- 标题
- 摘要
- 关键词
- 实验方案
- 产品
过滤筛选
- 2017
- spectral reconstruction
- interference
- polarization
- transform
- imaging spectrometer
- Optoelectronic Information Science and Engineering
- BITTT
- Zhejiang University
- Guilin University of Aerospace Technology
-
[IEEE 2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE) - Vilnius, Lithuania (2018.11.8-2018.11.10)] 2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE) - Deep Neural Network-based Feature Descriptor for Retinal Image Registration
摘要： Feature description is an important step in image registration workflow. Discriminative power of feature descriptors affects feature matching performance and overall results of image registration. Deep Neural Network-based (DNN) feature descriptors are emerging trend in image registration tasks, often performing equally or better than hand-crafted ones. However, there are no learned local feature descriptors, specifically trained for human retinal image registration. In this paper we propose DNN-based feature descriptor that was trained on retinal image patches and compare it to well-known hand-crafted feature descriptors. Training dataset of image patches was compiled from nine online datasets of eye fundus images. Learned feature descriptor was compared to other descriptors using Fundus Image Registration dataset (FIRE), measuring amount of correctly matched ground truth points (Rank-1 metric) after feature description. We compare the performance of various feature descriptors applied for retinal image feature matching.
关键词： artificial neural networks,biomedical imaging,machine learning,image registration,retinal images,feature descriptors
更新于2025-09-23 15:22:29
-
[IEEE 2018 International Conference and Exposition on Electrical And Power Engineering (EPE) - Iasi, Romania (2018.10.18-2018.10.19)] 2018 International Conference and Exposition on Electrical And Power Engineering (EPE) - Advanced Image Processing in Support of THz Imaging for Early Detection of Gastric Cancer
摘要： Gastric tumors are still late diagnosed and represent min. 17% of cases leading to metastasis. The ability to visualize the mucosa of the gastrointestinal tract in detail is a requisite for early detection of dysplasia and cancer. Although techniques such as chromoendoscopy, high resolution and magnification endoscopy, narrow band imaging, auto-fluorescence imaging improve the visualization and detection of mucosal lesions, biopsy of the targeted lesion must still be performed for a formal histological diagnosis of cellular and architectural atypical.
关键词： gastric cancer,image processing,THz imaging
更新于2025-09-23 15:22:29
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Extraction of Structural and Mineralogical Features from Hyperspectral Drill-Core Scans
摘要： For vein hosted mineralization such as encountered in porphyry systems, the documentation of the main alteration assemblages associated with specific vein generations is essential in understanding the geometry of the mineralized body. Hence, mineralogical and structural information are highly relevant for characterizing the system. In this paper, we present an approach for the extraction of both mineralogical and structural information from hyperspectral scans. We propose a parallel framework which includes a typical mineral mapping technique for the extraction of mineralogical information as well as a ridge detection method, for the extraction of veins, applied on mineral abundance maps. In the proposed framework, the abundance maps are obtained from hyperspectral VNIR-SWIR drill-core scans using a linear spectral unmixing technique. Drill cores hosting porphyry stockwork type mineralization are used for the evaluation of the proposed technique and the experimental results show that the method offers a tool for accurately characterizing the mineralized body.
关键词： Core scanning,feature extraction,hyperspectral imaging,mineral mapping,image segmentation
更新于2025-09-23 15:22:29
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Focusing of Spaceborne Bistatic SAR Data Based on Time-Domain Perturbation
摘要： Spaceborne bistatic synthetic aperture radar (BiSAR) system with an inclined geosynchronous (GEO) illuminator and a low-earth-orbit (LEO) receiver is capable of providing higher signal-to-noise ratio (SNR), finer resolution and vast area of surveillance. However, spatial-variant characteristics of the echo signal caused by the complex bistatic formation raise technical challenges in data focusing. To address the issue, an improved chirp scaling (CS) algorithm based on time-domain perturbation is proposed. Firstly, the signal model of GEO-LEO bistatic SAR is derived based on the geometry. Then, two-dimension (2-D) perturbation functions are employed to correct the spatial-variant characteristics of the echo signal. Finally, the phase compensation functions are generated to compensate for the residual phase. The proposed algorithm is able to implement wide-swath and high-resolution imaging. Simulation results of point targets show the validity of the presented method.
关键词： chirp scaling,spatial-variant,imaging,bistatic SAR,time-domain perturbation
更新于2025-09-23 15:22:29
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Optronic High-Resolution SAR Processing with the Capability of Full-Resolution Imaging
摘要： The improvement of synthetic aperture radar (SAR) resolution brings a broader applications but poses a great burden for SAR data processor. Real-time processing becomes a difficulty. Optronic technology has been developed for SAR real-time processing due to its ultrafast processing speed. A novel real-time optronic high-resolution SAR processor is proposed in this paper. It has the capability of full-resolution imaging. Restricted with the data scale of spatial light modulators (SLMs), SAR raw data cannot be all encoded onto the light beams at a time. To solve this, subaperture architecture is introduced in our system scheme. SAR data is optically processed in parallel by multiple optical subaperture processing modules and synthesized into a full-resolution SAR image. The module is implemented by multiple SLMs and lenses, which is innovatively proposed in this paper. The proposed system is applicable to large-scale SAR data processing, and the data scale is easy to extend with implementation of adding identical optical subaperture processing modules. Airborne SAR real data is used in the experiment, and a high-resolution image is also given. The PSLR of the focus results with and without subaperture partition are analyzed, which validate the satisfying image quality of the proposed algorithm.
关键词： high resolution,synthetic aperture radar,spatial light modulator,subaperture,full-resolution imaging,Optronic processing
更新于2025-09-23 15:22:29
-
Offshore Underwater Image Restoration Using Reflection-Decomposition-Based Transmission Map Estimation
摘要： A new restoration model for underwater images is presented, based on the dark channel reflection-illumination decomposition and local backscattering lighting estimation, to promote the clarity of edge detail and the colorfulness of the output image. For turbid offshore environments, a novel underwater image restoration method is further introduced by applying a statistical prior to the offshore attenuation coefficients. It is shown that the estimated transmission map with lighting-reflection decomposition, rather than dividing the dark channel by the maximal backscattering light as the other methods do, provides better clarity and color restoration. Detailed qualitative and quantitative analysis on hundreds of underwater images is performed, which demonstrates that the proposed method outperforms the state-of-the-art algorithms on the images taken in offshore water characterized by a heavy concentration of colored dissolved organic matter and total suspended matter, and is suitable for fast underwater processing.
关键词： underwater image restoration,underwater imaging,Offshore,underwater optical model
更新于2025-09-23 15:22:29
-
Nonuniformity Correction for Variable-Integration-Time Infrared Camera
摘要： A two-dimensional calibration technique is proposed to correct the spatial nonuniformity in infrared imaging systems adapting to different integration time and time-varying offset with one-time calibration. Differing from traditional calibration-based nonuniformity correction, this method calibrates nonuniformity with two-dimensional information from two integration time besides different irradiance, which conquers drawbacks of traditional calibration-based correction. First, it eliminates the dependence on integration time in calibration process and dramatically suppresses fixed pattern noise by a large attenuation factor. In addition, time-varying offset is real-time canceled by the subtraction of images integrated with normal and short time. Correction error of two-point correction and the proposed method are analyzed in detail. In experiments with cooled infrared camera, the proposed method provides enhanced uniformity even for seven-time variation of integration time using same correction coefficients. Both quantitative and qualitative comparisons to two-point correction demonstrate its superiority. The one-time calibration and shutterless correction scheme avoids interruption of the normal operation for real scene, extending the application range in practical engineering for infrared imaging systems with low complexity of computation and hardware.
关键词： Infrared imaging,nonuniformity correction
更新于2025-09-23 15:22:29
-
A prospective study on dual time 18F-FDG-PET/CT in high-risk prostate cancer patients
摘要： Objective: This proof of concept study investigated whether dual time point FDG-PET/CT with image acquisition after 1 and 3 h could be useful in preoperative staging of patients undergoing robot-assisted radical prostatectomy and extended pelvic lymph node dissection for high-risk prostate cancer. Results: Twenty patients with high-risk prostate cancer underwent dual time point FDG-PET/CT before undergoing surgery. Histologically confirmed lymph node metastases were found in 9/20 (45%). A median of 19 (range 10–41; n = 434) lymph nodes were removed per patient. Pelvic lymph nodes with detectable FDG uptake were seen in two patients only, but the FDG-avid lesion on PET did not correspond with pathological findings in either patient. We found a significant increase in maximal standardized uptake value of the prostate of around 30% between early and late imaging. We found no correlation between clinical findings after radical prostatectomy and PET measurements.
关键词： Prostatic neoplasms,Diagnostic imaging,Positron emission tomography,Fluorodeoxyglucose
更新于2025-09-23 15:22:29
-
[IEEE 2018 OCEANS - MTS/IEEE Kobe Techno-Ocean (OTO) - Kobe, Japan (2018.5.28-2018.5.31)] 2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO) - Generating Underwater Images by GANs and Similarity Measurement
摘要： The complexity of the underwater environment makes it difficult to capture underwater images, therefore can not provide a large amount of training data required for image processing with deep learning. Traditional color transfer methods can only map the color distribution of source image to that of target image one by one, without considering the complexity of the underwater imaging environment, which results in the disadvantages of effectiveness and performance. In this paper, our proposed method, based on GANs(Generative Adversarial Networks), is superior in its consideration of taking underwater imaging model to train the generative network, the air images are converted into underwater images in batches, so as to achieve the purpose of data augment. Additionally, we describe several implementation details to improve the performance of GANs. Finally, we first utilize SIMILATION, SSIM(Structural Similarity Index) and MS-SSIM(Multi-Scale-Structural Similarity Index) to compute the color and structure similarity level for the purpose of evaluating the quality of generated samples. The results indicate that the proposed method performs well in data augment.
关键词： GANs,underwater imaging,similarity measurement,Data Augment
更新于2025-09-23 15:22:29
-
[IEEE 2018 OCEANS - MTS/IEEE Kobe Techno-Ocean (OTO) - Kobe, Japan (2018.5.28-2018.5.31)] 2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO) - The 3D Imaging for Underwater Objects Using SAS Processing Based on Sparse Planar Array
摘要： Acoustic imaging of underwater objects has to include targets of two kinds which are unburied and buried, so that it can demonstrate the underwater environment thoroughly. Especially for the buried objects, it is much more difficult than unburied ones to obtain a qualified acoustical image due to the high backscattering reverberation generated by buried sediments. The three-dimensional downward-looking synthetic aperture sonar(SAS) imaging algorithm based on T-type sparse planar array is presented here to quantify and enhance the performance of underwater objects imaging and to improve the efficiency of sonar mapping as well. Pulse compression, multi narrow-beam nearfield beamforming and synthetic aperture method are applied in vertical direction, across-track direction and along-track direction, respectively. The simulation results show that with regard to the along-track direction, resolution is dependent on the length of the physical aperture and central frequency, as well as irrelevant to the range. Meanwhile, the signal-to-noise ratio(SNR) of image improves with the increase of the length of the synthetic aperture. The across-track direction resolution, however, degrades with the increase of the number of the along-track array elements. Moreover, the method is applied to the sea-trial data of shallow seawater area, where the depth of water is approximately 100 meters and the linear objects are buried at depth of about 3 meters. The results show that the presented algorithm is capable of leading the qualified imaging results for underwater targets.
关键词： underwater object imaging,downward-looking mode,nearfield beamforming,synthetic aperture processing
更新于2025-09-23 15:22:29