Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
Real-time disparity estimation requires real-time rectification which involves solving the models of lens distortions, image translations and rotations. Low complexity look-up-table based rectification algorithms usually require an external memory to store large look-up-tables. In this chapter, we present an implementation of the look-up-table based approach which compresses the rectification information to fit the look-up-table into the on-chip memory of a Virtex-5 FPGA. First, a very low complexity compressed look-up-table based rectification algorithm (CLUTR) and its real-time hardware are presented. The implemented CLUTR hardware rectifies stereo images with moderate lens distortion and camera misalignment. Moreover, an enhanced version of the compressed look-up-table based rectification algorithm (E-CLUTR) and its novel real-time hardware are presented. E-CLUTR solves more extreme camera alignment and distortion issues than CLUTR while maintaining the low complexity architecture.
Anastasia Ailamaki, Viktor Sanca, Hamish Mcniece Hill Nicholson, Andreea Nica, Syed Mohammad Aunn Raza