Colombia is an emerging space nation currently transitioning from being an operator of space systems to becoming a satellite manufacturer. The LEOPAR mission represents Colombia's fourth satellite development ende...
详细信息
ISBN:
(纸本)9798350304626
Colombia is an emerging space nation currently transitioning from being an operator of space systems to becoming a satellite manufacturer. The LEOPAR mission represents Colombia's fourth satellite development endeavor. It entails a 3U CubeSat platform equipped with a hyperspectral camera known as ANFA, designed for remote sensing in the spectral range of 450 to 900 nm. Its primary objective is to identify vegetation and deforested areas across Colombian territory. The design and implementation of ANFA, in its initial phase as a laboratory prototype, underwent multiple iterations to align with mission requirements based on the state of the art. Rigorous laboratory tests have successfully validated the payload's proper operation in terms of optical, mechanical, and electronic aspects of operational concepts. The ANFA laboratory prototype was developed using Commercial Off-The-Shelf (COTS) devices to emulate the optical subsystem and integrate it with the electronic subsystem. This prototype achieved scene capture, data transmission through the SPI protocol to the instrument's main microcontroller, data processing, storage in an SD memory card, and imagereconstruction to identify spectral signatures across each pixel in the hyperspectral data cube. Simultaneously, significant progress has been made in designing the optoelectronic detection chain for ANFA, based on the development of a radiometric model for analyzing a reference scene and transforming scene reflectance to Top of the Atmosphere (TOA). Subsequently, we plan to calculate the Signal-to-Noise Ratio (SNR) performance parameter as a tool to select a suitable detector for our hyperspectral camera, meeting the requirements of the LEOPAR mission. Once this process is completed, the goal is to scale the prototype to an engineering model and, ultimately, a flight model. The vision is for ANFA to become the first Colombian hyperspectral instrument launched into space, thereby aligning this development with ongoing
We present a method for the accurate 3D reconstruction of partly-symmetric objects. We build on the strengths of recent advances in neural reconstruction and rendering such as Neural Radiance Fields (NeRF). A major sh...
详细信息
ISBN:
(纸本)9783031198236;9783031198243
We present a method for the accurate 3D reconstruction of partly-symmetric objects. We build on the strengths of recent advances in neural reconstruction and rendering such as Neural Radiance Fields (NeRF). A major shortcoming of such approaches is that they fail to reconstruct any part of the object which is not clearly visible in the training image, which is often the case for in-the-wild images and videos. When evidence is lacking, structural priors such as symmetry can be used to complete the missing information. However, exploiting such priors in neural rendering is highly non-trivial: while geometry and non-reflective materials may be symmetric, shadows and reflections from the ambient scene are not symmetric in general. To address this, we apply a soft symmetry constraint to the 3D geometry and material properties, having factored appearance into lighting, albedo colour and reflectivity. We evaluate our method on the recently introduced CO3D dataset, focusing on the car category due to the challenge of reconstructing highly-reflective materials. We show that it can reconstruct unobserved regions with high fidelity and render high-quality novel view images.
imagereconstruction in photoacoustic tomography (PAT) faces significant challenges due to incomplete projection data. To address this problem, we propose a physics-driven, deep learning-based filtered back-projection...
详细信息
Event cameras offer many advantages, but their output is inherently ambiguous and needs to be converted into a more understandable output. One way to use the output of these cameras is to reconstruct the intensity. Va...
详细信息
In recent times, applications of crop image analysis is continuously increasing in agriculture fields for crop health monitoring, disease identification, and prevention. Crop images are generally captured by wireless ...
详细信息
Existing few-shot segmentation methods have achieved remarkable progress in medical image segmentation. However, many existing methods yield incomplete and discontinuous boundary predictions. In contrast, the Segment ...
详细信息
ISBN:
(纸本)9798350390155;9798350390162
Existing few-shot segmentation methods have achieved remarkable progress in medical image segmentation. However, many existing methods yield incomplete and discontinuous boundary predictions. In contrast, the Segment Anything Model (SAM) consistently produces clear, continuous, and comprehensive segmentation boundaries. Building on this observation, we propose a new two-step network called Mask Matching Network (MMNet) to introduce extra knowledge learned by SAM in natural images for few-shot medical image segmentation. Firstly, Q-Net has been utilized to locate some Regions of Interest (RoI) as prompts for SAM, allowing for the automatic generation of masks without relying on manual prompts. Secondly, we propose a novel Mask Matching Module (MMM), which considers both feature similarity and volume similarity as guidance to collaboratively mine the final segmentation from proposal masks. MMNet achieves state-of-the-art performance with remarkable improvements on two widely used datasets, abdominal MR (ABD) and cardiac MR (CMR), under two different settings.
X-ray computed tomography (CT) based on photon counting detectors (PCD) extends standard CT by counting detected photons in multiple energy bins. PCD data can be used to increase the contrast-to-noise ratio (CNR), inc...
详细信息
ISBN:
(纸本)9781510671553;9781510671546
X-ray computed tomography (CT) based on photon counting detectors (PCD) extends standard CT by counting detected photons in multiple energy bins. PCD data can be used to increase the contrast-to-noise ratio (CNR), increase spatial resolution, reduce radiation dose, reduce injected contrast dose, and compute a material decomposition using a specified set of basis materials.(1) Current commercial and prototype clinical photon counting CT systems utilize PCD-CT reconstruction methods that either reconstruct from each spectral bin separately, or first create an estimate of a material sinogram using a specified set of basis materials and then reconstruct from these material sinograms. However, existing methods are not able to utilize simultaneously and in a modular fashion both the measured spectral information and advanced prior models in order to produce a material decomposition. We describe an efficient, modular framework for PCD-based CT reconstruction and material decomposition using on Multi-Agent Consensus Equilibrium (MACE). Our method employs a detector proximal map or agent that uses PCD measurements to update an estimate of the pathlength sinogram. We also create a prior agent in the form of a sinogram denoiser that enforces both physical and empirical knowledge about the material-decomposed sinogram. The sinogram reconstruction is computed using the MACE algorithm, which finds an equilibrium solution between the two agents, and the final image is reconstructed from the estimated sinogram. Importantly, the modularity of our method allows the two agents to be designed, implemented, and optimized independently. Our results on simulated data show a substantial (450%) CNR boost vs conventional maximum likelihood reconstruction when applied to a phantom used to evaluate low contrast detectability.
Deep image compressors are extensively practiced presently conducive to reduce the complications of conventional image compression algorithms, namely JPEG, run-Iength-encoding etc. The primary focal point using the im...
详细信息
The features of aero-engine hollow turbine blades show a complicated inner air tract, which have a significant influence on the engine's performance. Inspection of the internal structure and flaws of the blades be...
详细信息
The features of aero-engine hollow turbine blades show a complicated inner air tract, which have a significant influence on the engine's performance. Inspection of the internal structure and flaws of the blades become indispensable. Non-destructive testing, such as computed tomography (CT), is an effective method for detecting internal problems. The purpose of this study is to demonstrate how an iterative excitation can be used to recover an incomplete projection in CT for a turbine blade. Firstly, the variance of the background was gathered as previous information. Then, to make up for the missed sample at the ill-angle position, a noise map was added and filtered as prep work for the forward projection. The original projections were retained, and the revised projections were used to extract additional characteristics from the damaged data. Finally, both simulation and actual tests were studied. The Normalised Mean Square Distance (NMSD) of the reconstructed image was reduced by over 20%. The Structural Similarity Index Measure (SSIM) and the Universal Quality Index (UQI) were both enhanced by at least 60% and 41%, respectively. It was demonstrated that the technique can increase the accuracy of reconstruction for a hollow turbine blade.
The Deep image Prior (DIP) technique has been successfully employed in Compressive Spectral Imaging (CSI) as a non-data-driven deep model approach. DIP methodology updates the deep network's weights by minimizing ...
详细信息
ISBN:
(纸本)9798350302615
The Deep image Prior (DIP) technique has been successfully employed in Compressive Spectral Imaging (CSI) as a non-data-driven deep model approach. DIP methodology updates the deep network's weights by minimizing a loss function that considers the difference between the measurements and the forward operator of the network's output. However, this method often yields local minima as all the measurements are evaluated at each iteration. This paper proposes a stochastic deep image prior (SDIP) approach, which stochastically trains DIP networks using random subsets of measurements from different CSI sensors in a CSI fusion (CSIF) setting, resulting in the improvement of the convergence through stochastic gradient descent optimization. The proposed SDIP method improves upon the deterministic DIP and requires less computational time since fewer forward operators are required per iteration. The SPID method provides comparable performance against the state-of-the-art CSIF techniques based on supervised data-driven and unsupervised methods, achieving up to 5 dB in the reconstruction.
暂无评论