Autonomous visual recognition of known surface landmarks for optical navigation around asteroids

In this letter, a structure filling and matching method is proposed for the 3-D reconstruction of buildings, particularly those with combinational structures, from a single high-resolution synthetic aperture radar (SAR) image. This method consists of two stages. First, the structure model of the investigated building is constructed by filling the building structure elements, i.e., walls and roofs, into an initialized empty scene. Subsequently, a series of simulated SAR images is generated by this structure model and matched with the real SAR image of the building. By finding the maximal mutual information between the simulated and real images, the optimal geometric parameters of the model are obtained, which make the output more accurate. Compared with other methods, this method can reconstruct different kinds of practical buildings and retrieve their exact geometric parameters, using only a single SAR image. The performance of this method is evaluated on real TerraSAR-X images to show its effectiveness.

Tagged MRI is a non-invasive technique to assess myocardial deformations. In this paper, we developed a novel non-tracking-based strain estimation method for tagged MRI. This method is based on the extraction of tag's deformation gradient, and therefore avoids the limitations of conventional tracking-based strain estimators. We tested this method on both simulated and real world images. In simulated images, we quantitatively evaluated the accuracy and robustness of our non-tracking estimator. We find that the results of circumferential strain and local tissue rotation angle are highly consistent with the ground truth values. We also tested our method on both normal and patient data. Real world tests show our results are valuable to visually distinguishing normal and abnormal data, and have the potential to quantitatively diagnose cardiac malfunctions or diseases.

Convolutional neural networks (CNNs) have recently been applied successfully in large scale image classification competitions for photographs found on the Internet. As our brains are able to recognize objects in the images, there must be some regularities in the data that a neural network can utilize. These regularities are difficult to find an explicit set of rules for. However, by using a CNN and the backpropagation algorithm for learning, the neural network can learn to pick up on the features in the images that are characteristic for each class. Also, data regularities that are not visually obvious to us can be learned. CNNs are particularly useful for classifying data containing some spatial structure, like photographs and speech. In this paper, the technique is tested on SAR images of ships in harbour. The tests indicate that CNNs are promising methods for discriminating between targets in SAR images. However, the false alarm rate is quite high when introducing confusers in the tests. A big challenge in the development of target classification algorithms, especially in the case of SAR, is the lack of real data. This paper also describes tests using simulated SAR images of the same target classes as the real data in order to fill this data gap. The simulated images are made with the MOCEM software (developed by DGA), based on CAD models of the targets. The tests performed here indicate that simulated data can indeed be helpful in training a convolutional neural network to classify real SAR images.

The rising use of Artificial Intelligence (AI) for Advanced Driver Assistance Systems (ADAS) and Autonomous Vehicles (AVs) comes with the need of comprehensive tests, verification and validation. This is hardly achievable in real test drives alone, but validation with simulated sensors in Virtual Testbeds (VTBs) becomes a popular supplement. To reduce the gap between simulation and reality, Digital Twins of real sensors need to generate data as realistic as possible. Instead of classical methods such as rasterization or ray tracing, a novel approach based on neural networks is developed and evaluated. Based on the concept of Generative Adversarial Networks (GANs) a classification network is trained to distinguish real from simulated images. At the same time the classifier is used as critic to improve a generation network that refines simulated sensor images to look more realistic. This contribution gives an overview of recent research in image-to-image translation with GANs and suggests a framework to generate more realistic sensor images for–but not limited to–automotive applications. State of the art image-to-image translation architectures are evaluated and several methods are suggested to deal with drawbacks and shortcomings. An evaluation metric according to the subjective assessment of a more realistic color distribution in the refined sensor images is introduced. Finally, the potential of the novel approach to be used in VTBs is analyzed and discussed.

Abstract. We propose a new adaptive strategy for text recognition that attempts to derive knowledge about the dominant font on a given page. The strategy uses a linguistic observation that over half of all words in a typical English passage are contained in a small set of less than 150 stop words. A small dictionary of such words is compiled from the Brown corpus. An arbitrary text page first goes through layout analysis that produces word segmentation. A fast procedure is then applied to locate the most likely candidates for those words, using only widths of the word images. The identity of each word is determined using a word shape classifier. Using the word images together with their identities, character prototypes can be extracted using a previously proposed method. We describe experiments using simulated and real images. In an experiment using 400 real page images, we show that on average, eight distinct characters can be learned from each page, and the method is successful on 90% of all the pages. These can serve as useful seeds to bootstrap font learning.

Hyperspectral image provides a way to analyze component and the fraction by spectral unmixing. The classical method is Least Squares algorithm. But it is defined without any constraint on the abundance. The Fully constrained Least Squares (FCLS) algorithm allows resulted abundances satisfying sum-to-one and non-negative, which is practical. It has been widely used till now because it may work quickly with a small unmxing error. But when the number of endmembers is large, it gets much slow. And unmxing error is high if the endmembers are not found out completely. As for improving the speed of the algorithm, there have been many research works. But fewer algorithms are developed for increasing accurateness. Here in this paper, a primal-dual interior-point method is tested for the fully constraint unmixing with the linear unmixing model being modified slightly. A dual problem is established firstly, and then the process of the algorithm is designed to decrease distance between original problem and the dual problem based on result of FCLS. In order to promise high unmxing accurateness, the unmxing error of resulted abundances is added into the optimizing goal. Several algorithms of fully constraint abundance estimation are tested on both simulation and real hyperspectral images. The experimental results show that the prompted algorithm may find the optimal abundance for existing endmembers even though the endmember set is not complete. Accurateness of unmxing is increased, especially on the real image.

A robust star identification algorithm with star shortlisting

Practical simulations of low-dose CT images have a possibility of being helpful means for optimization of the CT exposure dose. Because current methods reported by several researchers are limited to specific vendor platforms and generally rely on raw sinogram data that are difficult to access, we have developed a new computerized scheme for producing simulated low-dose CT images from real high-dose images without use of raw sinogram data or of a particular phantom. Our computerized scheme for low-dose CT simulation was based on the addition of a simulated noise image to a real high-dose CT image reconstructed by the filtered back-projection algorithm. First, a sinogram was generated from the forward projection of a high-dose CT image. Then, an additional noise sinogram resulting from use of a reduced exposure dose was estimated from a predetermined noise model. Finally, a noise CT image was reconstructed with a predetermined filter and was added to the real high-dose CT image to create a simulated low-dose CT image. The noise power spectrum and modulation transfer function of the simulated low-dose images were very close to those of the real low-dose images. In order to confirm the feasibility of our method, we applied this method to clinical cases which were examined with the high dose initially and then followed with a low-dose CT. In conclusion, our proposed method could simulate the low-dose CT images from their real high-dose images with sufficient accuracy and could be used for determining the optimal dose setting for various clinical CT examinations.

Purpose: To validate a previously proposed algorithm that modifies a mammogram to appear as if it was acquired with different technique factors using realistic phantom-based mammograms. Approach: Two digital mammography systems (an indirect- and a direct-detector-based system) were used to acquire realistic mammographic images of five 3D-printed breast phantoms with the technique factors selected by the automatic exposure control and at various other conditions (denoted by the original images). Additional images under other simulated conditions were also acquired: higher or lower tube voltages, different anode/filter combinations, or lower tube current-time products (target images). The signal and noise in the original images were modified to simulate the target images (simulated images). The accuracy of the image modification algorithm was validated by comparing the target and simulated images using the local mean, local standard deviation (SD), local variance, and power spectra (PS) of the image signals. The absolute relative percent error between the target and simulated images for each parameter was calculated at each sub-region of interest (local parameters) and frequency (PS), and then averaged. Results: The local mean signal, local SD, local variance, and PS of the target and simulated images were very similar, with a relative percent error of 5.5%, 3.8%, 7.8%, and 4.4% (indirect system), respectively, and of 3.7%, 3.8%, 7.7%, and 7.5% (direct system), respectively. Conclusions: The algorithm is appropriate for simulating different technique factors. Therefore, it can be used in various studies, for instance to evaluate the impact of technique factors in cancer detection using clinical images.

Learning based denoising methods have attracted increasing interest in the recent past. These methods rely on data pairs. In the case of denoising, the data pairs are usually noise corrupted images and their noise-free counterparts, if available. Otherwise an associated high-dose X-ray image can be used instead as a practical alternative. As the current image processing techniques are not yet able to provide the necessary image quality at very low dose levels, it is usually not possible to acquire clinical sequences. As variation in the data is extremely important for learning based methods, phantom data alone cannot be used to train a network and achieve optimal performance. A possibility to overcome this issue is to simulate low dose images from the related high dose images. However, to make sure that the simulated low dose images are realistic (replicate the properties of real low dose images), image noise attributes associated with low dose image acquisition need to be taken into account. In their paper we introduce a novel method to simulate low dose images from high dose images based on modelling the X-ray image formation process. This way, we can better account for imaging parameters such as system gain and electronic noise. We have evaluated our method by comparing several corresponding regions of the simulated lower dose images with that of real lower dose images using a two sample Kolmogorov-Smirnov Test at 5% significance. Out of 40 pairs, in 85% of the cases the hypothesis that the corresponding regions (from the low and simulated low dose images) belong to the same distribution has been accepted.

Identifying the proper orientation of the pelvis is a critical step in accurate placement of the femur prosthesis in the acetabulum in Total Hip Replacement \n(THR) surgeries. The general approach to localize the orientation of the pelvis coordinate system is to use X-ray fluoroscopy to guide the procedure. An \nalternative can be employing intra-operative ultrasound (US) imaging with pre-operative CT scan or fluoroscopy imaging. In this paper, we propose to replace \nthe need of pre-operative imaging by using a statistical shape model of the pelvis, constructed from several CT images. We then propose an automatic deformable \nintensity-based registration of the anatomical atlas to a sparse set of 2D ultrasound images of the pelvis in order to localize its anatomical coordinate system. \nIn this registration technique, we first extract a set of 2D slices from a single instance of the pelvic atlas. Each individual 2D slice is generated based on \nthe location of a corresponding 2D ultrasound image. Next, we create simulated ultrasound images out of the 2D atlas slices and calculate a similarity metric \nbetween the simulated images and the actual ultrasound images. The similarity metric guides an optimizer to generate an instance of the atlas that best matches \nthe ultrasound data. We demonstrated the feasibility of our proposed approach on two male human cadaver data. The registration was able to localize a \npatient-specific pelvic coordinate system with origin translation error of 2 mm and 3.45 mm, and average axes rotation error of 3.5 degrees and 3.9 degrees for \nthe two cadavers, respectively.\n\nCopyright 2010 Society of Photo-Optical Instrumentation Engineers. \nOne print or electronic copy may be made for personal use only. Systematic reproduction and distribution, \nduplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.

In recent years, automatic target recognition (ATR) based on deep learning has achieved great success in RGB field, which has huge data support. However, due to the confidentiality of military targets, weather constraints, and high shooting costs, it is difficult to obtain a large number of real IR images which leads to the performance degradation of deep learning algorithms in IR field. This paper discusses the method of using simulation IR images as training set to get rid of dependence on the real image. However, there are still great differences between the original simulated image and the real image, which leads to many defects when using the original simulated image for training. Therefore, in this paper, we use cycleGAN to convert the original simulation image into the intermediate image closer to the real image based on generative adversarial networks (GAN). Finally, the effectiveness of this method is proved by experiments.

The objective of this research was to develop and validate a custom computed tomography dose-reduction simulation technique for producing images that have an appearance consistent with the same scan performed at a lower mAs (with fixed kVp, rotation time, and collimation). Synthetic noise is added to projection (sinogram) data, incorporating a stochastic noise model that includes energy-integrating detectors, tube-current modulation, bowtie beam filtering, and electronic system noise. Experimental methods were developed to determine the parameters required for each component of the noise model. As a validation, the outputs of the simulations were compared to measurements with cadavers in the image domain and with phantoms in both the sinogram and image domain, using an unbiased root-mean-square relative error metric to quantify agreement in noise processes. Four-alternative forced-choice (4AFC) observer studies were conducted to confirm the realistic appearance of simulated noise, and the effects of various system model components on visual noise were studied. The "just noticeable difference (JND)" in noise levels was analyzed to determine the sensitivity of observers to changes in noise level. Individual detector measurements were shown to be normally distributed (p > 0.54), justifying the use of a Gaussian random noise generator for simulations. Phantom tests showed the ability to match original and simulated noise variance in the sinogram domain to within 5.6% +/- 1.6% (standard deviation), which was then propagated into the image domain with errors less than 4.1% +/- 1.6%. Cadaver measurements indicated that image noise was matched to within 2.6% +/- 2.0%. More importantly, the 4AFC observer studies indicated that the simulated images were realistic, i.e., no detectable difference between simulated and original images (p = 0.86) was observed. JND studies indicated that observers' sensitivity to change in noise levels corresponded to a 25% difference in dose, which is far larger than the noise accuracy achieved by simulation. In summary, the dose-reduction simulation tool demonstrated excellent accuracy in providing realistic images. The methodology promises to be a useful tool for researchers and radiologists to explore dose reduction protocols in an effort to produce diagnostic images with radiation dose "as low as reasonably achievable".

Strong lensing in galaxy clusters probes properties of dense cores of dark matter halos in mass, studies the distant universe at flux levels and spatial resolutions otherwise unavailable, and constrains cosmological models independently. The next-generation large-scale sky imaging surveys are expected to discover thousands of cluster-scale strong lenses, which would lead to unprecedented opportunities for applying cluster-scale strong lenses to solve astrophysical and cosmological problems. However, the large data set challenges astronomers to identify and extract strong-lensing signals, particularly strongly lensed arcs, because of their complexity and variety. Hence, we propose a framework to detect cluster-scale strongly lensed arcs, which contains a transformer-based detection algorithm and an image simulation algorithm. We embed prior information of strongly lensed arcs at cluster scale into the training data through simulation and then train the detection algorithm with simulated images. We use the trained transformer to detect strongly lensed arcs from simulated and real data. Results show that our approach could achieve 99.63% accuracy rate, 90.32% recall rate, 85.37% precision rate, and 0.23% false-positive rate in detection of strongly lensed arcs from simulated images and could detect almost all strongly lensed arcs in real observation images. Besides, with an interpretation method, we have shown that our method could identify important information embedded in simulated data. Next, to test the reliability and usability of our approach, we will apply it to available observations (e.g., DESI Legacy Imaging Surveys 6 6 https://www.legacysurvey.org/ ) and simulated data of upcoming large-scale sky surveys, such as Euclid 7 7 https://www.euclid-ec.org/ and the China Space Station Telescope. 8 8 https://nao.cas.cn/csst/

Anomaly detection of internal defects in underground engineering structures is critical. This paper proposes an unsupervised deep learning image-to-image translation method tailored for ground penetrating radar (GPR) images. The proposed model can translate real-world GPR images to simulated ones. In this manner, labeling real GPR images is not necessary, and only the target detection model trained on simulated GPR images is required to directly identify defects in real GPR images. The unsupervised deep learning network introduces geometry-consistency constraints into the CycleGAN, which largely prevents the problem of semantic distortion in translation. Validation of the proposed method was performed using GPR data collected in various scenarios using GPR of different center frequencies and manufacturers. Moreover, to verify its adaptability and feasibility for defect recognition, commonly used deep learning-based defect recognition methods, which were trained only on simulated GPR images, were used to detect the translated GPR images. The findings indicate that the type and location of internal defects in translated GPR images can be accurately identified using the proposed method.