Detection of moving objects through turbulent media. Decomposition of Oscillatory vs Non-Oscillatory spatio-temporal vector fields

Gilles, Jérôme; Álvarez, Federico; Ferrante, Nicholas; Fortman, Margaret; Tahir, L.; Tarter, A.; Seeger, Adam

doi:10.1016/j.imavis.2018.03.006

Cited by 9 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extensive researches have been conducted on modeling the generation of turbulence in the atmosphere and its effects on light propagation [3][4][5][6][7][8][9] . Kolmogorov turbulence model concisely described the spectrum of turbulence strength as a function of the eddy size (or spatial frequency).…”

Section: Atmospheric Turbulencementioning

confidence: 99%

See 1 more Smart Citation

Effective framework for space target detection through atmospheric turbulence

Chen,

Wang,

Song

et al. 2023

AOPC 2023: Optical Spectroscopy and Imaging; And Atmospheric and Environmental Optics

View full text Add to dashboard Cite

Section: Atmospheric Turbulencementioning

confidence: 99%

“…Object detection through atmospheric turbulence has been investigated by only a few researchers and most of these studies are based on moving target detection in sequences of images [3,8] . Due to the randomness of turbulence related aberrations, one-shot target recognition through turbulence is difficult.…”

Section: Object Detectionmentioning

confidence: 99%

Effective framework for space target detection through atmospheric turbulence

Chen,

Wang,

Song

et al. 2023

AOPC 2023: Optical Spectroscopy and Imaging; And Atmospheric and Environmental Optics

View full text Add to dashboard Cite

“…However, the boundaries of moving objects are detected based on the optical flow between frames, in order to compensate for occlusions that occur due to the motion. Gilles et al (2018) [19] introduce a method designed to separate the motion from moving objects from the turbulent motion. The approach consists in decomposing the spatiotemporal stack of optical flow images into an oscillatory (the turbulence) and a non-oscillatory (the moving object) component.…”

Section: Literature Overviewmentioning

confidence: 99%

Turbulence mitigation pipelines evaluation

Boehrer,

Piscaer,

Reeling Brouwer

et al. 2023

Environmental Effects on Light Propagation and Adaptive Systems VI

View full text Add to dashboard Cite

Long range horizontal path imaging through atmospheric turbulence is hampered by spatiotemporally randomly varying shifting and blurring of scene points in recorded imagery. Software mitigation strategies have been developed to produce sharp and stable imagery. However, it remains challenging to correct video disturbed by turbulence in real time. Real time implementation of turbulence mitigation will search for compromises between processing performance and corrected image quality. In this paper we compare the quality of real time turbulence mitigation to the results of non-real-time algorithms that should provide a higher image quality. The paper presents the method for the data collection and the results of the comparison on different scenarios relevant in an operational context.

show abstract

“…Then, moving objects are segmented with the L1 norm [ 25 ]. Gilles adopted a geometric spatiotemporal viewpoint to solve the atmospheric turbulence problem, and developed a model that distinguishes the movement of moving objects in the case of turbulence [ 26 ].…”

Section: Related Workmentioning

confidence: 99%

Domain Adaptation and Adaptive Information Fusion for Object Detection on Foggy Days

Chen

Zheng

et al. 2018

Sensors

View full text Add to dashboard Cite

Foggy days pose many difficulties for outdoor camera surveillance systems. On foggy days, the optical attenuation and scattering effects of the medium significantly distort and degenerate the scene radiation, making it noisy and indistinguishable. Aiming to solve this problem, in this paper we propose a novel object detection method that has the ability to exploit the information in the color and depth domains. To prevent the error propagation problem, we clean the depth information before the training process and remove false samples from the database. A domain adaptation strategy is employed to adaptively fuse the decisions obtained in the color and depth domains. In the experiments, we evaluate the contribution of the depth information for object detection on foggy days. Moreover, the advantages of the multiple-domain adaptation strategy are experimentally demonstrated via comparison with other methods.

show abstract

Detection of moving objects through turbulent media. Decomposition of Oscillatory vs Non-Oscillatory spatio-temporal vector fields

Cited by 9 publications

References 34 publications

Effective framework for space target detection through atmospheric turbulence

Effective framework for space target detection through atmospheric turbulence

Turbulence mitigation pipelines evaluation

Domain Adaptation and Adaptive Information Fusion for Object Detection on Foggy Days

Contact Info

Product

Resources

About