Moby: Empowering 2D Models for Efficient Point Cloud Analytics on the Edge

TL;DR

Moby is a system that enables efficient 3D object detection on edge devices by leveraging fast 2D detection and selective cloud offloading, significantly reducing latency with minimal accuracy loss.

Contribution

The paper introduces Moby, a novel system that transforms 2D detection results into 3D bounding boxes and employs a frame offloading scheduler to optimize edge-cloud collaboration.

Findings

Achieves up to 91.9% latency reduction on NVIDIA Jetson TX2.

Maintains competitive accuracy with state-of-the-art methods.

Demonstrates effectiveness on real-world autonomous driving datasets.

Abstract

3D object detection plays a pivotal role in many applications, most notably autonomous driving and robotics. These applications are commonly deployed on edge devices to promptly interact with the environment, and often require near real-time response. With limited computation power, it is challenging to execute 3D detection on the edge using highly complex neural networks. Common approaches such as offloading to the cloud induce significant latency overheads due to the large amount of point cloud data during transmission. To resolve the tension between wimpy edge devices and compute-intensive inference workloads, we explore the possibility of empowering fast 2D detection to extrapolate 3D bounding boxes. To this end, we present Moby, a novel system that demonstrates the feasibility and potential of our approach. We design a transformation pipeline for Moby that generates 3D bounding boxes efficiently and accurately based on 2D detection results without running 3D detectors. Further, we devise a frame offloading scheduler that decides when to launch the 3D detector judiciously in the cloud to avoid the errors from accumulating. Extensive evaluations on NVIDIA Jetson TX2 with real-world autonomous driving datasets demonstrate that Moby offers up to 91.9% latency improvement with modest accuracy loss over state of the art.