在边缘设备上实现低延迟高精度全景3D目标检测
Panopticus: Omnidirectional 3D Object Detection on Resource-constrained Edge Devices
- 动态自适应多分支结构，根据资源与空间复杂度调整模型
- 33毫秒内平均提升62%检测准确率，延迟降低2.1倍
- 适合移动机器人等资源受限的实时安全场景
基于全景视角的3D目标检测支持移动机器人导航等关键应用。此类应用日益部署在资源受限的边缘设备上，避免隐私泄露与网络延迟。摄像头作为低成本替代激光雷达的方案被广泛采用，但基于摄像头的高性能系统计算负载大，难以满足边缘设备算力限制。本文提出Panopticus，一种专为边缘设备设计的全景相机3D检测系统。该系统采用自适应多分支检测机制，考虑空间复杂性；通过动态调整模型架构与操作，在延迟约束下优化精度。我们在三类边缘设备上实现并测试，使用公开自动驾驶数据集及自建移动360°相机数据集。实验表明，在严格33毫秒延迟要求下，平均准确率提升62%，相比基线平均延迟降低2.1倍。
原文摘要 · Abstract (English)
3D object detection with omnidirectional views enables safety-critical applications such as mobile robot navigation. Such applications increasingly operate on resource-constrained edge devices, facilitating reliable processing without privacy concerns or network delays. To enable cost-effective deployment, cameras have been widely adopted as a low-cost alternative to LiDAR sensors. However, the compute-intensive workload to achieve high performance of camera-based solutions remains challenging due to the computational limitations of edge devices. In this paper, we present Panopticus, a carefully designed system for omnidirectional and camera-based 3D detection on edge devices. Panopticus employs an adaptive multi-branch detection scheme that accounts for spatial complexities. To optimize the accuracy within latency limits, Panopticus dynamically adjusts the model's architecture and operations based on available edge resources and spatial characteristics. We implemented Panopticus on three edge devices and conducted experiments across real-world environments based on the public self-driving dataset and our mobile 360° camera dataset. Experiment results showed that Panopticus improves accuracy by 62% on average given the strict latency objective of 33ms. Also, Panopticus achieves a 2.1{\times} latency reduction on average compared to baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。