Difference between revisions of "Private:Surveillance"

From NMSL
Line 8: Line 8:
 
<table border=1>
 
<table border=1>
 
<tr>
 
<tr>
<td>'''Video'''</td><td>'''#Frames'''</td><td>'''Key Frames'''</td>
+
<td>'''Video'''</td><td>'''#Frames'''</td><td>'''Key Frames'''</td><td>'''Summary Image'''</td>
 
</tr>
 
</tr>
 
<tr>
 
<tr>
<td>#1</td><td>490</td><td>2, 4, 7, 146, 200</td>
+
<td>#1</td><td>490</td><td>2, 4, 7, 146, 200</td><td>[[summary1.bmp]]</td>
 
</tr>
 
</tr>
 
<tr>
 
<tr>
<td>#2</td><td>540</td><td>2, 4, 205, 416, 522</td>
+
<td>#2</td><td>540</td><td>2, 4, 205, 416, 522</td><td>[[summary2.bmp]]</td>
 
</tr>
 
</tr>
 
<tr>
 
<tr>
<td>#3</td><td>420</td><td>10, 132, 396, 416</td>
+
<td>#3</td><td>420</td><td>10, 132, 396, 416</td><td>[[summary3.bmp]]</td>
 
</tr>
 
</tr>
 
</table>
 
</table>
  
 
Summary of Video 1 did not include any frames from the second half of the video. After comparing the sequence with that of Video 2, it was noticed that unlike Video 2, Video 1 starts when the person is in the scene. Therefore, the frames from the second half of the video seem 'normal' and not detected as significant frames. Therefore we tried [http://videos.cctvcamerapros.com/security-camera-videos/ppro-9475-box-camera.html Video 3] which similarly to Video1 is shot in day light but starts with no person in the scene.
 
Summary of Video 1 did not include any frames from the second half of the video. After comparing the sequence with that of Video 2, it was noticed that unlike Video 2, Video 1 starts when the person is in the scene. Therefore, the frames from the second half of the video seem 'normal' and not detected as significant frames. Therefore we tried [http://videos.cctvcamerapros.com/security-camera-videos/ppro-9475-box-camera.html Video 3] which similarly to Video1 is shot in day light but starts with no person in the scene.

Revision as of 18:21, 28 March 2008

In this set of experiments, we investigate applications of our algorithm to summarization of surveillance videos. The algorithm is modified to build the feature matrix using only H and S elements in the HSV color space. The sample videos are taken from CCTV Camera Pros

Video 1 shows a day view of a car, someone approaches the car and steals something from inside and runs away. Video 2 is similar but shot at night. For both videos the first frame which is totally dark and the final advertisements are dropped and not processed. From each a %1 summary is produced.

Video#FramesKey FramesSummary Image
#14902, 4, 7, 146, 200summary1.bmp
#25402, 4, 205, 416, 522summary2.bmp
#342010, 132, 396, 416summary3.bmp

Summary of Video 1 did not include any frames from the second half of the video. After comparing the sequence with that of Video 2, it was noticed that unlike Video 2, Video 1 starts when the person is in the scene. Therefore, the frames from the second half of the video seem 'normal' and not detected as significant frames. Therefore we tried Video 3 which similarly to Video1 is shot in day light but starts with no person in the scene.