Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Deep Learning and Preference Learning for Object Tracking: A Combined Approach

Deep Learning and Preference Learning for Object Tracking: A Combined Approach Object tracking is one of the most important processes for object recognition in the field of computer vision. The aim is to find accurately a target object in every frame of a video sequence. In this paper we propose a combination technique of two algorithms well-known among machine learning practitioners. Firstly, we propose a deep learning approach to automatically extract the features that will be used to represent the original images. Deep learning has been successfully applied in different computer vision applications. Secondly, object tracking can be seen as a ranking problem, since the regions of an image can be ranked according to their level of overlapping with the target object (ground truth in each video frame). During object tracking, the target position and size can change, so the algorithms have to propose several candidate regions in which the target can be found. We propose to use a preference learning approach to build a ranking function which will be used to select the bounding box that ranks higher, i.e., that will likely enclose the target object. The experimental results obtained by our method, called $$ DPL ^{2}$$ D P L 2 (Deep and Preference Learning), are competitive with respect to other algorithms. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Neural Processing Letters Springer Journals

Deep Learning and Preference Learning for Object Tracking: A Combined Approach

Download PDF
18 pages

Loading next page...
 
/lp/springer_journal/deep-learning-and-preference-learning-for-object-tracking-a-combined-W5EXJCq6gI
Publisher
Springer Journals
Copyright
Copyright © 2017 by Springer Science+Business Media, LLC
Subject
Computer Science; Artificial Intelligence (incl. Robotics); Complex Systems; Computational Intelligence
ISSN
1370-4621
eISSN
1573-773X
DOI
10.1007/s11063-017-9720-5
Publisher site
See Article on Publisher Site

Abstract

Object tracking is one of the most important processes for object recognition in the field of computer vision. The aim is to find accurately a target object in every frame of a video sequence. In this paper we propose a combination technique of two algorithms well-known among machine learning practitioners. Firstly, we propose a deep learning approach to automatically extract the features that will be used to represent the original images. Deep learning has been successfully applied in different computer vision applications. Secondly, object tracking can be seen as a ranking problem, since the regions of an image can be ranked according to their level of overlapping with the target object (ground truth in each video frame). During object tracking, the target position and size can change, so the algorithms have to propose several candidate regions in which the target can be found. We propose to use a preference learning approach to build a ranking function which will be used to select the bounding box that ranks higher, i.e., that will likely enclose the target object. The experimental results obtained by our method, called $$ DPL ^{2}$$ D P L 2 (Deep and Preference Learning), are competitive with respect to other algorithms.

Journal

Neural Processing Letters – Springer Journals

Published: Oct 23, 2017

References

  • Kernel-based object tracking
    Comaniciu, D; Ramesh, V; Meer, P
  • Statistical comparisons of classifiers over multiple data sets
    Demšar, J
  • Robust online appearance models for visual tracking
    Jepson, AD; Fleet, DJ; El-Maraghi, TF
  • Face recognition: a convolutional neural-network approach
    Lawrence, S; Giles, CL; Tsoi, AC; Back, AD
  • Deep learning
    LeCun, Y; Bengio, Y; Hinton, G
  • A survey of appearance models in visual object tracking
    Li, X; Hu, W; Shen, C; Zhang, Z; Dick, A; Hengel, AVD
  • A competitive neural network for multiple object tracking in video sequence analysis
    Luque-Baena, RM; Ortiz-de Lazcano-Lobato, JM; López-Rubio, E; Domínguez, E; Palomo, EJ
  • Face recognition: a novel deep learning approach
    Pang, S; Yu, Z
  • Incremental learning for robust visual tracking
    Ross, DA; Lim, J; Lin, RS; Yang, MH
  • 80 million tiny images: a large data set for nonparametric object and scene recognition
    Torralba, A; Fergus, R; Freeman, WT
  • Statistical learning theory
    Vapnik, V
  • Object tracking benchmark
    Wu, Y; Lim, J; Yang, M
  • Object tracking: a survey
    Yilmaz, A; Javed, O; Shah, M
  • Convolutional deep networks for visual data classification
    Zhou, S; Chen, Q; Wang, X