Image Distance Research Articles

Laser Image Enhancement Algorithm Based on Improved EnlightenGAN

In distance-selected imaging, the contrast of laser images is reduced due to long imaging distances, insufficient laser power, and atmospheric turbulence. An enhancement algorithm based on the EnlightenGAN network is proposed to improve the contrast of laser images. Firstly, the laser images are acquired using a distance selection pass system to establish the laser image dataset and expand the dataset, and the traditional algorithm is used to enhance the images and establish the mapping relationship between low-quality images and high-quality images. The global discriminator based on PatchGAN with the improved VGG model is used to regularize the self-feature retention loss and construct the depth link between the global discriminator and the local discriminator to improve the generalization ability of the model; adjust the attention map to the second layer before the CLB convolution module and also add the residual structure in the second layer CLB to improve the robustness of the model; adopt the idea of gray-scale layering with a low drop and high rise to improve the self regularization mechanism to achieve the enhancement of the key region; finally, use the improved EnlightenGAN to fit the relationship between a low-quality image and high-quality image. Finally, EnlightenGAN is used to fit the relationship between low-quality images and high-quality images, extract laser image features, and enhance low-quality images. The experimental results show that the improved algorithm improves PSNR by 12.3% and 0.7% on average, SSIM by 57% and 10.3% on average, and NIQE by 21% and 13% on average compared to other algorithms and the original EnlightenGAN algorithm, respectively. The algorithm improves the signal-to-noise ratio and contrast of laser images with richer image details. It provides a new idea for pre-processing laser images.

A Distance Measurement Approach for Large Fruit Picking with Single Camera

Target ranging is the premise for manipulators to complete agronomic operations such as picking and field management; however, complex environmental backgrounds and changing crop shapes increase the difficulty of obtaining target distance information based on binocular vision or depth cameras. In this work, a method for ranging large-sized fruit based on monocular vision was proposed to provide a low-cost and low-computation alternative solution for the fruit thinning or picking robot. The regression relationships between the changes in the number of pixels occupied by the target area and the changes in the imaging distance were calculated based on the images of square-shaped checkerboards and circular-shaped checkerboards with 100 cm2, 121 cm2, 144 cm2, 169 cm2, 196 cm2, 225 cm2, 256 cm2, 289 cm2, and 324 cm2 as the area, respectively. The 918 checkerboard images were collected by the camera within the range from 0.25 m to 1.5 m, with 0.025 m as the length of each moving step, and analyzed in MATLAB to establish the ranging models. A total of 2448 images of four oval watermelons, four pyriform pomelos, and four oblate pomelos, as the representatives of large fruit with different shapes, were used to evaluate and optimize the performance of the models. The images of the front were the input, while the imaging distances were the output. The results showed that the absolute error would be less than 0.06 m for both models and would linearly increase with a decrease in the distance. The relative error could be controlled at 5%. The results proved the proposed monocular method could be a solution for the ranging of large fruit targets.

Chiral Metasurface for Near-Field Imaging and Far-Field Holography Based on Deep Learning

Chiral metasurfaces have great influence on the development of holography. Nonetheless, it is still challenging to design chiral metasurface structures on demand. As a machine learning method, deep learning has been applied to design metasurface in recent years. This work uses a deep neural network with a mean absolute error (MAE) of 0.03 to inverse design chiral metasurface. With the help of this approach, a chiral metasurface with circular dichroism (CD) values higher than 0.4 is designed. The static chirality of the metasurface and the hologram with an image distance of 3000 μm are characterized. The imaging results are clearly visible and demonstrate the feasibility of our inverse design approach.

Fault Diagnosis of Rolling Bearing Based on Variational Mode Decomposition and Improved Canberra Distance in Symmetrized Dot Pattern Image

Fault Diagnosis of Rolling Bearing Based on Variational Mode Decomposition and Improved Canberra Distance in Symmetrized Dot Pattern Image

Large field-of-view short-wave infrared metalens for scanning fiber endoscopy.

The scanning fiber endoscope (SFE), an ultrasmall optical imaging device with a large field-of-view (FOV) for having a clear forward view into the interior of blood vessels, has great potential in the cardiovascular disease diagnosis and surgery assistance, which is one of the key applications for short-wave infrared biomedical imaging. The state-of-the-art SFE system uses a miniaturized refractive spherical lens doublet for beam projection. A metalens is a promising alternative that can be made much thinner and has fewer off-axis aberrations than its refractive counterpart. We demonstrate a transmissive metalens working at 1310nm for a forward viewing endoscope to achieve a shorter device length and better resolution at large field angles. We optimize the metalens of the SFE system using Zemax, fabricate it using e-beam lithography, characterize its optical performances, and compare them with the simulations. The SFE system has a resolution of at the center of field (imaging distance 15mm), an FOV of , and a depth-of-focus of , which are comparable with a state-of-the-art refractive lens SFE. The use of the metalens reduces the length of the optical track from 1.2 to 0.86mm. The resolution of our metalens-based SFE drops by less than a factor of 2 at the edge of the FOV, whereas the refractive lens counterpart has a times resolution degradation. These results show the promise of integrating a metalens into an endoscope for device minimization and optical performance improvement.

High temporal frequency vehicle counting from low-resolution satellite images

Frequent object counting at a specific location (FOC@Loc) is becoming a newly emerging but highly demanded task since the evolution of human activities can provide crucial statistics for social and economic development. Due to the unique requirement of both high temporal frequency for frequent observations and high spatial resolution for object counting, this article aims to propose a novel framework for FOC@Loc to take advantage of both high definitions of high-resolution (HR) image and continuous low-cost low-resolution (LR) image at the same location. To compensate for the low ground sample distance (GSD) in LR images, some prior knowledge about the fixed location is extracted from HR images, including (1) the short-term spatial consistency: provide exact feature-wise and pixel-wise guidance from HR image to the LR image on the same date, learning to predict vehicle area for each LR image; (2) the long-term location consistency: provide the prior parking density of the study location from the sparse HR image sequence, turning the vehicle area into the counting number of each LR image. The final results indicate that this new method obtains highly consistent counting results with the manual annotations, proofing that the HR image guidance information can promote the utilization of LR images for object counting and further analysis. The proposed dataset and methodology have the potential to boost the applications of extensive and inexpensive LR satellite images.

Imaging Threshold for Assessment of the Correct Reduction in the Treatment of Unstable Syndesmotic Injuries - A Retrospective Analysis of 57 CT Scans.

An incongruence of the distal tibiofibular joint (TFJ) after treatment of upper ankle joint injury represents a prearthrotic deformity and must be corrected. The objectives of this study were to analyze postoperative CT scans after surgical treatment of unstable syndesmotic injuries, and to determine the prevalence of syndesmotic malreduction and its contributing factors. The specific parameters of three-dimensional imaging for objective detection of malreduction should be identified as a helpful intraoperative imaging threshold. Postoperative CT scans of 57 patients were analyzed by identifying cases requiring correction. Factors that influenced the reduction result (patient age, sex, fracture type and surgeon qualifications) were evaluated. The following CT measurements were determined: anterior (AD) and posterior tibiofibular distance (PD), TFJ width, anteroposterior fibular translation (APT), length and rotation of the fibula, position of the malleoli to the talar joint surface. A confidence interval of 95% was assumed (significance level p < 0.05). A very high proportion of the cases required revision (38.5%). Age (p=0.199), sex (p=0.752), body mass (p=0.722), and fracture type (p=0.266) had no significant influence on the reduction result. The risk of requiring correction was slightly lower for well-experienced trauma surgeons. The measurements revealed the following thresholds: AD: ø 3.2 mm (±2.2), PD: ø 5.1 mm (±2.2), TFJ: ø 3.4 mm (±1.4), APT: ø 7.9 mm (±3.5), and rotation: ø 10.7° (±6.8). The fibula was too long in 4 cases (7%) and too short in 8 cases (14%). There was a malleolar incongruence in 5 cases (8.7%). The analysis revealed a significant correlation between the ratio of the anterior and posterior tibiofibular distances and a need for correction. The ratio between the anterior and posterior tibiofibular distances in the axial sectional image is an aid for intraoperative assessment of the correct reduction in the TFJ.

Wide field of view flat-panel head-up display system

We propose a novel flat panel-based head-up display (HUD) to realize a large viewing angle automotive display. The proposed flat-panel geometry is straightforward to integrate into the dashboard. We also provide a flat-panel compatible solution to eliminate the ghost image and stray-light in large field of view using space-variant polarization sheets and optimized directional filtering, respectively. The proposed system provides an image area that is about 14 times larger compared to commercial HUD, and the P-polarized virtual image is also viewable with polarized sunglasses. The virtual image distance in our experimental system is closer than in commercial HUD.

The Utility of Smartphone-Based Thermal Imaging in the Management and Monitoring of Microvascular Flap Procedures: A Systematic Review and Meta-Analysis.

Smartphone-based thermal imaging (SBTI) has been reported in the literature to be an easy-to-use, contactless, cost-friendly alternative to standard imaging modalities in identifying flap perforators, monitoring flap perfusion, and detecting flap failure. Our systematic review and meta-analysis aimed to evaluate SBTI's accuracy in perforator identification and secondarily evaluate SBTI's utility in flap perfusion monitoring as well as ability to predict flap compromise, failure, and survival. Following Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines, a systematic review was performed using PubMed from inception to 2021. Articles were uploaded into Covidence and, following duplicate deletion, were initially screened for use of SBTI in flap procedures through title and abstract screening followed by full-text review. The following data points, if provided, were extracted from each included study: study design, number of patients, patient demographics, perforator number and location, flap number and location, room temperature, cooling method, imaging distance, time from cloth removal, primary (SBTI's accuracy in perforator identification), and secondary outcomes (prediction of flap compromise/failure/survival and cost analysis). Meta-analysis was performed using RevMan v.5. The initial search yielded 153 articles. Eleven applicable studies with a total of 430 flaps from 416 patients were ultimately included. The SBTI device assessed in all included studies was FLIR ONE. Four studies assessed the SBTI's perforated detection ability and were included in meta-analysis. Smartphone-based thermal imaging correctly identified 378 (93.3%; n = 405) perforators, and computed tomography angiography (CTA) correctly identified 402 (99.2%; n = 402), although in one study SBTI found additional perforators not detected on CTA. A random-effects model was used (I2 = 65%), and no significant difference in perforator detection ability was found between SBTI and CTA (P = 0.27). This systematic review and meta-analysis supports SBTI as user- and cost-friendly ($229.99), contactless imaging modality with perforator detection ability comparable to current criterion-standard CTA. Postoperatively, SBTI outperformed Doppler ultrasound in early detection of microvascular changes causing flap compromise, allowing for prompt tissue salvage. With a minimal learning curve, SBTI seems to be a promising method of postoperative flap perfusion monitoring able to be used by all hospital ranks. Smartphone-based thermal imaging could thus increase flap monitoring frequency and lower complication rates, although further study is warranted.

The visceral pancreatic neck anterior distance may be an effective parameter to predict post-pancreaticoduodenectomy clinically relevant postoperative pancreatic fistula

BackgroundThe clinically relevant postoperative pancreatic fistula (CR-POPF) is significantly correlated with a high post-pancreaticoduodenectomy (PD) mortality rate. Several studies have reported an association between visceral obesity and CR-POPF. Nevertheless, there are many technical difficulties and controversies in the measurement of visceral fat. The aim of this research was to determine whether the visceral pancreatic neck anterior distance (V-PNAD) was a credible predictor for CR-POPF. MethodsWe retrospectively analyzed the data of 216 patients who underwent PD in our center between January 2016 and August 2021. The correlation of patients’ demographic information, imaging variables, and intraoperative data with CR-POPF was assessed. Furthermore, areas under the receiver operating characteristic curves for six distances (abdominal thickness, visceral thickness, abdominal width, visceral width, abdominal PNAD, V-PNAD) were used to identify the best imaging distance to predict POPF. ResultsIn the multivariate logistic analysis, V-PNAD (P < 0.01) was the most significant risk factor for CR-POPF after PD. Males with a V-PNAD >3.97 cm or females with a V-PNAD >3.66 cm were included into the high-risk group. The high-risk group had a higher prevalence of CR-POPF (6.5% vs. 45.1%, P < 0.001), intraperitoneal infection (1.9% vs. 23.9%, P < 0.001), pulmonary infection (3.7% vs. 14.1%, P = 0.012), pleural effusion (17.8% vs. 33.8%, P = 0.014), and ascites (22.4% vs. 40.8%, P = 0.009) than the low-risk group. ConclusionOf all imaging distances, V-PNAD may be the most effective predictor of CR-POPF. Moreover, high-risk patients (males, V-PNAD >3.97 cm; females, V-PNAD >3.66 cm) have a high incidence of CR-POPF and poor short-term post-PD prognosis. Therefore, surgeons should perform PD carefully and take adequate preventive measures to reduce the incidence of pancreatic fistula when the patient has a high V-PNAD.

Tilt Correction of Panoramic Images for a Holistic Visual Homing Method with Planar-Motion Assumption

Holistic local visual homing based on warping of panoramic images relies on some simplifying assumptions about the images and the environment to make the problem more tractable. One of these assumptions is that images are captured on flat ground without tilt. While this might be true in some environments, it poses a problem for a wider real-world application of warping. An extension of the warping framework is proposed where tilt-corrected images are used as inputs. The method combines the tilt correction of panoramic images with a systematic search through hypothetical tilt parameters, using an image distance measure produced by warping as the optimization criterion. This method not only improves the homing performance of warping on tilted images, but also allows for a good estimation of the tilt without requiring additional sensors or external image alignment. Experiments on two newly collected tilted panoramic image databases confirm the improved homing performance and the viability of the proposed tilt-estimation scheme. Approximations of the tilt-correction image transformations and multiple direct search strategies for the tilt estimation are evaluated with respect to their runtime vs. estimation quality trade-offs to find a variant of the proposed methods which best fulfills the requirements of practical applications.

Dynamic detection of three-dimensional crop phenotypes based on a consumer-grade RGB-D camera.

Nondestructive detection of crop phenotypic traits in the field is very important for crop breeding. Ground-based mobile platforms equipped with sensors can efficiently and accurately obtain crop phenotypic traits. In this study, we propose a dynamic 3D data acquisition method in the field suitable for various crops by using a consumer-grade RGB-D camera installed on a ground-based movable platform, which can collect RGB images as well as depth images of crop canopy sequences dynamically. A scale-invariant feature transform (SIFT) operator was used to detect adjacent date frames acquired by the RGB-D camera to calculate the point cloud alignment coarse matching matrix and the displacement distance of adjacent images. The data frames used for point cloud matching were selected according to the calculated displacement distance. Then, the colored ICP (iterative closest point) algorithm was used to determine the fine matching matrix and generate point clouds of the crop row. The clustering method was applied to segment the point cloud of each plant from the crop row point cloud, and 3D phenotypic traits, including plant height, leaf area and projected area of individual plants, were measured. We compared the effects of LIDAR and image-based 3D reconstruction methods, and experiments were carried out on corn, tobacco, cottons and Bletilla striata in the seedling stage. The results show that the measurements of the plant height (R²= 0.9~0.96, RSME = 0.015~0.023 m), leaf area (R²= 0.8~0.86, RSME = 0.0011~0.0041 m 2 ) and projected area (R² = 0.96~0.99) have strong correlations with the manual measurement results. Additionally, 3D reconstruction results with different moving speeds and times throughout the day and in different scenes were also verified. The results show that the method can be applied to dynamic detection with a moving speed up to 0.6m/s and can achieve acceptable detection results in the daytime, as well as at night. Thus, the proposed method can improve the efficiency of individual crop 3D point cloud data extraction with acceptable accuracy, which is a feasible solution for crop seedling 3D phenotyping outdoors.

Cryo-EM image alignment: From pair-wise to joint with deep unsupervised difference learning

Cryo-electron microscopy (cryo-EM) single-particle analysis is a revolutionary imaging technique to resolve and visualize biomacromolecules. Image alignment in cryo-EM is an important and basic step to improve the precision of the image distance calculation. However, it is a very challenging task due to high noise and low signal-to-noise ratio. Therefore, we propose a new deep unsupervised difference learning (UDL) strategy with novel pseudo-label guided learning network architecture and apply it to pair-wise image alignment in cryo-EM. The training framework is fully unsupervised. Furthermore, a variant of UDL called joint UDL (JUDL), is also proposed, which is capable of utilizing the similarity information of the whole dataset and thus further increase the alignment precision. Assessments on both real-world and synthetic cryo-EM single-particle image datasets suggest the new unsupervised joint alignment method can achieve more accurate alignment results. Our method is highly efficient by taking advantages of GPU devices. The source code of our methods is publicly available at “http://www.csbio.sjtu.edu.cn/bioinf/JointUDL/” for academic use.

Study of multispectral polarization imaging in sea fog environment

Marine exploration has become a popular field of concern and research all over the world. The impact of sea fog on ocean exploration is very great, and how to carry out accurate identification of targets in the sea fog environment is a problem we urgently need to solve. In this paper, we simulated and analyzed the particle distribution characteristics of the sea fog layer by using the principle of Mie scattering, designed a spectral polarization imaging system by using Liquid Crystal Variable Retarder (LCVR) and Liquid Crystal Tunable Filter (LCTF) according to the principle of spectral spectroscopy and polarization imaging, conducted calibration experiments on liquid crystal tunable filter, and carried out experiments on visibility, wavelength and imaging distance that affect the experimental results of polarization imaging of sea fog environment. The experimental results show that the polarization decreases with the increase of imaging distance; in the typical visibility (5 km for light fog, 0.5 km for medium fog and 0.05 km for dense fog), the higher the visibility, the higher the polarization; for the typical wavelengths of visible light (450 nm, 530 nm and 670 nm), the polarization increase with the increase of wavelength.

Self-attention module in a multi-scale improved U-net (SAM-MIU-net) motivating high-performance polarization scattering imaging.

Polarization imaging has outstanding advantages in the field of scattering imaging, which still encounters great challenges in heavy scattering media systems even though there are helps from deep learning technology. In this paper, we propose a self-attention module (SAM) in multi-scale improved U-net (SAM-MIU-net) for the polarization scattering imaging, which can extract a new combination of multidimensional information from targets effectively. The proposed SAM-MIU-net can focus on the stable feature carried by polarization characteristics of the target, so as to enhance the expression of the available features, and make it easier to extract polarization features which help to recover the detail of targets for the polarization scattering imaging. Meanwhile, the SAM's effectiveness has been verified in a series of experiments. Based on proposed SAM-MIU-net, we have investigated the generalization abilities for the targets' structures and materials, and the imaging distances between the targets and the ground glass. Experimental results demonstrate that our proposed SAM-MIU-net can achieve high-precision reconstruction of target information under incoherent light conditions for the polarization scattering imaging.

Experimental implementation for near-field displaying application of bound states in continuum supported by terahertz metasurfaces.

Optical bound states in continuum (BICs) are the special lossless electromagnetic resonance modes found in optical transmission media. Optical BICs supported by metasurfaces can bring a series of image-based applications, which can be classified into far-field image-based applications and near-field image-based applications according to imaging distance. The far field image-based applications of optical BICs supported by metasurfaces have been proved theoretically and experimentally. However, the near-field image-based applications are still in the stage of theoretical demonstration, and its practical feasibility is still questioned. In this letter, we have experimentally demonstrated the feasibility of near-field image-based applications of optical BICs. An all-silicon terahertz metasurface that supports near-field displaying based on quasi-BIC is designed. Its unit cell is based on the classic asymmetric elliptical strip structure, and one unit cell of the metasurface corresponds to one display pixel. By observing the electric field distribution of the metasurface in the near-field region, the display of the given image is successfully constructed. The near-field image-based application of BICs may be beneficial for the information encryption, the hidden item detection, matter analysis, etc.

Research progress of correlation imaging under outdoor environment

Image, as a method of information acquisition, is indispensable for human beings, and it plays an irreplaceable role in military and civilian fields, such as detection and scouting, precision guidance, transportation, and industrial production. In the outdoor environment, the resolution, signal-to-noise ratio, and working distance of optical imaging are limited as result of the influence of background light, stray light, and atmospheric medium. In recent years, with the development of muti-discipline such as optics, physics, information theory, and computer science, the new optical imaging technologies continue to emerge, thus bringing new opportunities for outdoor optical imaging towards long-distance, large field of view and high information flux. As one of the new active imaging technologies, correlation imaging has the potential applications of robustness against turbulence and noise, and the possibility of beating the Rayleigh limit. It can deal with the problems better, such as sharp attenuation of optical power caused by long distances, detection of interference signals from environmental noise, and influence of turbulence. Based on the principle of optical imaging, this paper analyzes the factors affecting optical imaging, in terms of resolution, signal-to-noise ratio, spatial bandwidth product, and imaging distance under outdoor environment, focusing on the research progress of outdoor correlation imaging including imaging systems, signal-to-noise screening technology and imaging algorithm. In addition, we analyze the requirements of optical imaging for longer distances and broader field of view, and consider the fundamental problems and the key technologies.

Realization of reconfigurable super-resolution imaging by liquid microlens arrays integrated on light disk

The microlens-assisted microscope realizes super-resolution imaging and observation, and has the advantages of no marking, no damage, real-time, localization, and good environmental compatibility. Liquid microlens arrays with uniformity and easy manipulation can realize super-resolution imaging without complicated mechanical scanning and driving. However, simply and efficiently controlling the imaging distance is a key technical challenge to the realization of super-resolution imaging of microlens. In this paper, the uniform depths of photoresist microholes on light disk are fabricated by ultraviolet exposure technology. Using liquid self-assembly technology, the microholes are filled with glycerol droplets, and thus ensuring the near-field imaging distance of the microlens. The reconfigurable super-resolution of 226-nm-wide grating line and the imaging magnification of 1.59 times are observed under the optical microscope. At present, the theory of super-resolution imaging based on microlens is not unified and perfect. In this paper, the Abbe imaging principle is used to explain the imaging magnification and super-resolution characteristics. Therefore, the liquid microlens arrays integrated on the light disk show great potential application in optical nanometer measurements and sensing devices.

A Fast Detection Method Using Anisotropic Guidance for Infrared Small Target Under Complex Scenes

The development of intelligent control and visual navigation, along with the ongoing increase in imaging distance, has led to realistic demands for weak and small target detection. However, figuring out how to reduce the interference of various complex factors while achieving a high detection rate and low false alarm rate for real-time infrared small target detection is still a significant challenge. We propose a computationally simple single-frame infrared small target fast detection method applicable to complex scenes. First, a novel anisotropy filter bank suitable for small target feature extraction is constructed and modified with a point spread function. This makes it possible to map the salient features and spatial features of the target in the spatial domain using the imaging mechanism. We then combined two sets of feature parameters using the filtered features, including isotropy measure and directional energy factors, to enable the detection of small targets. Experimental findings showed that the algorithm performs well in scenarios involving complicated clouds, urban ground, and vegetation. The software also achieved excellent real-time performance because of its straightforward computational design.

Topographic Mapping Capability Analysis of Moderate Resolution Imaging Camera (MoRIC) Imagery of Tianwen-1 Mars Mission

The Moderate Resolution Imaging Camera (MoRIC) onboard the orbiter of China’s Tianwen-1 Mars mission aims to map the surface of Mars globally and to explore its topography and geomorphology. This camera’s wide field of view can be used to overlap adjacent images sufficiently for topographic reconstruction. This study aimed to assess the topographic mapping potential of MoRIC images via a systematic accuracy analysis of MoRIC stereo mapping based on theoretical calculation and experimental validation. Experimental analyses were conducted using digital elevation models (DEMs) based on MoRIC images covering the Zhurong rover landing area and Mars Chart 11 region. Comparisons between these DEMs and reference DEMs revealed that the elevation accuracy of the former was approximately one ground sampling distance of the MoRIC image, which is consistent with the theoretical accuracy. Based on these results, MoRIC can be used to effectively map the Martian surface via stereo photogrammetry. These results serve as a useful guideline for topographic mapping based on MoRIC images and their application in various streams of research.