All projects
Project notes
P-CLAHE
A real-time CUDA implementation of CLAHE for underwater robotic vision, built to run image preprocessing on constrained GPU resources.
- Signal
- GPU image processing · underwater robotics
- Focus
- CUDA · C++ · Python
- Built a real-time CUDA implementation of CLAHE (P-CLAHE) to enhance underwater robotic vision, enabling autonomous submarine systems to run image preprocessing on limited GPU resources.
- Improved performance by applying shared memory caching, loop unrolling, and warp-optimized parallelization, cutting execution time and reducing memory overhead at scale.
- Delivered a 3–5x speedup over CPU and unoptimized implementations, validating scalability across diverse image sizes and demonstrating reliability for deployment in constrained embedded environments.