Abstract:As a variant of Convolutional Neural Networks (CNNs) in Deep Learning, the Fully Convolutional Network (FCN) model achieved state-of-the-art performance for natural image semantic segmentation. In this paper, an accurate classification approach for high resolution remote sensing imagery based on the improved FCN model is proposed. Firstly, we improve the density of output class maps by introducing Atrous convolution, and secondly, we design a multi-scale network architecture by adding a skip-layer structure to make it capable for multi-resolution image classification. Finally, we further refine the output class map using Conditional Random Fields (CRFs) post-processing. Our classification model is trained on 70 GF-2 true color images, and tested on the other 4 GF-2 images and 3 IKONOS true color images. We also employ object-oriented classification, patch-based CNN classification, and the FCN-8s approach on the same images for comparison. The experiments show that compared with the existing approaches, our approach has an obvious improvement in accuracy. The average precision, recall, and Kappa coefficient of our approach are 0.81, 0.78, and 0.83, respectively. The experiments also prove that our approach has strong applicability for multi-resolution image classification.

No abstract

No abstract

The paper presents a simple and effective sketch-based algorithm for large scale image retrieval. One of the main challenges in image retrieval is to localize a region in an image which would be matched with the query image in contour. To tackle this problem, we use the human perception mechanism to identify two types of regions in one image: the first type of region (the main region) is defined by a weighted center of image features, suggesting that we could retrieve objects in images regardless of their sizes and positions. The second type of region, called region of interests (ROI), is to find the most salient part of an image, and is helpful to retrieve images with objects similar to the query in a complicated scene. So using the two types of regions as candidate regions for feature extraction, our algorithm could increase the retrieval rate dramatically. Besides, to accelerate the retrieval speed, we first extract orientation features and then organize them in a hierarchal way to generate global-to-local features. Based on this characteristic, a hierarchical database index structure could be built which makes it possible to retrieve images on a very large scale image database online. Finally a real-time image retrieval system on 4.5 million database is developed to verify the proposed algorithm. The experiment results show excellent retrieval performance of the proposed algorithm and comparisons with other algorithms are also given.

Core Ideas A TDR array has been developed for soil moisture profiling. The sensor provides eight incremental measurements at centimeter‐depth resolution. Permittivity, evaporation rate, and soil moisture profile were determined. Near‐surface soil conditions (i.e., moisture and temperature) moderate mass and energy exchange at the soil–atmosphere interface. While remote sensing offers an effective means for mapping near‐surface moisture content across large areas, in situ measurements, targeting those specific remotely sensed soil depths, are poorly understood and high‐resolution near‐surface measurement capabilities are lacking. Time domain reflectometry (TDR) is a well‐established, accurate measurement method for soil dielectric permittivity and moisture content. A TDR array was designed to provide centimeter‐resolution measurements of near‐surface soil moisture. The array consists of nine stainless steel TDR rods spaced 1 cm apart, acting as waveguide pairs to form eight two‐rod TDR probes in series. A critical aspect of the design was matching the spacing of the coaxial cable–TDR rod transition to avoid unwanted reflections in the waveforms. The accuracy of the TDR array permittivity measurement (±1 permittivity unit) was similar to that of conventional TDR as verified in dielectric liquids. Electric field numerical simulations showed minimal influence of adjacent rods during a given rod‐pair measurement. The evaporation rate determined by the TDR array compared well with mass balance data in a laboratory test. Near‐surface soil moisture profile dynamics were monitored at centimeter‐depth resolution using the TDR array in a field experiment where volumetric moisture content estimates (0–8 cm) were within 2% of conventional three‐rod TDR probes averaging across 0 to 8 cm and from 1‐ to 3‐cm depths.