Výsledky vyhledávání - "Patrice Roulet"

Enhancing learning-based computer vision algorithms accuracy in sUAS using navigation wide-angle cameras

Autor: Simon Thibault, Julie Buquet, Xavier Dallaire, Pierre Konen, Jocelyn Parent, Patrice Roulet, Jean-François Lalonde

Publikováno v: Artificial Intelligence and Machine Learning in Defense Applications III.

The new generation of sUAS (small Unmanned Aircraft Systems) aims to extend the range of scenarios in which sense-and-avoid functionality and autonomous operation can be used. Relying on navigation cameras, having a wide field of view can increase th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::862ff061465f5dbf769a6f7f3d88ff7b
https://doi.org/10.1117/12.2600197

Zobrazit plný text záznamu

Methodology to design mobile-based camera lenses using freeform surfaces

Autor: Simon Thibault, Xavier Dallaire, Patrice Roulet, Jocelyn Parent, Zhenfeng Zhuang

Publikováno v: Current Developments in Lens Design and Optical Engineering XXII.

Freeform technology is one of the most promising solutions to enhance the performance of optical systems. Aiming to demonstrate the freedom and flexibility of optical system design, several challenging design examples using freeform surface are prese

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::aacec73f50309868d2455229274ccfbf
https://doi.org/10.1117/12.2594001

Zobrazit plný text záznamu

Evaluating the Impact of Wide-Angle Lens Distortion on Learning-based Depth Estimation

Autor: Simon Thibault, Jinsong Zhang, Jean-François Lalonde, Julie Buquet, Patrice Roulet

Publikováno v: CVPR Workshops

Most computer vision research focuses on narrow angle lenses and is not adapted to super-wide-angle (aka spherical) lenses. This is mainly because current neural networks are not designed or trained to interpret the significant barrel distortion that

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d4729c2cbfb5f233e7e3c61c4de69701
https://doi.org/10.1109/cvprw53098.2021.00409

Zobrazit plný text záznamu

Freeform wide-angle camera lens enabling mitigable distortion

Autor: Zhenfeng, Zhuang, Jocelyn, Parent, Patrice, Roulet, Simon, Thibault

Publikováno v: Applied Optics. 61:5449

Allowing natural scenes as well as maximizing field of view (FoV) can benefit from the minimization of distortion for the wide-angle camera. The wide-angle camera utilizing freeform surfaces for mitigating distortions, either barrel distortion or pin

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fe3c23a580e14c2963d7e34ff549a180
https://doi.org/10.1364/ao.456127

Zobrazit plný text záznamu

Impact of non-linear distortion on learning based approaches for depth estimation

Autor: Simon Thibault, Julie Buquet, Jean-François Lalonde, Jinsong Zhang, Patrice Roulet

Publikováno v: OSA Imaging and Applied Optics Congress 2021 (3D, COSI, DH, ISA, pcAOP).

In this work, we evaluate the impact of non-linear distortion on learning based approaches for depth estimation. We use real wide angle images with locally increased resolutions to see how it compares with perspective images.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::02e4619e5cf0743bc4089623e3084da2
https://doi.org/10.1364/3d.2021.3w5a.5

Zobrazit plný text záznamu

Wide angle lens with improved relative illumination characteristics

Autor: Xavier Dallaire, Simon Thibault, Zhenfeng Zhuang, Patrice Roulet, Jocelyn Parent

Publikováno v: Current Developments in Lens Design and Optical Engineering XXI.

Consumers nowadays have a higher expectation on cameras beyond the function of taking photos or videos. In the early years, the applications of cameras with lenses were, however, very restricted. A new generation of super wide-angle lenses capture th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::c2d9cf57e5ccb7d4fed17fc245b0b901
https://doi.org/10.1117/12.2570710

Zobrazit plný text záznamu

Learning-based depth estimation on wide angle images with non linear distortion

Autor: Julie Buquet, Jean-François Lalonde, Jinsong Zhang, Patrice Roulet, Simon Thibault

Publikováno v: Imaging and Applied Optics Congress.

We developed a Convolutional Neural Network to estimate depth on wide-angle images using panomorph lens with controlled distortion. We simulated three different lens model and compared their performances based on their zone of augmented resolution.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::c3e2e7078e548d6c8b720c1e94d6cc64
https://doi.org/10.1364/3d.2020.df3a.1

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání