arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.07503cs.CVcs.AIcs.LG
收藏

BED:一种用于边缘设备的实时的目标检测系统

BED: A Real-Time Object Detection System for Edge Devices

Rice University(莱斯大学);Analog Devices(亚德诺半导体);Meta Platforms, Inc(元平台公司)

Guanchu Wang, Zaid Pervaiz Bhat, Zhimeng Jiang, Yi-Wei Chen, Daochen Zha, Alfredo Costilla Reyes, Afshin Niktash, Gorkem Ulkar, Erman Okman, Xuanting Cai, Xia Hu

摘要:

在边缘设备上部署深度神经网络~(DNN)为现实世界的任务提供了高效的解决方案。边缘设备已被用于在不同的域中有效地收集大量数据。DNN已经成为数据处理和分析的有效工具。然而,由于有限的计算资源和内存,在边缘设备上设计DNN具有挑战性。为了应对这一挑战,我们在MAX 78000 DNN加速器上演示了边缘设备的目标检测系统~(BED)。它将设备上的DNN推理与摄像头和LCD显示器集成在一起,分别用于图像采集和检测显示。BED是一个简洁、有效、详细的解决方案,包括模型训练、量化、合成和部署。整个存储库在Github上开源,包括用于片上调试的图形用户界面~(GUI)。实验结果表明,BED可以产生准确的检测与300 KB的微小DNN模型,这只需要91.9 ms的推理时间和1.845 mJ的能量。实时的【形】检测可在YouTube上获得。

英文摘要:

Deploying deep neural networks~(DNNs) on edge devices provides efficient and effective solutions for the real-world tasks. Edge devices have been used for collecting a large volume of data efficiently in different domains. DNNs have been an effective tool for data processing and analysis. However, designing DNNs on edge devices is challenging due to the limited computational resources and memory. To tackle this challenge, we demonstrate Object Detection System for Edge Devices~(BED) on the MAX78000 DNN accelerator. It integrates on-device DNN inference with a camera and an LCD display for image acquisition and detection exhibition, respectively. BED is a concise, effective and detailed solution, including model training, quantization, synthesis and deployment. The entire repository is open-sourced on Github, including a Graphical User Interface~(GUI) for on-chip debugging. Experiment results indicate that BED can produce accurate detection with a 300-KB tiny DNN model, which takes only 91.9 ms of inference time and 1.845 mJ of energy. The real-time detection is available at YouTube.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑