arXiv subjects

Song Wang

Publications and source records attributed to Song Wang.

At least 433 records · Page 24Linked to original sources

arXiv2018

Does Haze Removal Help CNN-based Image Classification?

Hazy images are common in real scenarios and many dehazing methods have been developed to automatically remove the haze from images. Typically, the goal of image dehazing is to produce clearer images from which human vision can better identify the object and structural details present in the images. When the ground-truth haze-free image is available for a hazy image, quantitative evaluation of image dehazing is usually based on objective metrics, such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM). However, in many applications, large-scale images are collected not for visual examination by human. Instead, they are used for many high-level vision tasks, such as automatic classification, recognition and categorization. One fundamental problem here is whether various dehazing methods can produce clearer images that can help improve the performance of the high-level tasks. In this paper, we empirically study this problem in the important task of image classification by using both synthetic and real hazy image datasets. From the experimental results, we find that the existing image-dehazing methods cannot improve much the image-classification performance and sometimes even reduce the image-classification performance.

cs.CV↗

arXiv2018

Interactive Binary Image Segmentation with Edge Preservation

Binary image segmentation plays an important role in computer vision and has been widely used in many applications such as image and video editing, object extraction, and photo composition. In this paper, we propose a novel interactive binary image segmentation method based on the Markov Random Field (MRF) framework and the fast bilateral solver (FBS) technique. Specifically, we employ the geodesic distance component to build the unary term. To ensure both computation efficiency and effective responsiveness for interactive segmentation, superpixels are used in computing geodesic distances instead of pixels. Furthermore, we take a bilateral affinity approach for the pairwise term in order to preserve edge information and denoise. Through the alternating direction strategy, the MRF energy minimization problem is divided into two subproblems, which then can be easily solved by steepest gradient descent (SGD) and FBS respectively. Experimental results on the VGG interactive image segmentation dataset show that the proposed algorithm outperforms several state-of-the-art ones, and in particular, it can achieve satisfactory edge-smooth segmentation results even when the foreground and background color appearances are quite indistinctive.

cs.CV↗

arXiv2018

Machine Learning Classification of Gaia Data Release 2

Machine learning has increasingly gained more popularity with its incredibly powerful ability to make predictions or calculated suggestions for large amounts of data. We apply the machine learning classification to 85,613,922 objects in the $Gaia$ data release 2, based on the combination of the Pan-STARRS 1 and AllWISE data. The classification results are cross-matched with Simbad database, and the total accuracy is 91.9%. Our sample is dominated by stars, $\sim$ 98%, and galaxies makes up 2%. For the objects with negative parallaxes, about 2.5\% are galaxies and QSOs, while about 99.9% are stars if the relative parallax uncertainties are smaller than 0.2. Our result implies that using the threshold of 0 $< σ_π/π<$ 0.2 could yield a very clean stellar sample.

astro-ph.SR↗

arXiv2018

Gaia Calibrated UV Luminous Stars in LAMOST

We take advantage of the Gaia data release 2 to present 275 and 1,774 ultraviolet luminous stars in the FUV and the NUV. These stars are 5$σ$ exceeding the centers of the reference frame that is built with over one million UV stars in the log $g$ vs $T_\textrm{eff}$ diagram. The Galactic extinction is corrected with the 3D dusty map. In order to limit the Lutz-Kelker effect to an insignificant level, we select the stars with the relative uncertainties of the luminosity less than 40% and the trigonometric parallaxes less than 20%. We cross-identified our sample with the catalogs of RR Lyr stars and possible white dwarf main-sequence binaries, and find they compose $\sim$ 62% and $\sim$ 16% of our sample in the FUV and NUV, respectively. This catalog provides a unique sample to study stellar activity, spectrally unresolved compact main-sequence binaries and variable stars.

astro-ph.SR↗

arXiv2018

Unsupervised Learning for Large-Scale Fiber Detection and Tracking in Microscopic Material Images

Constructing 3D structures from serial section data is a long standing problem in microscopy. The structure of a fiber reinforced composite material can be reconstructed using a tracking-by-detection model. Tracking-by-detection algorithms rely heavily on detection accuracy, especially the recall performance. The state-of-the-art fiber detection algorithms perform well under ideal conditions, but are not accurate where there are local degradations of image quality, due to contaminants on the material surface and/or defocus blur. Convolutional Neural Networks (CNN) could be used for this problem, but would require a large number of manual annotated fibers, which are not available. We propose an unsupervised learning method to accurately detect fibers on the large scale, that is robust against local degradations of image quality. The proposed method does not require manual annotations, but uses fiber shape/size priors and spatio-temporal consistency in tracking to simulate the supervision in the training of the CNN. Experiments show significant improvements over state-of-the-art fiber detection algorithms together with advanced tracking performance.

cs.CV↗

arXiv2018

Design Identification of Curve Patterns on Cultural Heritage Objects: Combining Template Matching and CNN-based Re-Ranking

The surfaces of many cultural heritage objects were embellished with various patterns, especially curve patterns. In practice, most of the unearthed cultural heritage objects are highly fragmented, e.g., sherds of potteries or vessels, and each of them only shows a very small portion of the underlying full design, with noise and deformations. The goal of this paper is to address the challenging problem of automatically identifying the underlying full design of curve patterns from such a sherd. Specifically, we formulate this problem as template matching: curve structure segmented from the sherd is matched to each location with each possible orientation of each known full design. In this paper, we propose a new two-stage matching algorithm, with a different matching cost in each stage. In Stage 1, we use a traditional template matching, which is highly computationally efficient, over the whole search space and identify a small set of candidate matchings. In Stage 2, we derive a new matching cost by training a dual-source Convolutional Neural Network (CNN) and apply it to re-rank the candidate matchings identified in Stage 1. We collect 600 pottery sherds with 98 full designs from the Woodland Period in Southeastern North America for experiments and the performance of the proposed algorithm is very competitive.

cs.LG↗

arXiv2018

Discovery of two eclipsing X-ray binaries in M51

We discovered eclipses and dips in two luminous (and highly variable) X-ray sources in M\,51. One (CXOM51 J132943.3$+$471135) is an ultraluminous supersoft source, with a thermal spectrum at a temperature of about 0.1 keV and characteristic blackbody radius of about $10^4$ km. The other (CXOM51 J132946.1$+$471042) has a two-component spectrum with additional thermal-plasma emission; it approached an X-ray luminosity of $10^{39}$erg s$^{-1}$ during outbursts in 2005 and 2012. From the timing of three eclipses in a series of {\it Chandra} observations, we determine the binary period ($52.75 \pm 0.63$ hr) and eclipse fraction ($22\% \pm 0.1\%$) of CXOM51 J132946.1$+$471042. We also identify a blue optical counterpart in archival {\it Hubble Space Telescope} images, consistent with a massive donor star (mass of $\sim$20--35 $M_{\odot}$). By combining the X-ray lightcurve parameters with the optical constraints on the donor star, we show that the mass ratio in the system must be $M_2/M_1 \gtrsim ~18$, and therefore the compact object is most likely a neutron star (exceeding its Eddington limit in outburst). The general significance of our result is that we illustrate one method (applicable to high-inclination sources) of identifying luminous neutron star X-ray binaries, in the absence of X-ray pulsations or phase-resolved optical spectroscopy. Finally, we discuss the different X-ray spectral appearance expected from super-Eddington neutron stars and black holes at high viewing angles.

astro-ph.HE↗

arXiv2018

Object Detection with Mask-based Feature Encoding

Region-based Convolutional Neural Networks (R-CNNs) have achieved great success in the field of object detection. The existing R-CNNs usually divide a Region-of-Interest (ROI) into grids, and then localize objects by utilizing the spatial information reflected by the relative position of each grid in the ROI. In this paper, we propose a novel feature-encoding approach, where spatial information is represented through the spatial distributions of visual patterns. In particular, we design a Mask Weight Network (MWN) to learn a set of masks and then apply channel-wise masking operations to ROI feature map, followed by a global pooling and a cheap fully-connected layer. We integrate the newly designed feature encoder into the Faster R-CNN architecture. The resulting new Faster R-CNNs can preserve the object-detection accuracy of the standard Faster R-CNNs by using substantially fewer parameters. Compared to R-FCNs using state-of-art PS ROI pooling and deformable PS ROI pooling, the new Faster R-CNNs can produce higher object-detection accuracy with good run-time efficiency. We also show that a specifically designed and learned MWN can capture global contextual information and further improve the object-detection accuracy. Validation experiments are conducted on both PASCAL VOC and MS COCO datasets.

cs.CV↗

arXiv2018

The UV Emission of Stars in LAMOST Survey I. Catalogs

We present the ultraviolet magnitudes for over three million stars in the LAMOST survey, in which 2,202,116 stars are detected by $GALEX$. For 889,235 undetected stars, we develop a method to estimate their upper limit magnitudes. The distribution of (FUV $-$ NUV) shows that the color declines with increasing effective temperature for stars hotter than 7000 K in our sample, while the trend disappears for the cooler stars due to upper atmosphere emission from the regions higher than their photospheres. For stars with valid stellar parameters, we calculate the UV excesses with synthetic model spectra, and find that the (FUV $-$ NUV) vs. $R'_{\mathrm{FUV}}$ can be fitted with a linear relation and late-type dwarfs tend to have high UV excesses. There are 87,178 and 1,498,103 stars detected more than once in the visit exposures of $GALEX$ in the FUV and NUV, respectively. We make use of the quantified photometric errors to determine statistical properties of the UV variation, including intrinsic variability and the structure function on the timescale of days. The overall occurrence of possible false positives is below 1.3\% in our sample. UV absolute magnitudes are calculated for stars with valid parallaxes, which could serve as a possible reference frame in the NUV. We conclude that the colors related to UV provide good criteria to distinguish between M giants and M dwarfs, and the variability of RR Lyrae stars in our sample is stronger than that of other A and F stars.

astro-ph.SR↗

arXiv2017

New Open Cluster Candidates Discovered in the XSTPS-GAC Survey

The Xuyi Schmidt Telescope Photometric Survey of the Galactic Anti-center (XSTPS-GAC) is a photometric sky survey that covers nearly 6 000 deg^2 towards Galactic anti-center in g r i bands. Half of its survey field locates on the Galactic Anti-center disk, which makes XSTPS-GAC highly suitable for searching new open clusters in the GAC region. In this paper, we report new open cluster candidates discovered in this survey, as well as properties of these open cluster candidates, such as age, distance and reddening, derived by isochrone fitting in the color-magnitude diagram (CMD). These open cluster candidates are stellar density peaks detected in the star density maps by applying the method from Koposov et al. (2008). Each candidate is inspected on its true color image composed from XSTPS-GAC three band images. Then its CMD is checked, in order to identify whether the central region stars have a clear isochrone-like trend differing from the background stars. The parameters derived from isochrone fitting for these candidates are mainly based on three band photometry of XSTPS-GAC. Meanwhile, when these new candidates are able to be seen clearly on 2MASS, their parameters are also derived based on 2MASS (J-H, J) CMD. Finally, there are 320 known open clusters rediscovered and 24 new open cluster candidates discovered in this work. Further more, the parameters of these new candidates, as well as another 11 known recovered open clusters, are properly determined for the first time.

astro-ph.SR↗

arXiv2017

Curve-Structure Segmentation from Depth Maps: A CNN-based Approach and Its Application to Exploring Cultural Heritage Objects

Motivated by the important archaeological application of exploring cultural heritage objects, in this paper we study the challenging problem of automatically segmenting curve structures that are very weakly stamped or carved on an object surface in the form of a highly noisy depth map. Different from most classical low-level image segmentation methods that are known to be very sensitive to the noise and occlusions, we propose a new supervised learning algorithm based on Convolutional Neural Network (CNN) to implicitly learn and utilize more curve geometry and pattern information for addressing this challenging problem. More specifically, we first propose a Fully Convolutional Network (FCN) to estimate the skeleton of curve structures and at each skeleton pixel, a scale value is estimated to reflect the local curve width. Then we propose a dense prediction network to refine the estimated curve skeletons. Based on the estimated scale values, we finally develop an adaptive thresholding algorithm to achieve the final segmentation of curve structures. In the experiment, we validate the performance of the proposed method on a dataset of depth images scanned from unearthed pottery sherds dating to the Woodland period of Southeastern North America.

cs.CV↗

arXiv2017

Deep Reinforcement Learning with Surrogate Agent-Environment Interface

In this paper, we propose surrogate agent-environment interface (SAEI) in reinforcement learning. We also state that learning based on probability surrogate agent-environment interface provides optimal policy of task agent-environment interface. We introduce surrogate probability action and develop the probability surrogate action deterministic policy gradient (PSADPG) algorithm based on SAEI. This algorithm enables continuous control of discrete action. The experiments show PSADPG achieves the performance of DQN in certain tasks with the stochastic optimal policy nature in the initial training stage.

cs.LG↗

arXiv2017

On Study of the Reliable Fully Convolutional Networks with Tree Arranged Outputs (TAO-FCN) for Handwritten String Recognition

The handwritten string recognition is still a challengeable task, though the powerful deep learning tools were introduced. In this paper, based on TAO-FCN, we proposed an end-to-end system for handwritten string recognition. Compared with the conventional methods, there is no preprocess nor manually designed rules employed. With enough labelled data, it is easy to apply the proposed method to different applications. Although the performance of the proposed method may not be comparable with the state-of-the-art approaches, it's usability and robustness are more meaningful for practical applications.

cs.CV↗

arXiv2017

Ages and structural and dynamical parameters of two globular clusters in the M81 group

GC-1 and GC-2 are two globular clusters (GCs) in the remote halo of M81 and M82 in the M81 group discovered by Jang et al. using the {\it Hubble Space Telescope} ({\it HST}) images. These two GCs were observed as part of the Beijing--Arizona--Taiwan--Connecticut (BATC) Multicolor Sky Survey, using 14 intermediate-band filters covering a wavelength range of 4000--10000 Å. We accurately determine these two clusters' ages and masses by comparing their spectral energy distributions (from 2267 to 20000~Å, comprising photometric data in the near-ultraviolet of the {\it Galaxy Evolution Explorer}, 14 BATC intermediate-band, and Two Micron All Sky Survey near-infrared $JHK_{\rm s}$ filters) with theoretical stellar population-synthesis models, resulting in ages of $15.50\pm3.20$ for GC-1 and $15.10\pm2.70$ Gyr for GC-2. The masses of GC-1 and GC-2 obtained here are $1.77-2.04\times 10^6$ and $5.20-7.11\times 10^6 \rm~M_\odot$, respectively. In addition, the deep observations with the Advanced Camera for Surveys and Wide Field Camera 3 on the {\it HST} are used to provide the surface brightness profiles of GC-1 and GC-2. The structural and dynamical parameters are derived from fitting the profiles to three different models; in particular, the internal velocity dispersions of GC-1 and GC-2 are derived, which can be compared with ones obtained based on spectral observations in the future. For the first time, in this paper, the $r_h$ versus $M_V$ diagram shows that GC-2 is an ultra-compact dwarf in the M81 group.

astro-ph.GA↗

arXiv2017

Identifying Designs from Incomplete, Fragmented Cultural Heritage Objects by Curve-Pattern Matching

Study of cultural-heritage objects with embellished realistic and abstract designs made up of connected and intertwined curves crosscuts a number of related disciplines, including archaeology, art history, and heritage management. However, many objects, such as pottery sherds found in the archaeological record, are fragmentary, making the underlying complete designs unknowable at the scale of the sherd fragment. The challenge to reconstruct and study complete designs is stymied because 1) most fragmentary cultural-heritage objects contain only a small portion of the underlying full design, 2) in the case of a stamping application, the same design may be applied multiple times with spatial overlap on one object, and 3) curve patterns detected on an object are usually incomplete and noisy. As a result, classical curve-pattern matching algorithms, such as Chamfer matching, may perform poorly in identifying the underlying design. In this paper, we develop a new partial-to-global curve matching algorithm to address these challenges and better identify the full design from a fragmented cultural heritage object. Specifically, we develop the algorithm to identify the designs of the carved wooden paddles of the Southeastern Woodlands from unearthed pottery sherds. A set of pottery sherds from the Snow Collection, curated at Georgia Southern University, are used to test the proposed algorithm, with promising results.

cs.CV↗

arXiv2016

An Automated CNN Recommendation System for Image Classification Tasks

Nowadays the CNN is widely used in practical applications for image classification task. However the design of the CNN model is very professional work and which is very difficult for ordinary users. Besides, even for experts of CNN, to select an optimal model for specific task may still need a lot of time (to train many different models). In order to solve this problem, we proposed an automated CNN recommendation system for image classification task. Our system is able to evaluate the complexity of the classification task and the classification ability of the CNN model precisely. By using the evaluation results, the system can recommend the optimal CNN model and which can match the task perfectly. The recommendation process of the system is very fast since we don't need any model training. The experiment results proved that the evaluation methods are very accurate and reliable.

cs.CV↗

arXiv2016

Robust Gait Recognition by Integrating Inertial and RGBD Sensors

Gait has been considered as a promising and unique biometric for person identification. Traditionally, gait data are collected using either color sensors, such as a CCD camera, depth sensors, such as a Microsoft Kinect, or inertial sensors, such as an accelerometer. However, a single type of sensors may only capture part of the dynamic gait features and make the gait recognition sensitive to complex covariate conditions, leading to fragile gait-based person identification systems. In this paper, we propose to combine all three types of sensors for gait data collection and gait recognition, which can be used for important identification applications, such as identity recognition to access a restricted building or area. We propose two new algorithms, namely EigenGait and TrajGait, to extract gait features from the inertial data and the RGBD (color and depth) data, respectively. Specifically, EigenGait extracts general gait dynamics from the accelerometer readings in the eigenspace and TrajGait extracts more detailed sub-dynamics by analyzing 3D dense trajectories. Finally, both extracted features are fed into a supervised classifier for gait recognition and person identification. Experiments on 50 subjects, with comparisons to several other state-of-the-art gait-recognition approaches, show that the proposed approach can achieve higher recognition accuracy and robustness.

cs.CV↗

arXiv2016

An investigation of a magnetic cataclysmic variable with a period of 14.1 ks

Magnetic cataclysmic variables (CVs) contain a white dwarf with magnetic field strong enough to control the accretion flow from a late type secondary. In this paper, we discover a magnetic CV (CXOGSG J215544.4+380116) from the $Chandra$ archive data. The X-ray light curves show a significant period of 14.1 ks, and the X-ray spectra can be described by a multi-temperature hot thermal plasma, suggesting the source as a magnetic CV. The broad dip in the X-ray light curve is due to the eclipse of the primary magnetic pole, and the additional dip in the bright phase of the soft and medium bands may be caused by the accretion stream crossing our line of sight to the primary pole. Follow-up optical spectra show features of an M2--M4 dwarf dominating the red band and a WD which is responsible for the weak upturn in the blue band. The mass ($\sim$ 0.4 $M_{\odot}$) and radius ($\sim$ 0.4 $R_{\odot}$) for the M dwarf are obtained using CV evolution models and empirical relations between the orbital period and the mass/radius. The estimated low X-ray luminosity and accretion rate may suggest the source as a low-accretion-rate polar. In addition, Very Large Array observations reveal a possible radio counterpart to the X-ray source, but with a low significance. Further radio observations with high quality are needed to confirm the radio counterpart and explore the properties of this binary system.

astro-ph.SR↗