Install Kinect SDK to VS2010

Environment
VS2010
Kinect Driver 5.1.0.25
OpenNI  1.5.2.23
OpenCV  2.4.0
NITE  1.3.1.3-dev

先安裝OpenNI (Select OpenNI Binaries - Unstable)
再安裝NITE (Select OpenNI Compliant Middleware Binaries - Unstable)
http://www.openni.org/Downloads/OpenNIModules.aspx

最後到Kinect Driver
https://github.com/avin2/SensorKinect

完成的話可以用 OpenNI\Sample\Bin\Release 的 NIViewer.exe 或 NiSimpleViewer.exe
測試 Depth 和 Camera

小心Kinect diver和OpenNI 之間版本的問題
版本錯誤會出現「無法找到程序輸入點」




之後用 OpenNI\Sample\Bin\Release 的 NiUserTracker.exe
測試middleware - NITE

NITE, Kinect diver和OpenNI 之間版本的問題的話
會彈出 can't create any node of the requested type
或 One or more of the following nodes could not be enumerated

發生這個問題需要檢查一下OpenNI, NITE的版本問題
有可能需要重裝全部Driver, OpenNI 和 NITE



安裝library從來都是最浪費時間的工作......


留言

發佈留言

此網誌的熱門文章

[OpenCV] RAW rgb data to IplImage | 以rgb原始資料建立IplImage指標

Sometime we may only got rgb data from source, so we have to build valid IplImage pointer. This sample shows that how to change rgb data to IplImage. 有時我們只會收到rgb資料，所以要自己建立有效的IplImage，以下是將rgb資料轉成IplImage。 VARIABLE DEFINITION 變量定義 rgbtexture    raw rgb data get from the camera | 由視訊傳來的rgb原始資料 cpimg          IplImage to store the RAW rgb data | 用來存rgb原始資料的IplImage變量 arr                simple opencv data format | 基本的opencv的資料格式 According  to IplImage definition | 根據IplImage的定義 typedef struct _IplImage {     int  nSize;             /* sizeof(IplImage) */     int  ID;                /* version (=0)*/     int  nChannels;    /* Most of OpenCV functions suppor...
閱讀更多

Monitoring System Spec.& IO Mapping

This is the sophie SEM2012 Monitoring System Spec.& IO Mapping sheet I/O Number of I/O Measure point Solar panel 6 VI Converter 3 VI Battery 1 VI Motor driver 1 VI Motor 1 V, speed( by reed switch ) Total 12 23+1 Arduino Number of Analog I/O Mega2560 16 X2 Total Mega2560 x2 32 Because of Arduino x2, need 2 analog I/O for I2C communication Total Analog I/O used Number of analog I/O 27+1 32 Radio Frequency Features ( data rate ) 4800bps -> 600Bps ->75chars ps 1 point of measurement( e.g. 15.34 ) = 4 digits + dot + space = 6 chars Total Measurement (chars) Data to stream (chars) 2...
閱讀更多

face detection | 臉部偵測

This is the basic face detection method provided by OpenCV. The algorithm behind is Haar-like feature*. The database (haarcascade_frontalface_alt2.xml) that is needed is in the opencv directory that you installed. This database only can detect front face. Flow: 1. load database(.xml) -> 2. cvHaarDetectObjects() detect face -> 3. receive data in cvrect format 這裡的臉部偵測是用OpenCV提供的基本功能。演算法是哈爾特徵*，數據庫(haarcascade_frontalface_alt2.xml)在安裝opencv的位置內。 流程： 1. 讀入數據庫(.xml) -> 2. 用cvHaarDetectObjects()辯認臉部 -> 3. 以cvrect接收位置 1. OpenCV provide function to read in database, if data read in is failed, cvLoad will return 0, so we can use if(!cascade) to check. 讀入數據庫的話可以直接使用OpenCV函式，如果讀入不成功的話 cvLoad 會歸還 0， 所以可以用if(!cascade)檢查。 CvHaarClassifierCascade *cascade=NULL; cascade = (CvHaarClassifierCascade*)cvLoad( CASCADEPATH, 0, 0, 0 ); if (!cascade)      exit(0); 2. if cascade successfully loaded in, we can load our source, after that call cvHaarDet...
閱讀更多