no code implementations • 8 Dec 2022 • Sibendu Paul, Kunal Rao, Giuseppe Coviello, Murugan Sankaradas, Oliver Po, Y. Charlie Hu, Srimat T. Chakradhar
Elixir correctly detects 7. 1% (22, 068) and 5. 0% (15, 731) more cars, 94% (551) and 72% (478) more faces, and 670. 4% (4975) and 158. 6% (3507) more persons than the default-setting and time-sharing approaches, respectively.
no code implementations • 15 Nov 2022 • Sibendu Paul, Kunal Rao, Giuseppe Coviello, Murugan Sankaradas, Oliver Po, Y. Charlie Hu, Srimat Chakradhar
This is because the camera parameter settings, though optimal at deployment time, are not the best settings for good-quality video capture as the environmental conditions and scenes around a camera change during operation.
no code implementations • 23 Aug 2022 • Sibendu Paul, Kunal Rao, Giuseppe Coviello, Murugan Sankaradas, Oliver Po, Y. Charlie Hu, Srimat Chakradhar
It is a common practice to think of a video as a sequence of images (frames), and re-use deep neural network models that are trained only on images for similar analytics tasks on videos.
no code implementations • 8 Jul 2021 • Sibendu Paul, Kunal Rao, Giuseppe Coviello, Murugan Sankaradas, Oliver Po, Y. Charlie Hu, Srimat T. Chakradhar
We then present CamTuner, to our knowledge, the first framework that dynamically adapts NAUTO camera parameters to optimize the accuracy of AUs in a VAP in response to adverse changes in environmental conditions.
no code implementations • 24 Jan 2021 • Sibendu Paul, Utsav Drolia, Y. Charlie Hu, Srimat T. Chakradhar
Millions of cameras at edge are being deployed to power a variety of different deep learning applications.