An Efficient Real-Time Object Detection Framework on Resource-Constricted Hardware Devices via Software and Hardware Co-design (Invited Paper)

被引:6
|
作者
Liu, Mingshuo [1 ]
Luo, Shiyi [1 ]
Han, Kevin [1 ]
Yuan, Bo [2 ]
DeMara, Ronald F. [3 ]
Bai, Yu [1 ]
机构
[1] Calif State Univ Fullerton, Fullerton, CA 92634 USA
[2] Rutgers State Univ, New Brunswick, NJ USA
[3] Univ Cent Florida, Orlando, FL 32816 USA
来源
2021 IEEE 32ND INTERNATIONAL CONFERENCE ON APPLICATION-SPECIFIC SYSTEMS, ARCHITECTURES AND PROCESSORS (ASAP 2021) | 2021年
基金
美国国家科学基金会;
关键词
Deep learning; FPGA; Tensor Train; Energy Efficiency; RECURRENT NEURAL-NETWORKS;
D O I
10.1109/ASAP52443.2021.00020
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
The fast development of object detection techniques has attracted attention to developing efficient Deep Neural Networks (DNNs). However, the current state-of-the-art DNN models can not provide a balanced solution among accuracy, speed, and model size. This paper proposes an efficient real-time object detection framework on resource-constricted hardware devices through hardware and software co-design. The Tensor Train (TT) decomposition is proposed for compressing the YOLOv5 model. By unitizing the unique characteristics given by the TT decomposition, we develop an efficient hardware accelerator based on FPGA devices. Experimental results show that the proposed method can significantly reduce the model size and improve the execution time.
引用
收藏
页码:77 / 84
页数:8
相关论文
共 50 条
  • [41] A Resource Efficient Software-Hardware Co-Design of Lattice-Based Homomorphic Encryption Scheme on the FPGA
    Paul, Bikram
    Yadav, Tarun Kumar
    Singh, Balbir
    Krishnaswamy, Srinivasan
    Trivedi, Gaurav
    IEEE TRANSACTIONS ON COMPUTERS, 2023, 72 (05) : 1247 - 1260
  • [42] High Throughput FPGA-Based Object Detection via Algorithm-Hardware Co-Design
    Anupreetham, Anupreetham
    Ibrahim, Mohamed
    Hall, Mathew
    Boutros, Andrew
    Kuzhively, Ajay
    Mohanty, Abinash
    Nurvitadhi, Eriko
    Betz, Vaughn
    Cao, Yu
    Seo, Jae-Sun
    ACM TRANSACTIONS ON RECONFIGURABLE TECHNOLOGY AND SYSTEMS, 2024, 17 (01)
  • [43] Towards a Scalable Hardware/Software Co-Design Platform for Real-time Pedestrian Tracking Based on a ZYNQ-7000 Device
    Yu, Zheqi
    Yang, Shufan
    Sillitoe, Ian
    Buckley, Kevan
    2017 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS-ASIA (ICCE-ASIA), 2017, : 127 - 132
  • [44] Algorithm-Hardware Co-Design of Real-Time Edge Detection for Deep-Space Autonomous Optical Navigation
    Xiao, Hao
    Fan, Yanming
    Ge, Fen
    Zhang, Zhang
    Cheng, Xin
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2020, E103D (10) : 2047 - 2058
  • [45] A real-time life-care monitoring framework: Warn Red hardware and software design
    Cetin, Gamze Dogali
    Cetin, Ozdemir
    Bayilmis, Cuneyt
    TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2015, 23 (04) : 1040 - 1050
  • [46] CPU model-based hardware/software co-design, co-simulation and analysis technology for real-time embedded control systems
    Ishikawa, Makoto
    McCune, D. J.
    Saikalis, George
    Oho, Shigeru
    RTAS 2007: 13th Real-Time and Embedded Technology and Applications Symposium, Proceedings, 2007, : 3 - 11
  • [47] Hardware and Software Co-Design of a System-On-Chip for Real-Time Bidirectional Transfer and Processing of Data from a Time-to-Digital Converter
    Lusardi, N.
    Garzetti, F.
    Cibin, M. A.
    Sury, R.
    Geraci, A.
    2017 IEEE NUCLEAR SCIENCE SYMPOSIUM AND MEDICAL IMAGING CONFERENCE (NSS/MIC), 2017,
  • [48] FPGA-based hardware/firmware co-design for real-time radiometric correction onboard microsatellite
    Ghelamallah, Youcef
    Rachedi, Azzeddine
    JOURNAL OF REAL-TIME IMAGE PROCESSING, 2024, 21 (05)
  • [49] Spectral Coexistence of LDACS and DME: Analysis via Hardware Software Co-Design in Presence of Real Channels and RF Impairments
    Agrawal, Niharika
    Darak, Sumit J.
    Bader, Faouzi
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2020, 69 (09) : 9837 - 9848
  • [50] Software-Hardware Co-Design for Energy-Efficient Continuous Health Monitoring via Task-Aware Compression
    Wu, Di
    Zhao, Shiqi
    Yang, Jie
    Sawan, Mohamad
    IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS, 2023, 17 (02) : 180 - 191