Download presentation
Presentation is loading. Please wait.
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 t | Posterior ๐ โฆ votes ๐ ๐ 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
๐ฟ ๐ขโ๐ก : The potential risk resulting from tracking ๐ขโ๐ก ๐ ๐ (๐ข,๐ก): Deformation cost by patch matching ๐ฟ ๐ข : The minimax distance from the initial frame to ๐ข
17
Determining the weights
๐ ๐ (๐ข,๐ก): Deformation cost by patch matching Current frame: ๐ก Target at frame ๐ข Temporal target at frame ๐ก ๐ ๐ข ๐ ๐ก
18
Determining the weights
๐ฟ ๐ข : The minimax distance from the initial frame to ๐ข Current frame: ๐ก Current graph structure ๐ฟ 1 =0 3 7 ๐น ๐โ๐ =๐ 8 ๐ฟ 2 =3 10 ๐น ๐โ๐ =๐ 4 3 1 ๐น ๐โ๐ =๐๐ ๐ฟ 4 =7 ๐ฟ 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 ๐ก โ is positive if the following measure is less than a threshold. ๐ ๐ : The average Euclidean distance between ๐ ๐ก โ and k-nearest positive templates in ๐ท ๐กโ1 ๐ ๐ : The Euclidean distance between ๐ ๐ก โ and nearest negative templates in ๐ท ๐กโ1
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.
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.