Progressive compressive LIDAR sensing (Conference Presentation)

Adrian Stern; Vladislav Kravets

doi:10.1117/12.2563317

22 April 2020 Progressive compressive LIDAR sensing (Conference Presentation)

Adrian Stern, Vladislav Kravets

Author Affiliations +

Proceedings Volume 11402, Three-Dimensional Imaging, Visualization, and Display 2020; 114020G (2020) https://doi.org/10.1117/12.2563317
Event: SPIE Defense + Commercial Sensing, 2020, Online Only

Abstract

If the resolution of a compressively sensed image is not satisfactory then typically a new acquisition session with more samples needs to be set, and the reconstruction process needs to be run from scratch. Here we present a method to capture LiDAR images by progressively increasing the resolution of the 3D reconstructed image. The method prescribes the additional set of samples required to improve the resolution of a compressively sensed LiDAR. Then, a reconstruction procedure that uses the earlier captured coarser resolution 3D image and the additional samples is applied. The reconstruction process is realized by means of a specially designed deep neural network. This resolution refinement process is efficient in the sense that only the samples needed for the next higher resolution level are captured, and the resolution refinement is performed progressively.

Conference Presentation

Citation Download Citation

Adrian Stern and Vladislav Kravets "Progressive compressive LIDAR sensing (Conference Presentation)", Proc. SPIE 11402, Three-Dimensional Imaging, Visualization, and Display 2020, 114020G (22 April 2020); https://doi.org/10.1117/12.2563317

Access the abstract

PROCEEDINGS
PRESENTATION

WATCH
PRESENTATION SAVE TO MY LIBRARY