GPU-Accelerated Real-Time Surveillance De-Weathering
Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
A fully automatic de-weathering system to increase the visibility/stability in surveillance applications during bad weather has been developed. Rain, snow and haze during daylight are handled in real-time performance with acceleration from CUDA implemented algorithms. Video from fixed cameras is processed on a PC with no need of special hardware except an NVidia GPU. The system does not use any background model and does not require any precalibration. Increase in contrast is obtained in all haze/rain/snow-cases while the system lags the maximum of one frame during rain or snow removal. De-hazing can be obtained for any distance to simplify tracking or other operating algorithms on a surveillance system.
Place, publisher, year, edition, pages
2013. , 64 p.
CUDA, de-haze, de-rain, de-snow, image enhancement
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-97401ISRN: LiTH-ISY-EX--13/4677--SEOAI: oai:DiVA.org:liu-97401DiVA: diva2:647937
Saab Dynamics AB
Subject / course
Computer Vision Laboratory