COSSY paper published in Energy and Buildings – March 2024

Our paper summarizing outcomes of an ARPA-E grant on a Computational Occupancy Sensing SYstem (COSSY) has been published in  Elsevier Energy and Buildings: J. Konrad, M. Cokbas, P. Ishwar, T.D.C.Little, and M. Gevelber, “High-accuracy people counting in large spaces using overhead fisheye cameras,” Energy Build., vol. 307, p. 113936, Mar. 2024.

Paper on detection of social-distancing violations accepted at VISAPP-2023

Our paper: Zhangchi Lu, Mertcan Cokbas, Prakash Ishwar and Janusz Konrad,  “Estimating Distances Between People using a Single Overhead Fisheye Camera with Application to Social-Distancing Oversight”, has been accepted at the 18th International Conference on Computer Vision theory and Applications (VISAPP) to be held in Lisbon, Portugal, Feb. 19-21, 2023  (

Paper describing new dataset FRIDA accepted at AVSS-2022

Our paper: M. Cokbas, J. Bolognino,  J. Konrad and P. Ishwar, “FRIDA: Fisheye Re-Identification Dataset with Annotations“, has been accepted at the 18th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS),  November 29 – December 2, 2022 (

Patent on occupancy sensing in buildings awarded

A new patent has been awarded to the COSSY team: J. Konrad, P. Ishwar, T. Little, and M. Gevelber, Fusion-based occupancy sensing for building systems, US Patent 11,193,688, Dec. 7, 2021. This patent is one of the fruits of an ARPA-E supported project on occupancy sensing in commercial buildings.

Paper accepted at WACV 2022

Our paper: M.O. Tezcan, Z. Duan, M. Cokbas, P. Ishwar, and J. Konrad, “WEPDTOF: A Dataset and Benchmark Algorithms for In-the-Wild People Detection and Tracking from Overhead Fisheye Cameras” was accepted at the 2022 Winter Conference on Applications of Computer Vision (WACV) to be held January 4-7, 2022 in Waikoloa, HI (

Paper accepted at AVSS 2021

Our paper: J. Bone, M. Cokbas, O. Tezcan, J. Konrad and P. Ishwar, “Geometry-based person re-identification in fisheye stereo” was accepted at the 2021 IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS)  to be held virtually Nov. 16-19, 2021 (

BSUV-Net featured in an online article

BSUV-Net (Background Subtraction for Unseen Videos), a toolbox of algorithms for detecting changes in video streams developed by PhD candidate M. Ozan Tezcan,  has been recently featured in an article on the website of the Rafik B. Hariri Institute for Computing and Computational Science & Engineering. 

COSSY featured in two on-line articles

The Computational Occupancy Sensing System (COSSY) under the development with funding from the Advanced Research Projects Agency – Energy (ARPA-E) has been recently featured in a College of Engineering article and another one published by The Brink. Both focus on the the applicability of COSSY not only to saving energy but also as a tool to provide safe […]

BSUV-Net 2.0 published in IEEE Access

Two extensions of the original BSUV-Net (Background Subtraction for Unseen Videos) deep-learning algorithm have been published in a recent article: M. Tezcan, P. Ishwar, and J. Konrad, “BSUV-Net 2.0: Spatio-temporal data augmentation for video-agnostic supervised background subtraction,” IEEE Access, vol. 9, pp. 53849-53860, Apr. 2021.

3 papers accepted to CVPR workshops

Our papers have been accepted to CVPR workshops: Z. Duan, M.O. Tezcan, H. Nakamura, P. Ishwar and J. Konrad, “RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images”, in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Omnidirectional Computer Vision in Research and Industry (OmniCV) Workshop, June 2020. M.Cokbas, P. Ishwar, and J. Konrad, “Low-Resolution […]