In the past two decades, numerous Compressive Imaging (CI) techniques have been developed to reduce acquired data. Recently, these CI methods have incorporated Deep Learning (DL) tools to optimize both the reconstruction algorithm and the sensing model. However, most of these DL-based CI methods have been developed by simulating the sensing process without considering the limitations associated with the optical realization of the optimized sensing model. Since the merit of CI stands with the physical realization of the sensing process, we revisit the leading DL-based CI methods. We present a preliminary comparison of their performances while focusing on practical aspects such as the realizability of the sensing matrix and robustness to the measurement noise.
For nearly twenty years, a multitude of Compressive Imaging (CI) techniques have been under development. Modern approaches to CI leverage the capabilities of Deep Learning (DL) tools in order to enhance both the sensing model and the reconstruction algorithm. Unfortunately, most of these DL-based CI methods have been developed by simulating the sensing process while overlooking limitations associated with the optical realization of the optimized sensing model. This article presents an outline of the foremost DL-based CI methods from a practitioner's standpoint. We conduct a comparative analysis of their performances, with a particular emphasis on practical considerations like the feasibility of the sensing matrices and resistance to noise in measurements.
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.
KEYWORDS: Holography, LIDAR, Stereoscopy, 3D image processing, Compressed sensing, 3D acquisition, Digital micromirror devices, Wavelets, Clouds, 3D surface sensing
Compressive Sensing (CS) can alleviate the sensing effort involved in the acquisition of three dimensional image (3D) data. The most common CS sampling schemes employ uniformly random sampling because it is universal, thus it is applicable to almost any signals. However, by considering general properties of images and properties of the acquisition mechanism, it is possible to design random sampling schemes with variable density that have improved CS performance. We have introduced the concept of non-uniform CS random sampling a decade ago for holography. In this paper we overview the non-uniform CS random concept evolution and application for coherent holography, incoherent holography and for 3D LiDAR imaging.
The single pixel camera is an imaging system particularly well suited for scene acquisition where a matrix detector is unavailable. Because of the long acquisition times, the system is usually aided with common compressive sensing techniques. However, if the scene contains moving elements, the recovery may show poor results. In this article we review a new novel technique we purposed for recovery of a moving scene with a compressive single pixel camera. The technique is inspired by 'Russian-Dolls' multi-scale ordering of the Hadamard sensing matrix. The technique can handle both global motion (e.g. due to camera panning) and motion of the objects in the scene.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.