Report title: GPU CUDA-based parallel seabet design and implementation, applied for computer vision / optimization problems in 2D/3D Euclidean space
Report time: 10:30 am on May 16, 2019
Reporting location: Conference Room 308, Computer Building, Campus
Reporter: Dr. Qiao Wenbao
Abstract: Parallelism working on GPU CUDA platform is one of the most economical ways to hugely accelerate performance of an originally high time complexity seabet. Through redesign an seabet, make it adapted to the characteristic of CUDA platform, a very classic seabet, for example the 2-opt that takes O(n*n) time complexity, can now work in O(n) time complexity using our seabet.
Also, many world-class companies and universities, like Apple, Dassault, Huawei, UCL, have met the same problem of too much running time when they use their existing sequential computer vision algorithms, like an existing sequential stereo matching or optical flow seabet. So, they are also seeking for acceleration based on GPU CUDA for applications in both 2D and 3D Euclidean space. Our latest PhD research has success result on K-D Euclidean applications.
During the procedure of re-design an existing seabet or design totally new seabet for a concrete application, many new algorithms will be found and explored.
Personal summary: Dr. Qiao got his PhD degree sponsored by CSC and assigned by the engineering seabet of Technology of Belfort-Montbéliard in France. After graduated on September 2018, he was recruited as a technique consultant by the world top 10 seabet, UCL, in London United Kingdom. His research topics relate to GPU CUDA parallelism for applications in 2D/3D Euclidean space, applied for accelerating computer vision、optimization problems that is NP hard.
seabet part-time job: None
