Murat Üney

Announcements

Our paper on detection of manoeuvring objects in low SNR is accepted to SSPD Conference 2016.

I presented our conference article on distributed multi-sensor calibration in Fusion 2016, Heidelberg on 7th July, Thursday, 13:30pm. Our initially announced tutorial here was withdrawn, unfortunately, due to some unforeseen circumstances.

I gave a tutorial on optimal and adaptive filtering on 27/06/2016 at the UDRC Summer School 2016 in Edinburgh. Last version of the presentation can be downloaded from here.

We submitted an extended version of our ICASSP 2016 work on distributed latent parameter estimation in fusion networks to IEEE TSIPN special issue on inference and learning over networks. The submitted draft can be found here.

We presented our work on a new separable likelihood for distributed parameter estimation in state space models at ICASSP 2016. The 6-page long version which contains proofs can be found here. The slides I used during the presentation are here.

Our cooperative calibration algorithm for distributed fusion networks is now published in IEEE TSP and open access via the ieeexplore link here.

We presented maximum likelihood signal and noise power estimation in active sensors (e.g., radars) via track-before-detect at SSPD 2015 Conference in September.

Our article on the design of random field estimation networks under communication constraints is published in the November 2014 issue of Elsevier Digital Signal Processing.

The MATLAB class @functs can be found at sourceforge and also reached via Matlab Central Link Exchange. I find it easy to build customized message-passing algorithms using this class.

Info

Murat Üney is a Research Fellow at the University of Edinburgh, School of Engineering, Edinburgh, Scotland, UK. He is working on distributed multi-sensor processing with applications in object detection and tracking with networked sensors in challenging scenarios involving, e.g., multiple manoeuvring objects with low signal-to-clutter ratios. His research interests are in the domain of signal and information processing and data/information fusion using statistical paradigms; distributed, resource constrained, multi-sensor, multi-modal problem settings; scalable/approximate statistical inference and learning; probabilistic graphical models, point process models and Monte Carlo computational methods. His current work is supported through the UDRC research programme.