DSPU: A 281.6mW Real-Time Depth Signal Processing Unit for Deep Learning-Based Dense RGB-D Data Acquisition with Depth Fusion and 3D Bounding Box Extraction in Mobile Platforms

📋 论文概要

该论文提出了一款名为DSPU的深度信号处理单元，在281.6mW功耗下实现实时密集RGB-D数据采集与深度学习处理，解决了传统ToF传感器功耗高且在极端反射率区域深度提取失败的问题。

💡 主要创新点

• 提出低功耗实时深度信号处理单元，支持深度学习驱动的密集RGB-D数据采集，功耗仅281.6mW。
• 针对高反射率等极端场景优化深度提取，避免导航或AR交互失败。

🏷 关键词

📄 原文摘要

RGBD data and 3D bounding-box (BB) information for accurate navigation and seamless interaction with the surrounding environment. Specifically, the extraction of RGB-D data and 3D BB needs to be done in real-time (> 30fps) while consuming low power (< 1W) due to limited battery capacity. In addition, a conventional depth processing system consumes high power due to a high performance (HP) time-of-flight (ToF) sensor with an illuminator (> 3W) [1]. However, even the HP ToF fails to extract depth in areas of extreme reflectance, leading to failure in navigation or AR interaction. In addition, software implementation on an application processor suffers from high latency (~0.1s) to preprocess the depth data and process the 3D point cloud-based neural network (PNN)

👥 作者与机构

Dongseok Im, Gwangtae Park, Zhiyong Li, Junha Ryu, Sanghoon Kang,

Donghyeon Han, Jinsu Lee, Hoi-Jun Yoo KAIST, Daejeon, Korea Emerging mobile platforms, such as autonomous robots and AR devices, require