发表机构
Munich Center for Machine Learning; Technical University of Munich（慕尼黑机器学习中心; 慕尼黑工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出HexVIO系统，利用商用Hexagon DSP卸载立体惯性里程计的视觉前端，在保持后端于CPU的同时，显著降低功耗和延迟，实现全天候跟踪。
AI 中文摘要
设备在周围环境中定位自身的能力是空间计算的基本前提。视觉惯性里程计（VIO）已被证明是完成此任务的一种经济高效且准确的解决方案。机器人、可穿戴设备、XR设备和无人机可以从VIO的高效实现中显著受益，因为这使得设备更凉爽、更轻便、更便宜，并具有更长的电池续航和更好的用户体验。在这项工作中，我们提出通过利用Hexagon DSP（一种存在于许多现代智能手机和XR设备中的商用协处理器）来提高VIO系统的效率。我们的方法将立体惯性里程计系统的视觉前端卸载到DSP上，同时将后端保留在主CPU上。通过针对DSP架构优化实现，与仅CPU执行相比，我们实现了功耗和延迟的显著降低。我们的系统HexVIO在商用智能手机上展示了功耗降低67%或吞吐量增加86%的性能，并能够以0.83W的功耗维持长期实时30fps跟踪，相当于在测试设备上约18小时的跟踪时间。这些结果凸显了商用DSP在机器人和移动设备中实现全天候视觉惯性跟踪的潜力。
英文摘要
The ability of a device to localize itself within its surroundings is a fundamental prerequisite for spatial computing. Visual-inertial odometry (VIO) has proven to be a cost-effective and accurate solution for this task. Robots, wearables, XR devices, and drones can benefit significantly from efficient implementations of VIO since they allow for cooler, lighter, and cheaper devices with longer battery life and a better user experience. In this work, we propose to enhance the efficiency of a VIO system by leveraging the Hexagon DSP, a commodity co-processor present in many modern smartphones and XR devices. Our approach offloads the visual frontend of a stereo-inertial odometry system to the DSP while keeping the backend on the main CPU. By optimizing the implementation for the DSP architecture, we achieve significant reductions in power consumption and latency compared to CPU-only execution. Our system, HexVIO, demonstrates a 67% reduction in power consumption or an 86% increase in throughput on a commodity smartphone, with the ability to sustain long-term real-time 30 fps tracking for 0.83 W, corresponding to ~18 hours of tracking on the testing device. These results highlight the potential of commodity DSPs for enabling all-day visual-inertial tracking in robotics and mobile devices.
