Browsing by Author "Esen, E."

Now showing 1 - 4 of 4

Open Access
Background subtraction with a moving camera
(IEEE, 2013) Topçu O.; Kalem, Aslıhan; Esen, E.
Moving object segmentation with a nonstationary camera is a difficult problem due to the motion of both camera and the object. A moving object segmentation method is proposed in this work to be used in pan-tilt-zoom (PTZ) cameras. The method is based on composing scene mosaic and applying Gaussian mixture background subtraction algorithm after constructing a background model using the mosaic. Background subtraction is performed by mapping the frames captured during camera's course of motion to the background mosaic. The proposed mosaic building method requires less number of picture correspondences when compared to known methods. The success of the proposed segmentation method is demonstrated by the conducted experiments. © 2013 IEEE.
Open Access
The COST292 experimental framework for TRECVID 2007
(National Institute of Standards and Technology, 2007) Zhang, Q.; Corvaglia, M.; Aksoy, Selim; Naci, U.; Adami, N.; Aginako, N.; Alatan, A.; Alexandre, L. A.; Almeida, P.; Avrithis, Y.; Benois-Pineau, J.; Chandramouli, K.; Damnjanovic, U.; Esen, E.; Goya, J.; Grzegorzek, M.; Hanjalic, A.; Izquierdo, E.; Jarina, R.; Kapsalas, P.; Kompatsiaris, I.; Kuba, M.; Leonardi, R.; Makris, L.; Mansencal, B.; Mezaris, V.; Moumtzidou, A.; Mylonas, P.; Nikolopoulos, S.; Piatrik, T.; Pinheiro, A. M. G.; Reljin, B.; Spyrou, E.; Tolias, G.; Vrochidis, S.; Yakın, G.; Zajic, G.
In this paper, we give an overview of the four tasks submitted to TRECVID 2007 by COST292. In shot boundary (SB) detection task, four SB detectors have been developed and the results are merged using two merging algorithms. The framework developed for the high-level feature extraction task comprises four systems. The first system transforms a set of low-level descriptors into the semantic space using Latent Semantic Analysis and utilises neural networks for feature detection. The second system uses a Bayesian classifier trained with a "bag of subregions". The third system uses a multi-modal classifier based on SVMs and several descriptors. The fourth system uses two image classifiers based on ant colony optimisation and particle swarm optimisation respectively. The system submitted to the search task is an interactive retrieval application combining retrieval functionalities in various modalities with a user interface supporting automatic and interactive search over all queries submitted. Finally, the rushes task submission is based on a video summarisation and browsing system comprising two different interest curve algorithms and three features.
Open Access
Image segmentation with unified region and boundary characteristics within recursive shortest spanning tree
(IEEE, 2007) Esen, E.; Alp, Yaşar Kemal
The lack of boundary information in region based image segmentation algorithms resulted in many hybrid methods that integrate the complementary information sources of region and boundary, in order to increase the segmentation performance. In compliance with this trend, we propose a novel method to unify the region and boundary characteristics within the canonical Recursive Shortest Spanning Tree algorithm. The main idea is to incorporate the boundary information in the distance metric of RSST with minor changes in the algorithm. Additionaly, we still benefit from the simple yet powerful structure of RSST. The results indicate the superiority of the proposed algorithm with respect to the conventional RSST. The object boundaries are successfully preserved. Therefore, the proposed algorithm is a candidate for video object segmentation where object boundaries coincide with motion field boundaries.
Open Access
A smartphone based surface plasmon resonance imaging (SPRi) platform for on-site biodetection
(Elsevier, 2017) Guner, H.; Ozgur, E.; Kokturk, G.; Celik, M.; Esen, E.; Topal, A. E.; Ayas, S.; Uludag, Y.; Elbuken, C.; Dana, A.
We demonstrate a surface plasmon resonance imaging platform integrated with a smartphone to be used in the field with high-throughput biodetection. Inexpensive and disposable SPR substrates are produced by metal coating of commercial Blu-ray discs. A compact imaging apparatus is fabricated using a 3D printer which allows taking SPR measurements from more than 20.000 individual pixels. Real-time bulk refractive index change measurements yield noise equivalent refractive index changes as low as 4.12 × 10−5 RIU which is comparable with the detection performance of commercial instruments. As a demonstration of a biological assay, we have shown capture of mouse IgG antibodies by immobilized layer of rabbit anti-mouse (RAM) IgG antibody with nanomolar level limit of detection. Our approach in miniaturization of SPR biosensing in a cost-effective manner could enable realization of portable SPR measurement systems and kits for point-of-care applications.