SPATIAL WINDOWING FOR CORRELATION FILTER BASED VISUAL TRACKING

Date

2016-09-29

Author

gündoğdu, 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

126
views

0
downloads

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 output of the correlation filter and the windowed observation (i.e. element-wise multiplication of the window and the observation) is improved, especially in these adverse conditions. This approach leads to a performance uplift in the tracking result compared to the classical windowing operation. Moreover, the estimated spatial window of the object patch indicates the object regions that are useful for con-elation. We observe a considerable amount of performance increase in the benchmark video sequences by using the proposed visual tracking method.

Subject Keywords

Windowing, Visual tracking, Correlation

URI

https://hdl.handle.net/11511/36746

DOI

https://doi.org/10.1109/icip.2016.7532645

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

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...
Numerical implementation of magneto-acousto-electrical tomography (MAET) using a linear phased array transducer GÖZÜ, Mehmet Soner; ZENGİN, Reyhan; Gençer, Nevzat Güneri (2018-02-01) In this study, the performance and implementation of magneto-acousto-electrical tomography (MAET) is investigated using a linear phased array (LPA) transducer. The goal of MAET is to image the conductivity distribution in biological bodies. It uses the interaction between ultrasound and a static magnetic field to generate velocity current density distribution inside the body. The resultant voltage due to velocity current density is sensed by surface electrodes attached on the body. In this study, the theory...
Image Annotation With Semi-Supervised Clustering Sayar, Ahmet; Yarman Vural, Fatoş Tunay (2009-09-16) Methods developed for image annotation usually make use of region clustering algorithms. Visual codebooks are generated from the region clusters of low level features. These codebooks are then, matched with the words of the text document related to the image, in various ways. In this paper, we supervise the clustering process by using three types of side information. The first one is the topic probability information obtained from the text document associated with the image. The second is the orientation an...
Optimum placement of microphone array for sound capture using genetic algoritms Birinci, Isil Yazgan; Leblebicioğlu, Mehmet Kemal (2006-01-01) This paper presents a new method based on genetic algorithm for the optimum placement of microphone arrays for high-quality sound pickup. Microphone arrays are being used for the purposes of direction-of-arrival estimation and tracking of sound sources [1][2] as well as high quality sound capture by focusing on a source [3]. The placement of microphones has direct effect on the sound quality acquired [4][5]. The method proposed in this paper uses a metric function that takes this effect into account and op...
Interacting multiple model probabilistic data association filter using random matrices for extended target tracking Özpak, Ezgi; Orguner, Umut; Department of Electrical and Electronics Engineering (2018) In this thesis, an Interacting Multiple Model – Probabilistic Data Association (IMM-PDA) filter for tracking extended targets using random matrices is proposed. Unlike the extended target trackers in the literature which use multiple alternative partitionings/clusterings of the set of measurements, the algorithm proposed here considers a single partitioning/clustering of the measurement data which makes it suitable for applications with low computational resources. When the IMM-PDA filter uses clustered mea...

Citation Formats

e. gündoğdu and A. A. Alatan, “SPATIAL WINDOWING FOR CORRELATION FILTER BASED VISUAL TRACKING,” 2016, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/36746.