Presentation is loading. Please wait.

Presentation is loading. Please wait.

Online Graph-Based Tracking

Similar presentations


Presentation on theme: "Online Graph-Based Tracking"โ€” Presentation transcript:

1 Online Graph-Based Tracking
Postech Computer Vision Lab. Hyeonseob Nam

2 Outline Introduction Algorithm Overview Main Algorithm Results
Density Propagation Weighted Density Aggregation Model Update Results

3 Visual Tracking Estimate the target state throughout an input video.

4 Motivation Linear chain model assumes the temporal smoothness of two consecutive frames. However, it usually breaks because of fast motion, shot change, occlusion, etc. We propose an algorithm which constructs a graphical model considering the tracking appropriateness. 1 2 3 4 5 6 1 2 3 4 5 6 1 2 3 4 5 6

5 Traditional Linear Model
Sequentially estimate the target posteriors by the temporal order of frames. 1 29 34 43 50 92

6 Bayesian Model Averaging
Tracking easy-to-track frames first, estimate the target posteriors by blind model averaging. 1 29 34 43 50 92 Hong, S., Kwak, S., Han, B.: Orderless tracking through model-averaged posterior estimation. In: ICCV. (2013)

7 Our Approach Keep the temporal tracking order, but select the relevant frames where the posteriors are propagated from. 1 29 34 43 50 92

8 Our Approach

9 Complexity Issue Too many candidate!! Current frame Tracked frames

10 Complexity Issue Current frame Tracked frames Representative frames

11 Algorithm Overview Density Propagation Density Aggregation
Propagate the density functions by patch matching Density Aggregation Aggregate the posteriors regarding the tracking plausibility Model Update Update the set of representative frames

12 Density Propagation Implement Bayesian filtering by patch matching
: A set of samples drawn from Hong, S., Kwak, S., Han, B.: Orderless tracking through model-averaged posterior estimation. In: ICCV. (2013)

13 Density Propagation Matched patches Vote to center Tracked frame ๐’–
New frame ๐’• Matched patches Vote to center Sample 1 Voting map by sample 1 Hong, S., Kwak, S., Han, B.: Orderless tracking through model-averaged posterior estimation. In: ICCV. (2013)

14 Density Propagation Sample 2 Sample 3 Sample 4 Sample |๐•Š t | Posterior ๐’• โ€ฆ votes ๐’• ๐’Œ Hong, S., Kwak, S., Han, B.: Orderless tracking through model-averaged posterior estimation. In: ICCV. (2013)

15 Weighted Density Aggregation
Weighted Bayesian Model Averaging Key problem: How to determine the posterior weights? : A set of representative frames when tracking frame t

16 Determining the weights
๐›ฟ ๐‘ขโ†’๐‘ก : The potential risk resulting from tracking ๐‘ขโ†’๐‘ก ๐‘‘ ๐‘ (๐‘ข,๐‘ก): Deformation cost by patch matching ๐›ฟ ๐‘ข : The minimax distance from the initial frame to ๐‘ข

17 Determining the weights
๐‘‘ ๐‘ (๐‘ข,๐‘ก): Deformation cost by patch matching Current frame: ๐‘ก Target at frame ๐‘ข Temporal target at frame ๐‘ก ๐œ ๐‘ข ๐œ ๐‘ก

18 Determining the weights
๐›ฟ ๐‘ข : The minimax distance from the initial frame to ๐‘ข Current frame: ๐‘ก Current graph structure ๐›ฟ 1 =0 3 7 ๐œน ๐Ÿ‘โ†’๐’• =๐Ÿ’ 8 ๐›ฟ 2 =3 10 ๐œน ๐Ÿโ†’๐’• =๐Ÿ– 4 3 1 ๐œน ๐Ÿ’โ†’๐’• =๐Ÿ๐ŸŽ ๐›ฟ 4 =7 ๐›ฟ 3 =4

19 Model Update Classification False positives Model Update
New target Classification False positives Model Update Redundant or useless templates Representative frames

20 Template Classification
Prevent false tracking results from entering the set of representative frames A set of positive and negative templates New target template ๐œ ๐‘ก โˆ— is positive if the following measure is less than a threshold. ๐‘† ๐‘ : The average Euclidean distance between ๐œ ๐‘ก โˆ— and k-nearest positive templates in ๐ท ๐‘กโˆ’1 ๐‘† ๐‘› : The Euclidean distance between ๐œ ๐‘ก โˆ— and nearest negative templates in ๐ท ๐‘กโˆ’1

21 Maintaining Representative Frames
Each template in the representative set should be distinct and useful for further tracking.

22 Maintaining Representative Frames
Distinctness: Usefulness: Template Weight: Update: where where where

23 Results

24 Identified graph structure

25 Quantitative Results Benchmark Challenges

26 Quantitative Results

27 Summary We propose an adaptive and active algorithm to identify a general graphical model for a robust tracking. A new target posterior is estimated by a selective and weighted model averaging. For efficiency, only a small number of frames capture the important characteristics of input video. Outstanding experimental results on 50 sequences in the tracking benchmark and 10 more challenging sequences show the benefit of our progressive graph construction algorithm.


Download ppt "Online Graph-Based Tracking"

Similar presentations


Ads by Google