Imaging through scattering media is challenging since the signal to noise ratio (SNR) of the reflection can be heavily reduced by scatterers. Single-pixel detectors (SPD) with high sensitivities offer compelling advantages for sensing such weak signals. In this paper, we focus on the use of ghost imaging to resolve 2D spatial information using just an SPD. We prototype a polarimetric ghost imaging system that suppresses backscattering from volumetric media and leverages deep learning for fast reconstructions. In this work, we implement ghost imaging by projecting Hadamard patterns that are optimized for imaging through scattering media. We demonstrate good quality reconstructions in highly scattering conditions using a 1.6% sampling rate.

Compressive ghost imaging through scattering media with deep learning.

Super resolution methods alleviate the high cost and high difficulty in applying high resolution infrared image sensors. In this paper we present a novel single image super resolution method for infrared images by combining compressive sensing theory and deep learning. Low resolution images can be regarded as the compressed sampling results of the high resolution ones in compressive sensing. With sparsity in this theory, higher resolution images can be reconstructed. However, because of diverse level of sparsity for different images, the output contains noise and loss of high frequency information. Deep convolutional neural network provides a solution to relieve the noise and supplement some missing high frequency information. By concatenating two methods, we manage to produce better results in super resolution tasks for infrared images than SRCNN and ScSR. PSNR and SSIM values are used to quantify the performance. Applying our method to open datasets and actual infrared imaging experiments, we also find better visual results are preserved.

Infrared Image Super Resolution by Combining Compressive Sensing and Deep Learning.

Optical correlation assists to enhance underwater polarization imaging performance

Owing to its powerful adaptability and robustness to the weak light, the infrared camera equipped on the unmanned aerial vehicle is more and more applied for aerial photography. Nowadays, how to ma...

Moving vehicle detection in aerial infrared image sequences via fast image registration and improved YOLOv3 network

Owing to the great adaptability to the weak light, the infrared camera equipped on the unmanned aerial vehicle is more and more adopted to capture the aerial images. Therefore, how to fully utilize the aerial infrared images for the vehicle detection has attracted widespread attentions. However, due to the low-resolution, low contrast, and few texture features of the infrared image, it is really difficult to implement the vehicle detection in the aerial infrared images. In our work, an efficient and accurate vehicle detection algorithm in aerial infrared images is proposed via an improved yolov3 network. To increase the detection efficiency, we construct a new structure of the improved yolov3 network with only 16 layers. Besides, we expand the anchor boxes to four scales to improve the detection accuracy of the small vehicles. Meanwhile, for the limitation of the infrared vehicle samples, the transfer learning is introduced to train the improved yolov3 network. Finally, the proposed algorithm is evaluated on the VIVID and NPU data sets. Experiments and comprehensive analyses demonstrate that the proposed algorithm generates satisfactory and competitive vehicle detection results.

Vehicle Detection in the Aerial Infrared Images via an Improved Yolov3 Network

We hereby proposed and experimentally demonstrated an active polarization imaging technique, based on wavelength selection, for seeing through highly turbid water where targets are always visually lost. The method was realized by making use of the dependence of light scattering on wavelength in turbid water. Red light illumination was selected to minimize scattering occurring in light propagation and to guarantee accurate estimation of degree of polarization. Experiments demonstrate its contribution to turn targets in highly turbid water from “undetectable” to “detectable.”

Lu Bai

Papers

Deeply seeing through highly turbid water by active polarization imaging.

Super resolution reconstruction of infrared images based on classified dictionary learning