Panopticus: Omnidirectional 3D Object Detection on Resource-constrained Edge Devices

TL;DR

Panopticus is a system that enables accurate 3D object detection using omnidirectional cameras on resource-limited edge devices by dynamically adjusting model architecture to meet latency constraints.

Contribution

It introduces an adaptive multi-branch detection scheme and dynamic model adjustment for efficient omnidirectional 3D detection on edge devices.

Findings

Improves detection accuracy by 62% under latency constraints.

Reduces latency by 2.1 times compared to baseline methods.

Successfully deployed on three edge devices with real-world datasets.

Abstract

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{\deg} 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.