Presentation is loading. Please wait.

Presentation is loading. Please wait.

Tracking Learning Detection A Camera that Learns..

Similar presentations


Presentation on theme: "Tracking Learning Detection A Camera that Learns.."— Presentation transcript:

1 Tracking Learning Detection A Camera that Learns.

2 Why is object tracking so important ? surveillance hand recognition scene analysis vehicle detection robot vision motion capture

3

4 Outline - Framework- Key ideas What is TLD intuitively? How does TLD work exactly? Experiment Results Why TLD? - Traditional methods- Challenges to old ways - Tracking- Learning- Detection- TLD

5 Why TLD ?

6

7 Why TLD ? - Traditional method 1 : Tracking Accumulate error. Fail if the object disappears. Only need initialization. Appearance changing & Partial occlusions. (?) Estimate motion over frames

8 Why TLD ? - Traditional method 2 : Detection Off-line Learning Do not fail if the object disappears. Need off-line training. Appearance changing & Partial occlusions. Scan every frame independently

9 Why TLD ? - Challenges to old ways Not fail if the object disappears. Appearance changing. Partial occlusions.

10 Why TLD ? - Challenges to old ways Not fail if the object disappears. Appearance changing. Partial occlusions. TLD is an algorithm that can solve all these tasks !

11 What is TLD intuitively?

12 What is TLD intuitively? - Framework Tracking Detection Off-line Learning

13 What is TLD intuitively? - Framework Tracking Detection On-line Learning Update Location Trajectory fragment Update

14 What is TLD intuitively? - Key ideas 1 : Learning Track & detect Track Detect Updates training examples (add/delete) Update detector Appearance changing.

15 What is TLD intuitively? - Key ideas 2 : Updating True trajectoryTrackingDetection TLD Not fail if no object. Partial occlusions.

16 How does TLD work exactly?

17 How does TLD work exactly? - Framework

18 How does TLD work exactly? - Tracking 1.Reliable point selection: Choose point 1 Discard point 2 - Use forward-backward selection to select 50% of the most reliable points. - Forward-backward selection

19 How does TLD work exactly? - Tracking 2.Median-Flow tracker: Tracks the reliable points between consecutive frames, and estimates displacement using median with confidence proportional to (1/scale of the median).

20 How does TLD work exactly? - Framework

21 How does TLD work exactly? - Detection 2bitBP features Scanning window 2bitBP features Illumination invariance

22 How does TLD work exactly? - Detection Random Forest Posteriors 2bitBP features Scanning window Random Forest If the average posteriors is larger than 50%, consider it an object

23 How does TLD work exactly? - Detection 1-NN classifier Confidence =d - /(d - +d + ) Random Forest Posteriors 2bitBP features Scanning window Feature space

24 How does TLD work exactly? - Framework Pick the one with higher confidence score

25 How does TLD work exactly? - Learning Feature space

26 How does TLD work exactly? - Learning Track & detect Track Detect Updates training examples (add/delete) Update detector

27 How does TLD work exactly? - Learning : Appearance changing problem solved! 9

28 How does TLD work exactly? - Recap : t=0

29 How does TLD work exactly? - Recap : t=1 Decide by confidence score

30 How does TLD work exactly? - Recap : t=1

31 How does TLD work exactly? - Recap : t=2 Remove if false detect

32 Experiment Result

33

34

35

36 Thank you


Download ppt "Tracking Learning Detection A Camera that Learns.."

Similar presentations


Ads by Google