490 likes | 616 Views
Learning to Associate: HybridBoosted Multi-Target Tracker for Crowded Scene. Yuan Li, Chang Huang and Ram Nevatia. Yuan Li. Outline. introduction Related work MAP formulation Affinity model Results Conclusion. overview. STAGE 1. STAGE 2. STAGE 3. STAGE 4. Introduction.
E N D
Learning to Associate: HybridBoosted Multi-Target Tracker for Crowded Scene Yuan Li, Chang Huang and Ram Nevatia
Outline • introduction • Related work • MAP formulation • Affinity model • Results • Conclusion
STAGE 1 STAGE 2 STAGE 3 STAGE 4
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 .
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 DataAssociation based Tracking algorithm • there has been no use of machine learning algorithmin 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 v2(cont.) • Inner cost • Transition cost
MAP formulation v2(cont.) • With these ,we can rewrite it
Affinity model • Hybridboostalgorithm • Feature pool and weak learner • Training process
Hybridboostalgorithm • Ie. T2 T1 T3
Loos function • initial
Strong ranking classifier weak weak weak weak Update sample weight Update weight Update weight
Training process • T:tracklet set from the previous stage • G:groundtruth track set
Training process(cont) • For each Ti ∈ T, if • connecting Ti’stail to the head of some other tracklet
Training process(cont) • connecting Ti’s head to the tail of some other tracklet before Ti which is also matched to G
Training process(cont.) • use thegroundtruthG and the tracklet set Tk−1 obtained from stagek − 1 to generate ranking and binary classification samples • learn a strong ranking classifier Hkby the HybridBoost algorithm • UsingHk as the affinity model to perform association on Tk−1and 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
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
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).
Conclusion and future work • Use HybridBoost algorithm to learn the affinity model as a joint problem of ranking and classification • The affinity model is integrated in a hierarchical data association framework to track multiple targets in very crowded scenes.
problem • tracklet ?affinity model?圓圈?路徑? • automatically selectamong various features andcorresponding non-parametric models? Rankboost ? Adaboost? 匈牙利演算法