ECE597 Project Auto HUD - Revision history

Xinkeqiong: /* Display Buffer Mapping */

2010-05-21T06:31:29Z

‎Display Buffer Mapping

Xinkeqiong: /* Run Haar Training Program */

2010-05-21T06:31:05Z

‎Run Haar Training Program

Xinkeqiong: /* Sign Detection */

2010-05-21T06:23:41Z

‎Sign Detection

Xinkeqiong: /* Sign Detection */

2010-05-21T06:23:01Z

‎Sign Detection

Show changes

Xinkeqiong: /* OpenCV Haar Training */

2010-05-21T05:51:22Z

‎OpenCV Haar Training

Xinkeqiong: /* Reference */

2010-05-21T05:50:07Z

‎Reference

Xinkeqiong: /* Future Directions */

2010-05-21T05:49:14Z

‎Future Directions

Xinkeqiong: /* Generate Samples */

2010-05-21T05:45:19Z

‎Generate Samples

Xinkeqiong: /* Creating the Positive Index File */

2010-05-21T05:44:36Z

‎Creating the Positive Index File

Xinkeqiong: /* Generate Samples */

2010-05-21T05:43:31Z

‎Generate Samples

@@ Line 513: / Line 513: @@
 In order to get access to the display buffer on the beagle, you will need to run the following in U-Boot
 <pre>
-setenv bootargs console=ttyS2,115200n8 root=/dev/mmcblk0p2 rw rootwait omapfb.mode=1024x768MR-16@60 omapfb.debug=y omapdss.def_disp=dvi omapfb.vram=0:10M,1:10M vram=20M
+setenv bootargs console=ttyS2,115200n8 root=/dev/mmcblk0p2 rw rootwait omapfb.mode=1024x768MR-16@60 omapfb.debug=y
 </pre>

@@ Line 321: / Line 321: @@
 -maxfalsealarm .5 -npos 730 -nneg 835 -w 40 -h 40 -nonsym -mem 2048 -mode ALL
 </pre>
 ==Sign Detection==

@@ Line 394: / Line 394: @@
+     {
 	double fps = cvGetCaptureProperty(capture, CV_CAP_PROP_FPS);
-	CvSize size = cvSize((int)cvGetCaptureProperty(capture, CV_CAP_PROP_FRAME_WIDTH),(int)cvGetCaptureProperty(capture, CV_CAP_PROP_FRAME_HEIGHT));
+	CvSize size = cvSize((int)cvGetCaptureProperty(capture, CV_CAP_PROP_FRAME_WIDTH),(int)cvGetCaptureProperty(capture,
      	cout << "Camera Native Resolution: Width: " << size.width << " Height: " << size.height << endl;

@@ Line 321: / Line 321: @@
 -maxfalsealarm .5 -npos 730 -nneg 835 -w 40 -h 40 -nonsym -mem 2048 -mode ALL
 </pre>
 ==Display Buffer Mapping==

@@ Line 338: / Line 338: @@
 ==Reference==
-Learning OpenCV: Computer Vision with the OpenCV Library, Gary Bradski and Adrian Kaehler
+. Learning OpenCV: Computer Vision with the OpenCV Library, Gary Bradski and Adrian Kaehler
 Haar training Tutorials: http://note.sonots.com/SciSoftware/haartraining.html

← Older revision		Revision as of 05:49, 21 May 2010
Line 336:		Line 336:
	===GStreamer on the DSP===		===GStreamer on the DSP===
	There is a package available for the beagle called gst-dsp, which is a native GStreamer plug-in to give it access to the DSP. Along with gst-opamfb and the dsp-bridge driver, this should allow us to access the DSP directly and output video directly to the framebuffer. OpenCV can interact with GStreamer, so this appears to be a very promising direction for the project. See [http://felipec.wordpress.com/2009/10/13/new-project-gst-dsp-with-beagleboard-demo-image/ this article] for more information and a demonstration. That article also has a link to a minimal beagle image that provides a native framebuffer video player without requiring X.		There is a package available for the beagle called gst-dsp, which is a native GStreamer plug-in to give it access to the DSP. Along with gst-opamfb and the dsp-bridge driver, this should allow us to access the DSP directly and output video directly to the framebuffer. OpenCV can interact with GStreamer, so this appears to be a very promising direction for the project. See [http://felipec.wordpress.com/2009/10/13/new-project-gst-dsp-with-beagleboard-demo-image/ this article] for more information and a demonstration. That article also has a link to a minimal beagle image that provides a native framebuffer video player without requiring X.
		+
		+	==Reference==
		+	Learning OpenCV: Computer Vision with the OpenCV Library, Gary Bradski and Adrian Kaehler
		+	Haar training Tutorials: http://note.sonots.com/SciSoftware/haartraining.html

@@ Line 257: / Line 257: @@
 </pre>
-=== Generate Samples ===
+=== Create Samples ===
 Using the positive samples the creasamples cammand can apply transforms to the images and add them to the background images creating a wider range of images to train on. The syntax for this command is:
 <pre>

@@ Line 190: / Line 190: @@
 		CvPoint bottomRight = pointsClicked.at(i+1);
 		results.push_back( cvRect(topLeft.x,abs(topLeft.y), (bottomRight.x - topLeft.x), abs((topLeft.y - bottomRight.y)) ) );
-   		cout << "Rectangle Created --- X: " << topLeft.x << " Y: " << abs(topLeft.y) << " Width: " << (bottomRight.x - topLeft.x) << " Height: " << abs((topLeft.y - bottomRight.y)) << endl;
+   		cout << "Rectangle Created --- X: " << topLeft.x << " Y: " << abs(topLeft.y) << " Width: " << (bottomRight.x -
+}
@@ Line 231: / Line 232: @@
 	for(int j = 0; j < objectRects.size(); j++)
+	{
-		vecFile << " " << objectRects.at(j).x << " " << objectRects.at(j).y << " " << objectRects.at(j).width << " " << objectRects.at(j).height;
+		vecFile << " " << objectRects.at(j).x << " " << objectRects.at(j).y << " " << objectRects.at(j).width << " " <<
+	}

@@ Line 283: / Line 283: @@
 </pre>
-The second one is to create samples from multiple images which either selected or cropped from the method described above. Using the good images' description file, the command is like below:
+The second one is to create samples from multiple images which either selected or cropped from the method described above. This is the method we used for training stop signs. Because unlike using one standard positive image, the multiple positive samples are much more accurate, comparing with color intensity and image distortion. Using the good images' description file, the command is like below:
 <pre>
 $ opencv-createsamples -info signs.idx -vec signs.vec -w 40 -h 40