Search

Using deep learning semantic segmentation for land use extraction is the most challenging problem in medium spatial resolution imagery. This is because of the deep convolution layer and multiple levels of deep steps of the baseline network, which can cause a degradation problem in small land use features. In this paper, a deep learning semantic segmentation algorithm which comprises an adjustment network architecture (LoopNet) and land use dataset is proposed for automatic land use classification using Landsat 8 imagery. The experimental results illustrate that deep learning semantic segmentation using the baseline network (SegNet, U-Net) outperforms pixel-based machine learning algorithms (MLE, SVM, RF) for land use classification. Furthermore, the LoopNet network, which comprises a convolutional loop and convolutional block, is superior to other baseline networks (SegNet, U-Net, PSPnet) and improvement networks (ResU-Net, DeeplabV3+, U-Net++), with 89.84% overall accuracy and good segmentation results. The evaluation of multispectral bands in the land use dataset demonstrates that Band 5 has good performance in terms of extraction accuracy, with 83.91% overall accuracy. Furthermore, the combination of different spectral bands (Band 1–Band 7) achieved the highest accuracy result (89.84%) compared to individual bands. These results indicate the effectiveness of LoopNet and multispectral bands for land use classification using Landsat 8 imagery. [ABSTRACT FROM AUTHOR]

We present the weak-lensing analysis of 279 CODEX clusters using imaging data from 4200 deg2 of the DECam Legacy Survey (DECaLS) Data Release 3. The cluster sample results from a joint selection in X-ray, optical richness in the range 20 ≤ λ < 110, and redshift in the range 0.1 ≤  z  ≤ 0.2. We model the cluster mass (M 200c) and the richness relation with the expression |$\left\langle M_{\rm 200c} | \lambda \right\rangle \propto M_{0} \, (\lambda / 40)^{F_{\lambda }}$|⁠. By measuring the CODEX cluster sample as an individual cluster, we obtain the best-fitting values, |$M_{0} = 3.24^{+0.29}_{-0.27} \times 10^{14} \text{M}_{\odot }$|⁠ , and |$F_{\lambda } = 1.00 ^{+0.22}_{-0.22}$| for the richness scaling index, consistent with a power-law relation. Moreover, we separate the cluster sample into three richness groups; λ = 20–30, 30–50, and 50–110, and measure the stacked excess surface mass density profile in each group. The results show that both methods are consistent. In addition, we find an excellent agreement between our weak lensing based scaling relation and the relation obtained with dynamical masses estimated from cluster member velocity dispersions measured by the SDSS-IV/SPIDERS team. This suggests that the cluster dynamical equilibrium assumption involved in the dynamical mass estimates is statistically robust for a large sample of clusters. [ABSTRACT FROM AUTHOR]

In the first of a pair of articles, Utane Sawangwit and Tom Shanks play devil's advocate, wondering if the standard cosmological model is missing something. [ABSTRACT FROM AUTHOR]

The capture of a target spacecraft by a chaser is an on-orbit docking operation that requires an accurate, reliable, and robust object recognition algorithm. Vision-based guided spacecraft relative motion during close-proximity maneuvers has been consecutively applied using dynamic modeling as a spacecraft on-orbit service system. This research constructs a vision-based pose estimation model that performs image processing via a deep convolutional neural network. The pose estimation model was constructed by repurposing a modified pretrained GoogLeNet model with the available Unreal Engine 4 rendered dataset of the Soyuz spacecraft. In the implementation, the convolutional neural network learns from the data samples to create correlations between the images and the spacecraft's six degrees-of-freedom parameters. The experiment has compared an exponential-based loss function and a weighted Euclidean-based loss function. Using the weighted Euclidean-based loss function, the implemented pose estimation model achieved moderately high performance with a position accuracy of 92.53 percent and an error of 1.2 m. The in-attitude prediction accuracy can reach 87.93 percent, and the errors in the three Euler angles do not exceed 7.6 degrees. This research can contribute to spacecraft detection and tracking problems. Although the finished vision-based model is specific to the environment of synthetic dataset, the model could be trained further to address actual docking operations in the future. [ABSTRACT FROM AUTHOR]