Enhancing Embedded Object Tracking: A Hardware Acceleration Approach for Real-Time Predictability

被引:0
|
作者
Zhang, Mingyang [1 ]
Van Beeck, Kristof [1 ]
Goedeme, Toon [1 ]
机构
[1] Katholieke Univ Leuven, Dept Elect Engn, PSI EAVISE Res Grp, B-2860 St Katelijne Waver, Belgium
关键词
deep learning; object tracking; siamese network; FPGA; real-time system predictability; hardware acceleration; high-level synthesis; embedded system; MEAN-SHIFT; NETWORKS;
D O I
10.3390/jimaging10030070
中图分类号
TB8 [摄影技术];
学科分类号
0804 ;
摘要
While Siamese object tracking has witnessed significant advancements, its hard real-time behaviour on embedded devices remains inadequately addressed. In many application cases, an embedded implementation should not only have a minimal execution latency, but this latency should ideally also have zero variance, i.e., be predictable. This study aims to address this issue by meticulously analysing real-time predictability across different components of a deep-learning-based video object tracking system. Our detailed experiments not only indicate the superiority of Field-Programmable Gate Array (FPGA) implementations in terms of hard real-time behaviour but also unveil important time predictability bottlenecks. We introduce dedicated hardware accelerators for key processes, focusing on depth-wise cross-correlation and padding operations, utilizing high-level synthesis (HLS). Implemented on a KV260 board, our enhanced tracker exhibits not only a speed up, with a factor of 6.6, in mean execution time but also significant improvements in hard real-time predictability by yielding 11 times less latency variation as compared to our baseline. A subsequent analysis of power consumption reveals our approach's contribution to enhanced power efficiency. These advancements underscore the crucial role of hardware acceleration in realizing time-predictable object tracking on embedded systems, setting new standards for future hardware-software co-design endeavours in this domain.
引用
收藏
页数:17
相关论文
共 50 条
  • [31] A dedicated hardware accelerator for real-time acceleration of YOLOv2
    Ke Xu
    Xiaoyun Wang
    Xinyang Liu
    Changfeng Cao
    Huolin Li
    Haiyong Peng
    Dong Wang
    Journal of Real-Time Image Processing, 2021, 18 : 481 - 492
  • [32] Hardware Acceleration for Real-Time Wildfire Detection Onboard Drone Networks
    Briley, Austin Alexander
    Afghah, Fatemeh
    IEEE INFOCOM 2024-IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS, INFOCOM WKSHPS 2024, 2024,
  • [33] A dedicated hardware accelerator for real-time acceleration of YOLOv2
    Xu, Ke
    Wang, Xiaoyun
    Liu, Xinyang
    Cao, Changfeng
    Li, Huolin
    Peng, Haiyong
    Wang, Dong
    JOURNAL OF REAL-TIME IMAGE PROCESSING, 2021, 18 (03) : 481 - 492
  • [34] Toward real-time object detection on heterogeneous embedded systems
    Niazi-Razavi, Milad
    Savadi, Abdorreza
    Noori, Hamid
    2019 9TH INTERNATIONAL CONFERENCE ON COMPUTER AND KNOWLEDGE ENGINEERING (ICCKE 2019), 2019, : 450 - 454
  • [35] Real-time object tracking based on scale-invariant features employing bio-inspired hardware
    Yasukawa, Shinsuke
    Okuno, Hirotsugu
    Ishii, Kazuo
    Yagi, Tetsuya
    NEURAL NETWORKS, 2016, 81 : 29 - 38
  • [36] Real-time Object Detection and Tracking in Mixed Reality using Microsoft HoloLens
    Farasin, Alessandro
    Peciarolo, Francesco
    Grangetto, Marco
    Gianaria, Elena
    Garza, Paolo
    VISAPP: PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 4: VISAPP, 2020, : 165 - 172
  • [37] An Improved Real-Time Object Tracking Algorithm Based on Deep Learning Features
    Wang, Xianyu
    LI, Cong
    LI, Heyi
    Zhang, Rui
    Liang, Zhifeng
    Wang, Hai
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2023, E106D (05) : 786 - 793
  • [38] Real-Time Tracking of Fast Moving Weak Object Based on Siamese Network
    Zheng Junsong
    Guo Hao
    Li Abiao
    An Jubai
    LASER & OPTOELECTRONICS PROGRESS, 2022, 59 (04)
  • [39] SiamCAM: A Real-Time Siamese Network for Object Tracking with Compensating Attention Mechanism
    Huang, Kai
    Qin, Peixuan
    Tu, Xuji
    Leng, Lu
    Chu, Jun
    APPLIED SCIENCES-BASEL, 2022, 12 (08):
  • [40] Real-Time Clustering of Datasets with Hardware Embedded Neuromorphic Neural Networks
    Bako, Laszlo
    2009 INTERNATIONAL WORKSHOP ON HIGH PERFORMANCE COMPUTATIONAL SYSTEMS BIOLOGY, PROCEEDINGS, 2009, : 13 - 22