1. Fast and Robust Object Tracking with Adaptive Detection
Sushil Pratap Bharati, Soumyaroop Nandi, Yanwei Wu, Yao Sui and Guanghui Wang

2. Aim of the research
To develop an autonomous intelligent vision system that assists in autonomous navigation for Unmanned Aerial Vehicles (UAVs)
Automatically localize and track the obstacles present in the trajectory of UAVs in real-time

3. Contributions
Localizes and generates an adaptive bounding box in real-time around the object being tracked as the object changes its shape and size.
Conjoins tracking with detection for long-term error free tracking
Avoids computationally expensive supervised training for detection
Runs automatically without any manual initializations

4. Breakdown
Object Tracking
Salient Object Detection
Post-processing

5. Overview - Flowchart

6. OBJECT TRACKING

7. Correlation Filter based tracking
Filters trained on previously tracked objects and their immediately surrounding background
Small test window is selected on the object that needs to be tracked.
Filter is correlated over a search window in an adjacent frame and a peak value is determined on the correlation output.
Fast Fourier Transform is used to reduce computational complexity

8. Advantages of Correlation Filters
Can track complex objects through rotations, occlusions and other distractions at over 20x the rate of current state-of-the-art techniques.
Tracking is computationally inexpensive O(PlogP) where P is the number of pixels in the tracking window

9. Formulae used in MOSSE (A type of Correlation Filter)

10. Tracking using kernels
Necessity? Sparse Sampling Strategy and Sub-window Overlap
Inability to exploit structure efficiently or ran out of time

11. Classifier and its use
The core component in tracking-by-detection is a classifier. Each frame, a set of samples is collected around the estimated position of the object/target; samples close to the target are labelled +ve and the ones further away are labelled –ve. Updating the classifier with these samples allows it to adapt over time.
In Kernelized Correlation Filtering (KCF), training of a classifier is performed using dense sampling.

12. KCF in action
Kernel Trick can improve the performance by allowing classification on a rich high dimensional features space
Further, we can express ‘w’ as a linear combination of non-linear feature space with kernel trick

13. Closed form solutions

14. Kernel Trick We need to solve for Train using: Kernel correlation:
Track (fast detection) using:

15. SALIENT OBJECT DETECTION

16. Saliency Map and Raster Scan
Salient object detection is formulated as finding the shortest distance from pixel pij to set of pixels B along the image boundary.

17. Parameters for Saliency Map
Since we consider 4-adjacent neighboring pixels to calculate the distance of pij namely; pi-1,j , pi+1,j , pi,j-1 , p i,j+1
A path P = <P(0), P(1), … , P(k)> on I is a sequence of pixels where consecutive pairs of pixels are adjacent
Given a distance cost function D, the distance map for each pixel in I is best defined as
The cost function is given as

18. Parameters for Saliency Map
During the raster scan, pi,j-1 and pi-1,j and during the inverse raster scan, pi,j+1 and pi+1,j are updated using
where,
Thus, each iteration of raster/inverse raster scan updates H and L if path assignment is found to be changed. The final outcome is a saliency map S for region R, where post processing needs to be done to obtain a binary image for final object detection.

19. POST PROCESSING

20. Importance!?
Post processing is vital to enhance the quality of the saliency map S
Obtain a binary image that differentiates a foreground salient object with the background
Applying a direct threshold would not work  Why? Because different scene may have different level of noise content, relative size of objects background, illuminance and reflectance.
Okay, gotcha. So what do we need? – Adaptive Thresholding

21. Adaptive Threshold

23. Mean Intensities

24. DEMO

25. Inter Class Variance

26. Experiments and Curves

27. Comparison Table

28. Our method in Action

29. Our Method in Action

30. THANK YOU