Detection of Fiducial Marker With Neural Network Compression

被引:0
作者
Park T. [1 ]
Shin H. [1 ]
Oh H. [1 ]
机构
[1] Department of Mechanical Engineering, Ulsan National Institute of Science and Technology
基金
新加坡国家研究基金会;
关键词
computer vision; deep learning; fiducial marker; neural network compression; neural network quantization; pose estimation;
D O I
10.5302/J.ICROS.2023.23.0054
中图分类号
学科分类号
摘要
Fiducial markers are used to localize camera positions and are widely employed in various fields where fast and highly accurate positioning is required, including AR (Augmented Reality), VR (Virtual Reality), PCB (Printed Circuit Board) design factories, and robot localization research. Over the past 20 years, many fiducial marker designs and detection algorithms have been proposed to improve detection rates, broaden the same marker family, or save computational resources. However, most of these algorithms work well in constrained environments, such as well-lit conditions, minimal motion blur, or no shadows. These limitations can be addressed by using learning-based methods, but they often suffer from high computational loads or the need for collecting training datasets. To overcome these limitations, we introduce a novel fiducial marker detection algorithm along with a neural network compression. By using a feature detection network with a simple circular-shape based fiducial marker, training datasets can be fully synthesized considering real-world noise without the effort of collecting and labeling datasets. Since many fiducial marker applications run on computationally constrained embedded systems, TD (Tensor Decomposition) and QAT (Quantization Aware Training) are applied to the neural network to reduce the number of parameters and improve the inference speed of the network. We demonstrate that our neural network compression approach preserves overall performance while reducing network parameters by 55.48% and accelerating inference speed by 569% on an NVIDIA Jetson Xavier NX. Furthermore, we validate our methods by testing them on real-world images taken by a flying drone. © ICROS 2023.
引用
收藏
页码:628 / 635
页数:7
相关论文
共 50 条
[41]   Neural Network Compression Based on Tensor Ring Decomposition [J].
Xie, Kun ;
Liu, Can ;
Wang, Xin ;
Li, Xiaocan ;
Xie, Gaogang ;
Wen, Jigang ;
Li, Kenli .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 36 (03) :1-15
[42]   LTNN: A Layerwise Tensorized Compression of Multilayer Neural Network [J].
Huang, Hantao ;
Yu, Hao .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2019, 30 (05) :1497-1511
[43]   Recurrent Neural Network-Based Video Compression [J].
Montajabi, Zahra ;
Ghassab, Vahid Khorasani ;
Bouguila, Nizar .
2022 21ST IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, ICMLA, 2022, :925-930
[44]   Efficient Tunstall Decoder for Deep Neural Network Compression [J].
Chen, Chunyun ;
Wang, Zhe ;
Chen, Xiaowei ;
Lin, Jie ;
Aly, Mohamed M. Sabry .
2021 58TH ACM/IEEE DESIGN AUTOMATION CONFERENCE (DAC), 2021, :1021-1026
[45]   Profiling the real world potential of neural network compression [J].
Lorentz, Joe ;
Moawad, Assaad ;
Hartmann, Thomas ;
Aouada, Djamila .
2022 IEEE INTERNATIONAL CONFERENCE ON OMNI-LAYER INTELLIGENT SYSTEMS (IEEE COINS 2022), 2022, :134-139
[46]   ENCODER OPTIMIZATIONS FOR THE NNR STANDARD ON NEURAL NETWORK COMPRESSION [J].
Haase, Paul ;
Becking, Daniel ;
Kirchhoffer, Heiner ;
Mueller, Karsten ;
Schwarz, Heiko ;
Samek, Wojciech ;
Marpe, Detlev ;
Wiegand, Thomas .
2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, :3522-3526
[47]   Towards neural network approaches for point cloud compression [J].
Alexiou, Evangelos ;
Tung, Kuan ;
Ebrahimi, Touradj .
APPLICATIONS OF DIGITAL IMAGE PROCESSING XLIII, 2020, 11510
[48]   Safety and efficacy of fiducial marker implantation for robotic stereotactic body radiation therapy with fiducial tracking [J].
Nathaniel Scher ;
Marc Bollet ;
Gauthier Bouilhol ;
Remi Tannouri ;
Imane Khemiri ;
Aurelie Vouillaume ;
Noura Sellami ;
Rie Von Eyben ;
Jean-Michel Vannetzel ;
Ilan Darmon ;
Luc Rotenberg ;
Hanah Lamallem ;
Olivier Bauduceau ;
Denis Foster ;
Alain Toledano .
Radiation Oncology, 14
[49]   A generative adversarial network-based (GAN-based) architecture for automatic fiducial marker detection in prostate MRI-only radiotherapy simulation images [J].
Singhrao, Kamal ;
Fu, Jie ;
Parikh, Neil R. ;
Mikaeilian, Argin G. ;
Ruan, Dan ;
Kishan, Amar U. ;
Lewis, John H. .
MEDICAL PHYSICS, 2020, 47 (12) :6405-6413
[50]   Fiducial Marker Placement Via Convex Probe EBUS [J].
Argento, A. Christine ;
Decker, Roy ;
Puchalski, Jonathan .
JOURNAL OF BRONCHOLOGY & INTERVENTIONAL PULMONOLOGY, 2016, 23 (02) :181-185