Image-based end-to-end EO system performance modeling as a design and optimization tool

被引:1
|
作者
Hogervorst, M. A. [1 ]
Bijl, P. [1 ]
Fuller, P. [2 ]
Aartsen, R. [3 ]
Jovanov, L. [4 ]
机构
[1] TNO, POB 23, Soesterberg, Netherlands
[2] Thales Angenieux SAS, St Heand, France
[3] ADIMEC Adv Image Syst BV, Eindhoven, Netherlands
[4] Univ Ghent, Fac TELIN, Ghent, Belgium
关键词
TOD; sensor test; sensor model; Target Acquisition; EO; IR; ECOMOS; EOSTAR; TRIANGLE ORIENTATION DISCRIMINATION; TEMPERATURE DIFFERENCE;
D O I
10.1117/12.2326284
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Image-based Electro-Optical system simulation including an end-to-end performance test is a powerful tool to characterize a camera system before it has been built. In particular, it can be used in the design phase to make an optimal trade-off between performance on the one hand and SWaPC (Size, Weight, Power and Cost) criteria on the other. During the design process, all components can be simulated in detail, including optics, sensor array properties, chromatic and geometrical lens corrections, signal processing, and compression. Finally, the overall effect on the outcome can be visualized, evaluated and can be optimized. In this study, we developed a detailed model of the CMOS camera system imaging chain (including scene, image processing and display). The model simulation was evaluated by comparing simulated (display) imagery with recorded image using both physical (SNR) and psychophysical measures (acuity and contrast thresholds using the TOD-methodology with a human observer) for a range of conditions: different light levels, moving stimuli with different speeds, movies and single frames. The performance analysis show that the model simulations are largely in line with the recorded sensor images with some minor deviations. The result of the study is a detailed, validated and powerful sensor performance prediction model. This project has received funding from the Electronic Component Systems for European Leadership Joint Undertaking.
引用
收藏
页数:12
相关论文
共 50 条
  • [1] EO system design and performance optimization by image-based end-to-end modeling
    Bijl, P.
    Hogervorst, M. A.
    [J]. INFRARED IMAGING SYSTEMS: DESIGN, ANALYSIS, MODELING, AND TESTING XXX, 2019, 11001
  • [2] End-to-End Image-Based Fashion Recommendation
    Elsayed, Shereen
    Brinkmeyer, Lukas
    Schmidt-Thieme, Lars
    [J]. RECOMMENDER SYSTEMS IN FASHION AND RETAIL, 2023, 981 : 109 - 119
  • [3] End-to-end learning for image-based air quality level estimation
    Chao Zhang
    Junchi Yan
    Changsheng Li
    Hao Wu
    Rongfang Bie
    [J]. Machine Vision and Applications, 2018, 29 : 601 - 615
  • [4] End-to-end learning for image-based air quality level estimation
    Zhang, Chao
    Yan, Junchi
    Li, Changsheng
    Wu, Hao
    Bie, Rongfang
    [J]. MACHINE VISION AND APPLICATIONS, 2018, 29 (04) : 601 - 615
  • [5] Requirements Based Design and End-to-End Dynamic Modeling of a Robotic Tool for Vitreoretinal Surgery
    Mablekos-Alexiou, Anestis
    Ourselin, Sebastien
    da Cruz, Lyndon
    Bergeles, Christos
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2018, : 135 - 141
  • [6] Toward end-to-end optical system modeling and optimization; a step forward in optical design
    Crowther, BG
    Wassom, SR
    [J]. NOVEL OPTICAL SYSTEMS DESIGN AND OPTIMIZATION VII, 2004, 5524 : 196 - 204
  • [7] Ultrasound Image-Based Diagnosis of Cirrhosis with an End-to-End Deep Learning model
    Yang, Hai
    Sun, Xiaohui
    Sun, Yang
    Cui, Ligang
    Li, Bingshan
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE, 2020, : 1193 - 1196
  • [8] Investigation of an end-to-end neural architecture for image-based source term estimation
    Abdulaziz, A.
    Altmann, Y.
    McLaughlin, S.
    Davies, M. E.
    [J]. 2023 SENSOR SIGNAL PROCESSING FOR DEFENCE CONFERENCE, SSPD, 2023, : 71 - 75
  • [9] End-to-End Deep Reinforcement Learning for Image-Based UAV Autonomous Control
    Zhao, Jiang
    Sun, Jiaming
    Cai, Zhihao
    Wang, Longhong
    Wang, Yingxun
    [J]. APPLIED SCIENCES-BASEL, 2021, 11 (18):
  • [10] End-to-End Learning for Image-Based Detection of Molecular Alterations in Digital Pathology
    Teichmann, Marvin
    Aichert, Andre
    Bohnenberger, Hanibal
    Stroebel, Philipp
    Heimann, Tobias
    [J]. MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT II, 2022, 13432 : 88 - 98