CVIVSPJul 17, 2019

Real-Time Highly Accurate Dense Depth on a Power Budget using an FPGA-CPU Hybrid SoC

arXiv:1907.07745v14 citations
Originality Highly original
AI Analysis

This addresses the problem of high-quality depth sensing for embedded systems in robotics and computer vision, offering a significant improvement over existing methods.

The paper tackled real-time dense depth estimation from stereo images under power constraints by proposing a novel FPGA-CPU hybrid approach, achieving an 8.7% error rate on KITTI 2015 at over 50 FPS with 5W power consumption.

Obtaining highly accurate depth from stereo images in real time has many applications across computer vision and robotics, but in some contexts, upper bounds on power consumption constrain the feasible hardware to embedded platforms such as FPGAs. Whilst various stereo algorithms have been deployed on these platforms, usually cut down to better match the embedded architecture, certain key parts of the more advanced algorithms, e.g. those that rely on unpredictable access to memory or are highly iterative in nature, are difficult to deploy efficiently on FPGAs, and thus the depth quality that can be achieved is limited. In this paper, we leverage a FPGA-CPU chip to propose a novel, sophisticated, stereo approach that combines the best features of SGM and ELAS-based methods to compute highly accurate dense depth in real time. Our approach achieves an 8.7% error rate on the challenging KITTI 2015 dataset at over 50 FPS, with a power consumption of only 5W.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes