Search for: All records

In this paper, we assess the noise-susceptibility of coherent macroscopic single random phase encoding (SRPE) lensless imaging by analyzing how much information is lost due to the presence of camera noise. We have used numerical simulation to first obtain the noise-free point spread function (PSF) of a diffuser-based SRPE system. Afterwards, we generated a noisy PSF by introducing shot noise, read noise and quantization noise as seen in a real-world camera. Then, we used various statistical measures to look at how the shared information content between the noise-free and noisy PSF is affected as the camera-noise becomes stronger. We have run identical simulations by replacing the diffuser in the lensless SRPE imaging system with lenses for comparison with lens-based imaging. Our results show that SRPE lensless imaging systems are better at retaining information between corresponding noisy and noiseless PSFs under high camera noise than lens-based imaging systems. We have also looked at how physical parameters of diffusers such as feature size and feature height variation affect the noise robustness of an SRPE system. To the best of our knowledge, this is the first report to investigate noise robustness of SRPE systems as a function of diffuser parameters and paves the way for the use of lensless SRPE systems to improve imaging in the presence of image sensor noise. 

Integral imaging has proven useful for three-dimensional (3D) object visualization in adverse environmental conditions such as partial occlusion and low light. This paper considers the problem of 3D object tracking. Two-dimensional (2D) object tracking within a scene is an active research area. Several recent algorithms use object detection methods to obtain 2D bounding boxes around objects of interest in each frame. Then, one bounding box can be selected out of many for each object of interest using motion prediction algorithms. Many of these algorithms rely on images obtained using traditional 2D imaging systems. A growing literature demonstrates the advantage of using 3D integral imaging instead of traditional 2D imaging for object detection and visualization in adverse environmental conditions. Integral imaging’s depth sectioning ability has also proven beneficial for object detection and visualization. Integral imaging captures an object’s depth in addition to its 2D spatial position in each frame. A recent study uses integral imaging for the 3D reconstruction of the scene for object classification and utilizes the mutual information between the object’s bounding box in this 3D reconstructed scene and the 2D central perspective to achieve passive depth estimation. We build over this method by using Bayesian optimization to track the object’s depth in as few 3D reconstructions as possible. We study the performance of our approach on laboratory scenes with occluded objects moving in 3D and show that the proposed approach outperforms 2D object tracking. In our experimental setup, mutual information-based depth estimation with Bayesian optimization achieves depth tracking with as few as two 3D reconstructions per frame which corresponds to the theoretical minimum number of 3D reconstructions required for depth estimation. To the best of our knowledge, this is the first report on 3D object tracking using the proposed approach. 

We propose a diffuser-based lensless underwater optical signal detection system. The system consists of a lensless one-dimensional (1D) camera array equipped with random phase modulators for signal acquisition and one-dimensional integral imaging convolutional neural network (1DInImCNN) for signal classification. During the acquisition process, the encoded signal transmitted by a light-emitting diode passes through a turbid medium as well as partial occlusion. The 1D diffuser-based lensless camera array is used to capture the transmitted information. The captured pseudorandom patterns are then classified through the 1DInImCNN to output the desired signal. We compared our proposed underwater lensless optical signal detection system with an equivalent lens-based underwater optical signal detection system in terms of detection performance and computational cost. The results show that the former outperforms the latter. Moreover, we use dimensionality reduction on the lensless pattern and study their theoretical computational costs and detection performance. The results show that the detection performance of lensless systems does not suffer appreciably. This makes lensless systems a great candidate for low-cost compressive underwater optical imaging and signal detection. 

Image restoration and denoising has been a challenging problem in optics and computer vision. There has been active research in the optics and imaging communities to develop a robust, data-efficient system for image restoration tasks. Recently, physics-informed deep learning has received wide interest in scientific problems. In this paper, we introduce a three-dimensional integral imaging-based physics-informed unsupervised CycleGAN algorithm for underwater image descattering and recovery using physics-informed CycleGAN (Generative Adversarial Network). The system consists of a forward and backward pass. The base architecture consists of an encoder and a decoder. The encoder takes the clean image along with the depth map and the degradation parameters to produce the degraded image. The decoder takes the degraded image generated by the encoder along with the depth map and produces the clean image along with the degradation parameters. In order to provide physical significance for the input degradation parameter w.r.t a physical model for the degradation, we also incorporated the physical model into the loss function. The proposed model has been assessed under the dataset curated through underwater experiments at various levels of turbidity. In addition to recovering the original image from the degraded image, the proposed algorithm also helps to model the distribution under which the degraded images have been sampled. Furthermore, the proposed three-dimensional Integral Imaging approach is compared with the traditional deep learning-based approach and 2D imaging approach under turbid and partially occluded environments. The results suggest the proposed approach is promising, especially under the above experimental conditions. 

RRAM-based in-memory computing (IMC) effectively accelerates deep neural networks (DNNs) and other machine learning algorithms. On the other hand, in the presence of RRAM device variations and lower precision, the mapping of DNNs to RRAM-based IMC suffers from severe accuracy loss. In this work, we propose a novel hybrid IMC architecture that integrates an RRAM-based IMC macro with a digital SRAM macro using a programmable shifter to compensate for the RRAM variations and recover the accuracy. The digital SRAM macro consists of a small SRAM memory array and an array of multiply-and-accumulate (MAC) units. The non-ideal output from the RRAM macro, due to device and circuit non-idealities, is compensated by adding the precise output from the SRAM macro. In addition, the programmable shifter allows for different scales of compensation by shifting the SRAM macro output relative to the RRAM macro output. On the algorithm side, we develop a framework for the training of DNNs to support the hybrid IMC architecture through ensemble learning. The proposed framework performs quantization (weights and activations), pruning, RRAM IMC-aware training, and employs ensemble learning through different compensation scales by utilizing the programmable shifter. Finally, we design a silicon prototype of the proposed hybrid IMC architecture in the 65nm SUNY process to demonstrate its efficacy. Experimental evaluation of the hybrid IMC architecture shows that the SRAM compensation allows for a realistic IMC architecture with multi-level RRAM cells (MLC) even though they suffer from high variations. The hybrid IMC architecture achieves up to 21.9%, 12.65%, and 6.52% improvement in post-mapping accuracy over state-of-the-art techniques, at minimal overhead, for ResNet-20 on CIFAR-10, VGG-16 on CIFAR-10, and ResNet-18 on ImageNet, respectively.