EmguCV Image Process: Process Video Sequences

參考OpenCV 2 Computer Vision Application Programming Cookbook第十章

介紹內容如下：

Reading video sequences

Processing the video frames

Writing video sequences

Tracking feature points in video

Extracting the foreground objects in video

EmguCV Image Process: Process Video Sequences part 4

EmguCV Image Process: Process Video Sequences

參考OpenCV 2 Computer Vision Application Programming Cookbook第十章

介紹內容如下：

Reading video sequences

Processing the video frames

Writing video sequences

Tracking feature points in video

Extracting the foreground objects in video

EmguCV Image Process: Process Video Sequences part 3

EmguCV Image Process: Process Video Sequences

參考OpenCV 2 Computer Vision Application Programming Cookbook第十章

介紹內容如下：

Reading video sequences

Processing the video frames

Writing video sequences

Tracking feature points in video

Extracting the foreground objects in video

EmguCV Image Process: Process Video Sequences part 2

EmguCV Image Process: Process Video Sequences

參考OpenCV 2 Computer Vision Application Programming Cookbook第十章

介紹內容如下：

Reading video sequences

Processing the video frames

Writing video sequences

Tracking feature points in video

Extracting the foreground objects in video

EmguCV Image Process: Process Video Sequences part 1

EmguCV Image Process: Process Video Sequences

參考OpenCV 2 Computer Vision Application Programming Cookbook第十章

介紹內容如下：

Reading video sequences

Processing the video frames

Writing video sequences

Tracking feature points in video

Extracting the foreground objects in video

EmguCV Image Process: Estimating Projective Relations in Images part4

EmguCV Image Process: Estimating Projective Relations in Images

參考OpenCV 2 Computer Vision Application Programming Cookbook第九章

介紹內容如下：

Calibrating a camera

Computing the fundamental matrix of an image pair

Matching images using random sample consensus

Computing a homography between two images

EmguCV Image Process: Estimating Projective Relations in Images part3

EmguCV Image Process: Estimating Projective Relations in Images

參考OpenCV 2 Computer Vision Application Programming Cookbook第九章

介紹內容如下：

Calibrating a camera

Computing the fundamental matrix of an image pair

Matching images using random sample consensus

Computing a homography between two images

EmguCV Image Process: Estimating Projective Relations in Images part2

EmguCV Image Process: Estimating Projective Relations in Images

參考OpenCV 2 Computer Vision Application Programming Cookbook第九章

介紹內容如下：

Calibrating a camera

Computing the fundamental matrix of an image pair

Matching images using random sample consensus

Computing a homography between two images

EmguCV Image Process: Estimating Projective Relations in Images part1

EmguCV Image Process: Estimating Projective Relations in Images

參考OpenCV 2 Computer Vision Application Programming Cookbook第九章

介紹內容如下：

Calibrating a camera

Computing the fundamental matrix of an image pair

Matching images using random sample consensus

Computing a homography between two images

EmguCV Image Process: Detecting and Matching Interest Points part5

EmguCV Image Process: Detecting and Matching Interest Points

參考OpenCV 2 Computer Vision Application Programming Cookbook第八章

介紹內容如下：

Detecting Harris corners

Detecting FAST features

Detecting the scale-invariant SURF features

Describing SURF features

EmguCV Image Process: Detecting and Matching Interest Points part4

EmguCV Image Process: Detecting and Matching Interest Points

參考OpenCV 2 Computer Vision Application Programming Cookbook第八章

介紹內容如下：

Detecting Harris corners

Detecting FAST features

Detecting the scale-invariant SURF features

Describing SURF features