Search

Due to the complexity of real optical flow capture, the existing research still has not performed real optical flow capture of infrared (IR) images with the production of an optical flow based on IR images, which makes the research and application of deep learning-based optical flow computation limited to the field of RGB images only. Therefore, in this paper, we propose a method to produce an optical flow dataset of IR images. We utilize the RGB-IR cross-modal image transformation network to rationally transform existing RGB image optical flow datasets. The RGB-IR cross-modal image transformation is based on the improved Pix2Pix implementation, and in the experiments, the network is validated and evaluated using the RGB-IR aligned bimodal dataset M3FD. Then, RGB-IR cross-modal transformation is performed on the existing RGB optical flow dataset KITTI, and the optical flow computation network is trained using the IR images generated by the transformation. Finally, the computational results of the optical flow computation network before and after training are analyzed based on the RGB-IR aligned bimodal data. [ABSTRACT FROM AUTHOR]

Advanced deep learning-based Single Image Super-Resolution (SISR) techniques are designed to restore high-frequency image details and enhance imaging resolution through the use of rapid and lightweight network architectures. Existing SISR methodologies face the challenge of striking a balance between performance and computational costs, which hinders the practical application of SISR methods. In response to this challenge, the present study introduces a lightweight network known as the Spatial and Channel Aggregation Network (SCAN), designed to excel in image super-resolution (SR) tasks. SCAN is the first SISR method to employ large-kernel convolutions combined with feature reduction operations. This design enables the network to focus more on challenging intermediate-level information extraction, leading to improved performance and efficiency of the network. Additionally, an innovative 9 × 9 large kernel convolution was introduced to further expand the receptive field. The proposed SCAN method outperforms state-of-the-art lightweight SISR methods on benchmark datasets with a 0.13 dB improvement in peak signal-to-noise ratio (PSNR) and a 0.0013 increase in structural similarity (SSIM). Moreover, on remote sensing datasets, SCAN achieves a 0.4 dB improvement in PSNR and a 0.0033 increase in SSIM. [ABSTRACT FROM AUTHOR]

Risley-prism-based image sensors can expand the imaging field of view through beam control. The larger the top angle of the prism, the higher the magnification of the field of view, but at the same time, it aggravates the problem of imaging aberrations, which also puts higher requirements on the aberration correction method for the Risley-prism-based image sensor. To improve the speed, accuracy, and stability of the aberration correction process, an automatic calibration method for the Risley-prism-based image sensor is proposed based on a two-axis turntable. The image datasets of the calibration plate with different prism rotation angles and object distances are acquired using a two-axis turntable. Then, the images of the calibration plate are pre-processed using the bicubic interpolation algorithm. The calibration parameters are finally calculated, and parameter optimization is performed. The experimental results verify the feasibility of this automated calibration method. The reprojection error of the calibration is within 0.26 pixels when the distance of the imaging sensor is 3.6 m from the object, and the fine aberration correction results are observed. [ABSTRACT FROM AUTHOR]

Deep-learning-based polarization 3D imaging techniques, which train networks in a data-driven manner, are capable of estimating a target's surface normal distribution under passive lighting conditions. However, existing methods have limitations in restoring target texture details and accurately estimating surface normals. Information loss can occur in the fine-textured areas of the target during the reconstruction process, which can result in inaccurate normal estimation and reduce the overall reconstruction accuracy. The proposed method enables extraction of more comprehensive information, mitigates the loss of texture information during object reconstruction, enhances the accuracy of surface normal estimation, and facilitates more comprehensive and precise reconstruction of objects. The proposed networks optimize the polarization representation input by utilizing the Stokes-vector-based parameter, in addition to separated specular and diffuse reflection components. This approach reduces the impact of background noise, extracts more relevant polarization features of the target, and provides more accurate cues for restoration of surface normals. Experiments are performed using both the DeepSfP dataset and newly collected data. The results show that the proposed model can provide more accurate surface normal estimates. Compared to the UNet architecture-based method, the mean angular error is reduced by 19%, calculation time is reduced by 62%, and the model size is reduced by 11%. [ABSTRACT FROM AUTHOR]

In the process of unmanned aerial vehicle (UAV) visual-navigation-algorithm design and accuracy verification, the question of how to develop a high-precision and high-reliability semi-physical simulation platform has become a significant engineering problem. In this study, a new UAV semi-physical-simulation-platform architecture is proposed, which includes a six-degree-of-freedom mechanical structure, a real-time control system and real-time animation-simulation software. The mechanical structure can realistically simulate the flight attitude of a UAV in a three-dimensional space of 4 × 2 × 1.4 m. Based on the designed mechanical structure and its dynamics, the control system and the UAV real-time flight-animation simulation were designed. Compared with the conventional simulation system, this system enables real-time flight-attitude simulation in a real physical environment and simultaneous flight-attitude simulation in virtual-animation space. The test results show that the repeated positioning accuracy of the three-axis rotary table reaches 0.006°, the repeated positioning accuracy of the three-axis translation table reaches 0.033 mm, and the dynamic-positioning accuracy reaches 0.04° and 0.4 mm, which meets the simulation requirements of high-precision visual UAV navigation. [ABSTRACT FROM AUTHOR]

We applied a polarization filter array and high-speed camera to the imaging of biological tissues during large, dynamic deformations at 7000 frames per second. The results are compared to previous measurements of similar specimens using a rotating polarizer imaging system. The polarization filter eliminates motion blur and temporal bias from the reconstructed collagen fiber alignment angle and retardation images. The polarization imaging configuration dose pose additional challenges due to the need for calibration of the polarization filter array for a given sample in the same lighting conditions as during the measurement. [ABSTRACT FROM AUTHOR]

Conventional multispectral imaging systems based on bandpass filters struggle to record multispectral videos with high spatial resolutions because of their limited light efficiencies. This paper proposes a multi-aperture multispectral imaging system based on notch filters that overcomes this limitation by allowing light from most of the spectrum to pass through. Based on this imaging principle, a prototype multi-aperture multispectral imaging system comprising notch filters was built and demonstrated. Further, a dictionary learning- and total variation-based spectral super-resolution algorithm was developed to reconstruct spectral images. The simulation results obtained using public multispectral datasets showed that, compared to the dictionary learning-based spectral super-resolution algorithm, the proposed algorithm reconstructed the spectral information with a higher accuracy and removed noise, and the verification experiments confirmed the performance efficiency of the prototype system. The experimental results showed that the proposed imaging system can capture images with high spatial and spectral resolutions under low illumination conditions. The proposed algorithm improved the spectral resolution of the acquired data from 9 to 31 bands, and the average peak signal-to-noise ratio remained above 43 dB, which is 13 dB higher than those of the state-of-the-art coded aperture snapshot spectral imaging methods. Simultaneously, the frame rate of the imaging system was up to 5000 frames/s under natural daylight. [ABSTRACT FROM AUTHOR]

How to sustainably conduct intersection operations is a key issue of the current research. For an actuated control intersection, queued vehicles, control parameters, and phase schemes all affect the operation effect. This paper discusses queued vehicles at actuated intersections and their influence on signal timing. First, this paper establishes an improved traffic wave model and proposes a vehicle queuing model on this basis. Second, by analyzing the queuing and dispersion process of queued vehicles, a minimal green time calculation model is proposed. Then, this paper establishes a maximal green time calculation model aiming at minimizing average vehicle delay and maximizing traffic capacity under different phase schemes, and considers the influence of queued vehicles. Lastly, the models are verified separately; results show that the average error of the minimal green time model was 4.18%, and the average optimization rate of the maximal green time model was 9.27%. It is proved that the models achieved great accuracy and optimization effects, which could potentially improve intersection sustainability. [ABSTRACT FROM AUTHOR]