Method For Learning Deep Features For Correlation Based Visual Tracking

Date

2017-05-18

Author

Gundogdu, Erhan
Alatan, Abdullah Aydın

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

150
views

0
downloads

In this paper, we address the problem of visual tracking by proposing a novel feature learning technique. Recently, correlation filter based methods have dominated the visual tracking community due to various reasons such as efficient dense matching in frequency domain and simple update strategy. Nevertheless, the studies of correlation filters utilize hand-crafted or pre-trained deep features of classification task without considering the correlation filter cost function. Thus, we attempt to learn deep convolutional features for correlation filter based object tracking. In our experiments on benchmark sequences, we observe a significant improvement over the hand-crafted features while decreasing the number of features utilized in the recent correlation filter based trackers.

Subject Keywords

Correlation filters, Visual tracking, Deep learning

URI

https://hdl.handle.net/11511/55427

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

EXTRACTION OF INTERPRETABLE DECISION RULES FROM BLACK-BOX MODELS FOR CLASSIFICATION TASKS GALATALI, EGEMEN BERK; ALEMDAR, HANDE; Department of Computer Engineering (2022-8-31) In this work, we have proposed a new method and ready to use workflow to extract simplified rule sets for a given Machine Learning (ML) model trained on a classifi- cation task. Those rules are both human readable and in the form of software code pieces thanks to the syntax of Python programming language. We have inspired from the power of Shapley Values as our source of truth to select most prominent features for our rule sets. The aim of this work to select the key interval points in given data in order t...
SPATIAL WINDOWING FOR CORRELATION FILTER BASED VISUAL TRACKING gündoğdu, erhan; Alatan, Abdullah Aydın (2016-09-29) Con-elation filters have been extensively studied to address online visual object tracking task, while achieving favourable performance against the-state-of-the-art methods in various benchmark datasets. Nevertheless, undesired conditions, i.e. partial occlusions or abrupt deformations of the object appearance, severely degrade the performance of con-elation filter based tracking methods. To this end, we propose a method for estimating a spatial window for the object observation such that the correlation ou...
Visual Object Tracking with Autoencoder Representations Besbinar, Beril; Alatan, Abdullah Aydın (2016-05-19) Deep learning is the discipline of training computational models that are composed of multiple layers and these methods have recently improved the state of the art in many areas as a virtue of large labeled datasets, increase in the computational power of current hardware and unsupervised training methods. Although such a dataset may not be available for lots of application areas, the representations obtained by the well-designed networks that have a large representation capacity and trained with enough dat...
A method for quadruplet sample selection in deep feature learning Derin Öznitelik Öǧrenme için Dördüz Örnek Seçme Yöntemi Karaman, Kaan; Gundogdu, Erhan; Koc, Aykut; Alatan, Abdullah Aydın (2018-07-05) Recently, the deep learning based feature learning methodologies have been developed to recognize the objects in fine-grained detail. In order to increase the discriminativeness and robustness of the utilized features, this paper proposes a sample selection methodology for the quadruplet based feature learning. The feature space is manipulated by using the hierarchical structure of the training set. In the training process, the quadruplets are selected by considering the distances between the samples in the...
IMPROVING PROPOSAL-BASED OBJECT DETECTION USING CONVOLUTIONAL CONTEXT FEATURES Kaya, Emre Can; Alatan, Abdullah Aydın (2018-10-10) A novel extension to proposal-based detection is proposed in order to learn convolutional context features for determining boundaries of objects better. Objects and their context are aimed to be learned through parallel convolutional stages. The resulting object and context feature maps are combined in such a way that they preserve their spatial relationship. The proposed algorithm is trained and evaluated on PASCAL VOC 2007 detection benchmark dataset and yielded improvements in performance over baseline, ...

Citation Formats

E. Gundogdu and A. A. Alatan, “Method For Learning Deep Features For Correlation Based Visual Tracking,” 2017, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/55427.