期刊
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY
卷 94, 期 10, 页码 1083-1099出版社
SPRINGER
DOI: 10.1007/s11265-022-01766-3
关键词
Compressive sensing; Depth reconstruction; Mixed precision; Alternating direction method of multipliers; Proximal gradient descent; Field-programmable gate array
资金
- Engineering and Physical Sciences Research Council of the UK (EPSRC) [EP/S000631/1]
- UK MOD University Defence Research Collaboration (UDRC) in Signal Processing
This paper presents a mixed precision framework for compressive depth reconstruction, which achieves better results in reducing resource consumption and improving system efficiency by varying precision scaling.
Rapid reconstruction of depth images from sparsely sampled data is important for many applications in machine perception, including robot or vehicle assistance or autonomy. Approximate computing techniques have been widely adopted to reduce resource consumption and increase efficiency in energy and resource constrained systems, especially targeted at FPGA and solid state implementation. Whereas previous work has focused on approximate, but static, representation of data in LiDAR systems, in this paper we show how the flexibility of an arbitrary precision accelerator with fine-grain tuning allows a better trade-off between algorithmic performance and implementation efficiency. A mixed precision framework of l(1) solvers is presented, with compact ADMM and PGD, for the lasso problem, enabling compressive depth reconstruction by varying the precision scaling in single bit granularity during the iterative optimization process. Implementing mixed precision l(1) solvers on an FPGA with a pipelined architecture for depth image reconstruction across various sensing scenarios, over 74% savings in hardware resources and 60% in power are achieved with only minor reductions in reconstructed depth image quality when compared to single float precision, while over 10% saving in hardware resources and power is achieved compared to relative consistently reduced precision solutions.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据