University of Bristol
  • provision logo

About Us

The Visual Information Laboratory of the University of Bristol exists to undertake innovative, collaborative and interdisciplinary research resulting in world leading technology in the areas of computer vision, image and video communications, content analysis and distributed sensor systems. VI-Lab was formed in 2010, merging the two well established research groups, Signal Processing (EEEng) and Computer Vision (CS). The two constituent groups offer shared and complementary strengths and, with a history of successful collaboration since 1993, their merger has created one of the largest groupings of its type in the UK.

BVI Seminar, Tim Meese, University of Birmingham

Psychophysical probes into spatial vision: you ain’t seen nothin’ yet. 10 March 2017, 4.00 PM – 10 March 2017, 6.00 PM Prof Tim Meese, Professor of Vision Science School of Life and Health Sciences Aston…

Computational cameras

A novel close-to-sensor computational camera has been designed and developed at the ViLab. ROIs can be captured and processed at 1000fps; the concurrent processing enables low latency sensor control and flexible image processing. With 9DoF…

BVI Seminar, Jolyon Troscianko, Exeter University

  Jolyon Troscianko, Postdoctoral Research Fellow, Exeter University The effectiveness of camouflage; predator learning and new modelling approaches Abstract:  Abstract: Evading detection is crucial for the survival of many animals, and number of different means of…

Errata and Corrections – The Visibility of Motion Artifacts and their Effect on Motion Quality

This paper was presented at the “IEEE International Conference on Image Processing (ICIP)”, Phoenix, USA, 2016, and is available on IEEE Xplore An updated version of the paper, which includes corrections, can be downloaded here

Best poster award for SEMBED at BMVA summer school

Second best paper award at the British Machine Vision Association (BMVA) summer school

VILSS: Human Action Recognition and Detection from Noisy 3D Skeleton Data

Mohamed Hussein, Egypt-Japan University of Science and Technology Human action recognition and human action detection are two closely related problems. In human action recogniton, the purpose is to determine the class of an action performed by…

Terrain analysis for biped locomotion

Numerous scenarios exist where it is necessary or advantageous to classify surface material at a distance from a moving forward-facing camera. Examples include the use of image based sensors for assessing and predicting terrain type…

Mitigating the effects of atmospheric turbulence on surveillance imagery

Various types of atmospheric distortion can influence the visual quality of video signals during acquisition. Typical distortions include fog or haze which reduce contrast, and atmospheric turbulence due to temperature variations or aerosols. An effect…

Computer Assisted Analysis of Retinal OCT Imaging

Texture-preserving image enhancement for Optical Coherence Tomography This project developed novel image enhancement algorithms for retinal optical coherence tomography (OCT). These images contain a large amount of speckle causing them to be grainy and of…

VILSS: Global description of images. Application to robot mapping and localisation

VILab Seminar with speaker Luis Payá from Miguel Hernández University, Spain

Next Page »