Robust Object Tracking with Online Multiple Instance Learning

Authors:
Boris Babenko;Ming-Hsuan Yang;Serge Belongie
Affiliations:
University of California, San Diego, La Jolla;University of California, Merced, Merced;University of California, San Diego, La Jolla
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2011

Citing 0
Cited 36

Theory of evidence for face detection and tracking

International Journal of Approximate Reasoning
Real-Time object tracking algorithm employing on-line support vector machine and multiple candidate regeneration

ICAISC'12 Proceedings of the 11th international conference on Artificial Intelligence and Soft Computing - Volume Part I
Multiple feature fusion for object tracking

IScIDE'11 Proceedings of the Second Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Real-time visual tracking via online weighted multiple instance learning

Pattern Recognition
Analysis of MILTrack

Proceedings of the 4th International Conference on Internet Multimedia Computing and Service
Real-time compressive tracking

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
To track or to detect? an ensemble framework for optimal selection

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Exploiting the circulant structure of tracking-by-detection with kernels

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
FaceHugger: the ALIEN tracker applied to faces

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Semi-supervised multiple instance learning based domain adaptation for object detection

Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing
Visual tracking with dual modeling

Proceedings of the 27th Conference on Image and Vision Computing New Zealand
Salient instance selection for multiple-instance learning

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part III
Iterative appearance learning with online multiple instance learning

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part V
Euler Principal Component Analysis

International Journal of Computer Vision
Salience-Based prototype selection for k-nearest neighbor classification in multiple-instance learning

IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Online web-data-driven segmentation of selected moving objects in videos

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II
Robust multiple-instance learning with superbags

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II
Structured visual tracking with dynamic graph

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Navigation toward non-static target object using footprint detection based tracking

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
MI2LS: multi-instance learning from multiple informationsources

Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining
Using appearance re-matching to improve real-time compressive tracking

Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
A multiple face detection and tracking system based on TLD

Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
Visual tracking using superpixel-based appearance model

ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
Probabilistic cue integration for real-time object pose tracking

ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
Low-complexity scalable distributed multicamera tracking of humans

ACM Transactions on Sensor Networks (TOSN)
Real-time visual tracking based on an appearance model and a motion mode

ICIC'13 Proceedings of the 9th international conference on Intelligent Computing Theories and Technology
A user supported tracking framework for interactive video production

Proceedings of the 10th European Conference on Visual Media Production
Dynamic Compressive Tracking

Proceedings of International Conference on Advances in Mobile Computing & Multimedia
Discriminative subspace learning with sparse representation view-based model for robust visual tracking

Pattern Recognition
Visual tracking via weakly supervised learning from multiple imperfect oracles

Pattern Recognition
Take your eyes off the ball: Improving ball-tracking by focusing on team play

Computer Vision and Image Understanding
Combining example selection with instance selection to speed up multiple-instance learning

Neurocomputing
A new classification model using privileged information and its application

Neurocomputing
Collaborative object tracking model with local sparse representation

Journal of Visual Communication and Image Representation
Multi-cue based tracking

Neurocomputing
Structured partial least squares for simultaneous object tracking and segmentation

Neurocomputing

Quantified Score

Hi-index	0.14

Visualization

Abstract

In this paper, we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques called “tracking by detection” has been shown to give promising results at real-time speeds. These methods train a discriminative classifier in an online manner to separate the object from the background. This classifier bootstraps itself by using the current tracker state to extract positive and negative examples from the current frame. Slight inaccuracies in the tracker can therefore lead to incorrectly labeled training examples, which degrade the classifier and can cause drift. In this paper, we show that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems and can therefore lead to a more robust tracker with fewer parameter tweaks. We propose a novel online MIL algorithm for object tracking that achieves superior results with real-time performance. We present thorough experimental results (both qualitative and quantitative) on a number of challenging video clips.