Human tracking using convolutional neural networks

Authors:
Jialue Fan;Wei Xu;Ying Wu;Yihong Gong
Affiliations:
Department of Electrical Engineering and Computer Science, Northwestern University, Evanston, IL;Facebook, Inc., Palo Alto, CA and NEC Laboratories America, Inc., Cupertino, CA;Department of Electrical Engineering and Computer Science, Northwestern University, Evanston, IL;NEC Laboratories America, Inc., Cupertino, CA
Venue:
IEEE Transactions on Neural Networks
Year:
2010

Citing 16
Cited 5

On-Line Selection of Discriminative Tracking Features

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Tracking Multiple Humans in Complex Situations

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Field Model for Human Detection and Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
On-line Boosting and Vision

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Tracking People by Learning Their Appearance

IEEE Transactions on Pattern Analysis and Machine Intelligence
Ensemble Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors

International Journal of Computer Vision
Incremental Learning for Robust Visual Tracking

International Journal of Computer Vision
Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Life Spans

IEEE Transactions on Pattern Analysis and Machine Intelligence
Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
Semi-supervised On-Line Boosting for Robust Tracking

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Robust Object Tracking by Hierarchical Association of Detection Responses

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Tracking nonstationary visual appearances by data-driven adaptation

IEEE Transactions on Image Processing
CAVIAR: a 45k neuron, 5M synapse, 12G connects/s AER hardware sensory-processing-learning-actuating system for high-speed visual object recognition and tracking

IEEE Transactions on Neural Networks
Support vector tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face recognition: a convolutional neural-network approach

IEEE Transactions on Neural Networks

Multi-scale convolutional neural networks for natural scene license plate detection

ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part II
Multi-instance multi-label image classification: A neural approach

Neurocomputing
An adaptive sample count particle filter

Computer Vision and Image Understanding
Part template: 3D representation for multiview human pose estimation

Pattern Recognition
Multi-cue based tracking

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we treat tracking as a learning problem of estimating the location and the scale of an object given its previous location, scale, as well as current and previous image frames. Given a set of examples, we train convolutional neural networks (CNNs) to perform the above estimation task. Different from other learning methods, the CNNs learn both spatial and temporal features jointly from image pairs of two adjacent frames. We introduce multiple path ways in CNN to better fuse local and global information. A creative shift-variant CNN architecture is designed so as to alleviate the drift problem when the distracting objects are similar to the target in cluttered environment. Furthermore, we employ CNNs to estimate the scale through the accurate localization of some key points. These techniques are object-independent so that the proposed method can be applied to track other types of object. The capability of the tracker of handling complex situations is demonstrated in many testing sequences.