Designing efficient hardware accelerators for imaging, vision and machine learning

Priyanka Raina

(Stanford University)

Please LOG IN to view the video.

Date: November 30, 2018


85% of images today are taken by cell phones. These images are not merely projections of light from the scene onto the camera sensor but result from a deep calculation. This calculation involves a number of computational imaging algorithms such as high dynamic range (HDR) imaging, panorama stitching, image deblurring and low-light imaging that compensate for camera limitations, and a number of deep learning based vision algorithms such as face recognition, object recognition and scene understanding that make inference on these images for a variety of emerging applications. However, because of their high computational complexity, mobile CPU or GPU based implementations of these algorithms do not achieve real-time performance. Moreover, offloading these algorithms to the cloud is not a viable solution because wirelessly transmitting large amounts of image data results in long latency and high energy consumption, making them unsuitable for mobile devices. [..]

Further Information:

Created: Friday, November 30th, 2018