ETRI-Knowledge Sharing Plaform



논문 검색
구분 SCI
연도 ~ 키워드


학술대회 A Method for Optimizing Deep Learning Object Detection in Edge Computing
Cited 4 time in scopus Download 1 time Share share facebook twitter linkedin kakaostory
김량수, 김근용, 김희도, 윤기하, 유학
International Conference on Information and Communication Technology Convergence (ICTC) 2020, pp.1164-1167
20HK1200, 다중의 IoT 서비스를 위한 모듈 구조의 엣지 컴퓨팅 게이트웨이 플랫폼 기술 개발, 유학
Recently, edge computing has received considerable attention as a promising solution to provide deep learning-based video analysis services in real-time. However, due to the limited computation capability of the data processing units (such as CPUs, GPUs, and specialized accelerators) embedded in the edge devices, the question of how to use the limited resources of the edge devices is one of the most pressing issues affecting deep learning-based video analysis service efficiency. In this paper, we introduce a practical approach to optimize deep learning object detection at the edge devices embedding CPUs and GPUs. The proposed approach adopts TVM, an automated end-to-end deep learning compiler that automatically optimizes deep learning workloads with respect to hardware-specific characteristics. In addition, task-level pipeline parallelism is applied to maximize resource utilization of the CPUs and GPUs so as to improve overall object detection performance. Through experiment results, we show that the proposed approach achieves performance improvement for detecting objects on multiple video streams in terms of frame per second.
deep learning, deep learning compiler, Edge computing, object detection, pipeline parallelism
KSP 제안 키워드
Analysis services, Data processing, Edge devices, End to End(E2E), Experiment results, Learning-based, Limited resources, Object detection, Practical approach, Real-Time, deep learning(DL)