Download presentation
Presentation is loading. Please wait.
1
Week 9 Emily Hand UNR
2
This Week Blended Template Partial SVM Model Speed Motion Model
Improvements/Debugging/Testing Finding best parameters Partial SVM Model Debugging/Testing Speed Decrease Speed of both methods Motion Model Used to help detector
3
Blended Template SVM for entire template is used to find the location in the next frame Confidence of each block extracted using blockSVM function A new template is constructed from positive blocks Blended with most recent positive blocks to form a complete template
4
Blended Template Ex 1
5
Example 1 Tracked Successfully: 36 Frames
First frame – full occlusion 40% Partial Occlusion: Frames 33-36 Full Occlusion: Frame 37 Time Per Frame: ~5 minutes Threshold: 0.40
6
Example 1 Partial
7
Example 2
8
Example 2 Tracked Successfully: 57 frames
First full instance – end of sequence 100% Partial Occlusion: Frames 40-48 Full Occlusion: None Time Per Frame: ~5 minutes Threshold: 0.40
9
Example 2 Partial
10
Example 3
11
Example 3 Tracked Successfully: 21 Frames
First full instance – full occlusion 62% Partial Occlusion: Frames 66-69, 71-74 Full Occlusion: Frame 76 Time Per Frame: ~6 minutes Threshold: 0.40
12
Example 3 Partial
13
Example 3 Partial
14
Example 4
15
Example 4 Tracked Successfully: 84 Frames
First full instance – end of sequence 100% Partial Occlusion: Frames 35-42 Full Occlusion: None Time Per Frame: ~7 minutes Threshold: 0.40
16
Example 4
17
Example 5
18
Example 5 Tracked Successfully: 133 Frames
First full instance – end of sequence 100% Partial Occlusion: Frames , Full Occlusion: None Time Per Frame: ~30 seconds Threshold: 0.40
19
Example 5 Partial
20
Example 5 Partial
21
Example 6
22
Example 6 Tracked Successfully: 46 Frames
First full instance – full occlusion 56% Partial Occlusion: Frames 30-32, 42-46 Full Occlusion: 47-50 Time Per Frame: ~30 seconds Threshold: 0.40
23
Example 6 Partial
24
Example 6 Partial
25
Example 7
26
Example 7 Tracked Successfully: 80 Frames
First full instance – end of sequence 100% Partial Occlusion: Frames Full Occlusion: None Time Per Frame: ~30 seconds Threshold: 0.40
27
Example 7 Partial
28
Conclusions Blended Template Model works for situations without full occlusion. In the case of full occlusion a motion model must be used This can improve our results and allow the detector to continue locating the person after the full occlusion has passed.
29
Partial SVM Test with entire template. Find best match.
If low confidence, then find blocks with a high confidence and train new SVM with those blocks. In next frame, test with both the entire template and the partial SVM model. Find highest match between the two. Worse Results than we expected....
30
Partial SVM
31
Partial SVM
32
Motion Model Used to help detector. A predicted location is computed.
The confidence of each position inside of the search area is computed. The distance of each of these points is computed from the predicted location. If the distance is high, then the confidence at that point is decreased.
33
Blended Template Ex 1 36 Frames → 82 40% → 90%
34
Example 6 46 Frames → 82 56% → 100%
35
Speed Improvement Speed Decreased Search Area
7 minutes → seconds per frame Much faster If the confidence is low for several frames, then the search area grows Once the confidence is high again, the search area shrinks around the confident area.
36
What's Next? New detection ideas 10-15 blocks in a template.
Each has its own SVM Search for these parts and combine them to find best detection.
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.