PcDuino9 AI visual edge computing development kit - Revision history

Alvin at 08:51, 26 March 2019

2019-03-26T08:51:57Z

Alvin at 06:09, 14 January 2019

2019-01-14T06:09:57Z

Alvin at 09:30, 4 January 2019

2019-01-04T09:30:12Z

Alvin: /* How To Get Video Frames from Hi3516D */

2018-12-26T11:31:50Z

‎How To Get Video Frames from Hi3516D

Alvin at 11:30, 26 December 2018

2018-12-26T11:30:22Z

Alvin: /* How To Get Video Frames from Hi3516D */

2018-12-26T11:25:52Z

‎How To Get Video Frames from Hi3516D

Alvin: /* Resources */

2018-12-26T08:49:31Z

‎Resources

Alvin: /* Hardware Introduction */

2018-12-26T08:25:58Z

‎Hardware Introduction

Alvin: /* Specifications of Hi3516D IPC */

2018-12-26T08:24:56Z

‎Specifications of Hi3516D IPC

Alvin at 08:17, 26 December 2018

2018-12-26T08:17:48Z

@@ Line 1: / Line 1: @@
 == Introduction  ==
-PcDuino9 AI visual edge computing development kit is for image analysis development. The kit includes general IPC using hi3516D solution and pcDuino9 embedded AI visual edge computing module. The kit mainly uses the pcDuino9 embedded AI visual edge computing module to process the video stream acquired from hi3516D, and carries out a series of analysis and processing of the video stream. The kit builds a basic development environment for developers. It provides video frames obtained from hi3516D by pcDuino9，developers can freely develop on the frame maps, such as face detection, license plate detection, object detection and other AI image analysis and processing functions. At the same time, it provides an open API interface. Developers can return the information which were processed on pcDuino9 to hi3516D, and the detected image can be optimized select on hi3516D, and then output them via FTP.
 [[Image:pcDuino9 AI Cam Ai Kit-7.PNG|500px]]

← Older revision		Revision as of 06:09, 14 January 2019
Line 113:		Line 113:

	== Resources ==		== Resources ==
−
−	~~[http://cutedigi.com/products.php?product=pcDuino9-AI-visual-edge-computing-development-kit How to buy it?]~~

@@ Line 75: / Line 75: @@
 [[Image:pcDuino9 AI Cam Ai Kit-13.PNG]]
-== How To Get Video Frames from Hi3516D ==
+== How To Develop ==
 Hi3516 transfers BT1120 data to pcDuino 9. pcDuino 9 converts BT1120 data into MIPI signal through LT8918, and then receives it. At present, it supports 640x480 60FPS frame data transmission. We encapsulate the protocol layer and make it similar to OpenCV style. While reading the frame data, we will return the frame number, which is transmitted by 3516 and is the synchronous frame number for data interaction.
@@ Line 81: / Line 83: @@
 [[Image:pcDuino9 AI Cam Ai Kit-14.PNG]]
-== How to send back the analyzed information to Hi3516D ==
+=== How To Optimize Your Network and Run Object Detect ===
 == Resources ==
 [http://cutedigi.com/products.php?product=pcDuino9-AI-visual-edge-computing-development-kit How to buy it?]

@@ Line 79: / Line 79: @@
 Hi3516 transfers BT1120 data to pcDuino 9. pcDuino 9 converts BT1120 data into MIPI signal through LT8918, and then receives it. At present, it supports 640x480 60FPS frame data transmission. We encapsulate the protocol layer and make it similar to OpenCV style. While reading the frame data, we will return the frame number, which is transmitted by 3516 and is the synchronous frame number for data interaction.
-[[Image:pcDuino9 AI Cam Ai Kit-14.PNG|500px]]
+[[Image:pcDuino9 AI Cam Ai Kit-14.PNG]]
 == How to send back the analyzed information to Hi3516D ==

@@ Line 79: / Line 79: @@
 Hi3516 transfers BT1120 data to pcDuino 9. pcDuino 9 converts BT1120 data into MIPI signal through LT8918, and then receives it. At present, it supports 640x480 60FPS frame data transmission. We encapsulate the protocol layer and make it similar to OpenCV style. While reading the frame data, we will return the frame number, which is transmitted by 3516 and is the synchronous frame number for data interaction.
-#include <iostream>
+[[Image:pcDuino9 AI Cam Ai Kit-14.PNG|500px]]
 == How to send back the analyzed information to Hi3516D ==

@@ Line 79: / Line 79: @@
 Hi3516 transfers BT1120 data to pcDuino 9. pcDuino 9 converts BT1120 data into MIPI signal through LT8918, and then receives it. At present, it supports 640x480 60FPS frame data transmission. We encapsulate the protocol layer and make it similar to OpenCV style. While reading the frame data, we will return the frame number, which is transmitted by 3516 and is the synchronous frame number for data interaction.
- #include <iostream>
+#include <iostream>
- #include <opencv2/opencv.hpp>
+#include <opencv2/opencv.hpp>
- #include "C4L2.hpp"
- using namespace std;
+#include "C4L2.hpp"
- using namespace cv;
- int main(int argc,char *argv[])
+using namespace std;
 using namespace cv;
- string dev = "/dev/video2";
- C4L2Capture *cap = new C4L2Capture;
+int main(int argc,char *argv[])
- int ret = cap->initialzer(dev);
- if(ret < 0){
+	string dev = "/dev/video2";
- cout << "C4L2Capture initialze failed... \n";
+	C4L2Capture *cap = new C4L2Capture;
- return -1;
+	int ret = cap->initialzer(dev);
+	if(ret < 0){
- while(true)
+		cout << "C4L2Capture initialze failed... \n";
+		return -1;
- unsigned int syn = 0; //Frame ID
- Mat frame = cap->read(syn);
+	while(true)
- if(frame.empty()){
- cout << "this frame is empty ...\n";
+		unsigned int syn = 0;  //Frame ID
- break;
+		Mat frame = cap->read(syn);
+		if(frame.empty()){
- cv::imshow("DeepCam LLC",frame);
+			cout << "this frame is empty ...\n";
- cv::waitKey(10);
+			break;
-−
+		}
- cap->destroy();
+		cv::imshow("DeepCam LLC",frame);
- delete cap;
+		cv::waitKey(10);
- return 0;
+	cap->destroy();
 == How to send back the analyzed information to Hi3516D ==

← Older revision		Revision as of 08:49, 26 December 2018
Line 115:		Line 115:
	== Resources ==		== Resources ==

−	[http://cutedigi.com/products.php?product=~~DeepCam~~-~~embedded~~-AI-~~image~~-~~processing~~-~~module~~ How to buy it?]	+	[http://cutedigi.com/products.php?product=pcDuino9-AI-visual-edge-computing-development-kit How to buy it?]

@@ Line 47: / Line 47: @@
 === The introduction of pcDuino9 embedded AI visual edge computing module ===
 '''I/O Diagram'''
@@ Line 61: / Line 62: @@
 [[Image:pcDuino9 AI Cam Ai Kit-3.PNG]]
 '''RK3288 CPU Benchmark'''
 [[Image:pcDuino9 AI Cam Ai Kit-4.jpg|500px]]
 === Specifications of Hi3516D IPC ===

@@ Line 70: / Line 70: @@
 [[Image:pcDuino9 AI Cam Ai Kit-11.PNG]]
-[[Image:pcDuino9 AI Cam Ai Kit-12.PNG]]
+[[Image:pcDuino9 AI Cam Ai Kit-13.PNG]]
 == How To Get Video Frames from Hi3516D ==