Difference between revisions of "Private:Surveillance"

From NMSL
 
Line 3: Line 3:
 
[http://videos.cctvcamerapros.com/category/surveillance-video-samples CCTV Camera Pros]
 
[http://videos.cctvcamerapros.com/category/surveillance-video-samples CCTV Camera Pros]
  
[http://videos.cctvcamerapros.com/surveillance-video-samples/30-frames-per-second.html Video 1] shows a day view of a car, someone approaches the car and steals something from inside and runs away. [http://videos.cctvcamerapros.com/surveillance-video-samples/cctv-camera-recording.html Video 2] is similar but shor at night.
+
[http://videos.cctvcamerapros.com/surveillance-video-samples/30-frames-per-second.html Video 1] shows a day view of a car, someone approaches the car and steals something from inside and runs away. [http://videos.cctvcamerapros.com/surveillance-video-samples/cctv-camera-recording.html 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.
 
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.
  
Line 15: Line 15:
 
<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>
 +
</tr>
 +
<tr>
 +
<td>#3</td><td>420</td><td>10, 132, 396, 416</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].
+
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 17:24, 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 Frames
#14902, 4, 7, 146, 200
#25402, 4, 205, 416, 522
#342010, 132, 396, 416

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.