Abstract:
Supremo is a cloud-assisted mobile image super-resolution (SR) system. We optimize state-of-the-art DNN to reduce inference latency since SR is compute-intensive.
We also design a mobile-cloud cooperative execution pipeline with specialized data compression algorithms to reduce end-to-end latency and image quality degradation.
Finally, we use a dynamic optimal control algorithm to design Supremo−Opt for video applications, which maximizes SR’s impact while satisfying latency and resource constraints under practical network conditions.Supremo upscales 360p to 1080p in 122 ms, 43.68× faster than on-device GPU execution.
Compared to cloud offloading-based solutions, Supremo reduces wireless network bandwidth consumption and end-to-end latency by 15.23× and 4.85×, respectively, and achieves 2.39 dB higher PSNR than conventional JPEG to compress data. Supremo−Opt also ensures practical performance.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
