Professor Bahram Jalali along with the Ph.D. students Yiming Zhou and Callen MacPhee delivered a successful academic lecture on PhyCV at Qualcomm entitled “Low-complexity image processing algorithm for Autonomous Driving using Physics-AI Symbiosis”
Abstract:
Low-dimensional computational imaging tools with surprisingly high performance can be created by coding physical phenomena as algorithms. This qualitatively new approach to computational imaging treats images as complex particles propagating through a virtual medium. In contrast to existing algorithms that are based on pixel intensity, PhyCV operates on the spectral and spatial phases. Emulating physical processes of diffraction and coherent detection, the algorithms have the potential to be implemented in analog hardware for accelerated computing.
Explore more about PhyCV at: https://github.com/JalaliLabUCLA/phycv
