Upload
jemima
View
22
Download
0
Embed Size (px)
DESCRIPTION
Learning to Associate: HybridBoosted Multi-Target Tracker for Crowded Scene. Yuan Li, Chang Huang and Ram Nevatia. Yuan Li. outline. Instruction Related work MAP formulation Affinity model Results Conclusion. overview. Introduction. - PowerPoint PPT Presentation
Citation preview
Learning to Associate: HybridBoosted Multi-Target Tracker
for Crowded Scene
Yuan Li, Chang Huang and Ram Nevatia
Yuan Li
outline
• Instruction• Related work• MAP formulation• Affinity model• Results• Conclusion
overview
Introduction
• learning-based hierarchical approach of multi-target tracking
• HybridBoost algorithm-hybrid loss function
• association of tracklet is formulated as a joint problem of ranking and classification
ranking
• the ranking part aims to rank correct tracklet associations higher than other alternatives
classification
• the classification part is responsible to reject wrong associations when no further association should be done
HybridBoost
• combines the merits of the RankBoost algorithm and the AdaBoost algorithm .
RankBoost
• learning to rank as a problem of binary classification on instance pairs
• trains one weak ranker at each round of iteration
• //re-weighted: it decreases the weight of correctly ranked pairs and increases the weight of wrongly ranked pairs.??
adaboost
• http://www.cmlab.csie.ntu.edu.tw/~cyy/learning/tutorials/AdaBoostBinary.pdf
Related work
• the earliest works look at a longer period of time in contrast to frame-by-frame tracking.
• To overcome this, a category of Data Association based Tracking algorithm
• there has been no use of machine learning algorithm in building the affinity model.
MAP formulation
• Robust Object Tracking by Hierarchical Association of Detection Responses
• ours
MAP formulation v1
• R = {ri} the set of all detection responses
MAP formulation v1(cont.)
• tracklet association
MAP formulation v1(cont.)
MAP formulation v2
MAP formulation v2(cont.)
• Inner cost
• Transition cost
MAP formulation v2(cont.)
• With these ,we can rewrite it
Affinity model
• Hybridboost algorithm• Feature pool and weak learner• Training process
Hybridboost algorithm
• Ie.
Hybridboost algorithm(cont.)
Loos function
• initial
Hybridboost algorithm
Feature pool and weak learner
Training process
• T:tracklet set from the previous stage
• G:groundtruth track set
Training process _conti
• For each Ti T, if∈• connecting Ti’s tail to the head of
some other tracklet
• connecting Ti’s head to the tail of some other tracklet before Ti which is also matched to G
Ranking sample set
Binary sample set
Training process (cont.)
• use the groundtruth G and the tracklet set Tk−1 obtained from stage k − 1 to generate ranking and binary classification samples
• learn a strong ranking classifier Hk by the HybridBoost algorithm
• Using Hk as the affinity model to perform association on Tk−1 and generate Tk
Experimental results
• Implementation details• Evaluation metrics• Analysis of the training process• Tracking performance
Implementation details
• dual-threshold strategy to generate short but reliable tracklets
• four stages of association• maximum allowed frame gap 16,
32, 64 and 128• a strong ranking classifier H with
100 weak ranking classifiers• Β=0.75• ζ = 0
Evaluation metrics
track fragments &ID switches
• Traditional ID switch:“two tracks exchanging their ids”.
• ID switch : a tracked trajectory changing its matched GT ID
• track fragments:more strict
compare
Best features
• Motion smoothness (feature type 13 or 14)
• color histogram similarity (feature 4)
• number of miss detected frames in the gap between the two trackelts (feature 7 or 9).
Strong ranking classifier output
Choice of β
Tracking performance
Conclusion and future work
problem
• tracklet ?affinity model?圓圈 ?路徑 ?• automatically select among
various features and corresponding non-parametric
models?Rankboost ? Adaboost?