Abstract
Contour tracing is a critical technique in image analysis and computer vision, with applications in medical imaging, big data analytics, machine learning, and robotics. We introduce a novel hardware accelerator based on the Adapted and Segmented (AnS) Vertex Following and Run-Data-Based-Following families of fast contour tracing algorithms implemented on the Zynq-7000 FPGA platform. Our algorithmic implementation utilizing a mesh-interconnected multiprocessor architecture is at least 55 times faster than the existing implementations. With input-output overheads, it is up to 12.5 times faster. Our hardware accelerator for contour tracing is benchmarked on mesh-interconnected hardware, all three families of contour tracing algorithms, and a random image from the Imagenet database. Our implementation is, thus, faster for FPGA, ASIC, GPU, and supercomputer hardware in comparison to the CPU-GPU collaborative approach and offers a better solution for those systems where the input-output overheads can be minimized, like parallel processing arrays and mesh-connected sensor networks.
Shubh Goel
Computer Science
My research interests include Embodied AI, Computer Vision and Deep Learning.