Deep learned Inter-Channel Colored Texture Pattern: a new chromatic-texture descriptor

Pattern Analysis and Applications - Texture is a dominant tool for feature extraction. Incorporation of inter-channel chromatic information along with the texture feature will improve the accuracy...     

Gravity measurements and terrain corrections using a digital terrain model in the NW Himalaya

Areas recently gravity surveyed in the NW Himalaya are characterized by high-elevation and high-amplitude topographic undulations. A new method of applying combined Bouguer and terrain corrections using a digital terrain model is highly accurate and offers advantages over conventional techniques by saving efforts and being more flexible. Partitioning parameters for station-dependent inner-zone compartments and station-independent outer zones can be optimally selected for the desired accuracy requirements. A digital terrain database is used to obtain the outer-zone corrections. In the situation of the NW Himalaya surveys, a 1.2 km inner zone is divided into 112 compartments for each station and a digital terrain database containing nearly 16 000 data points for 30″×30″ compartments was applied using the computer program EFFECT.FOR, to compute combined Bouguer and terrain corrections for a 20 km range. The terrain corrections between 20 and 170 km were computed using National Geophysical Data Centre (NGDC) 5′×5′ gridded global elevation database. The magnitude of the terrain correction varies between 3 and 50 mGal. The effects of the 20 km range terrain correction are more pronounced on short-medium wavelength anomalies. The Swarghat gravity high is further enhanced while several high-frequency pseudo-anomalies disappear after applying the terrain corrections. The refined Bouguer anomaly varies from −160 mGal at the southern end of the section, to −310 mGal at the northern end, suggesting a Moho depth variation from 45 to nearly 60 km. The steepness of the northward negative gravity gradient, typical for the Himalaya, is considerably reduced after applying a terrain correction for the 170 km range.     

Hot monkey,cold reality: surveying rainforest canopy mammals using drone-mounted thermal infrared sensors

Animals of the rainforest canopies are often endangered by deforestation or hunting but are difficult to survey and study because of the inaccessibility of the treetops, combined with the visual camouflage of many species. Drone-based thermal sensors have the potential to overcome these hurdles by rapidly scanning large forested areas from above, detecting and mapping wildlife based on the contrast between their warm body temperatures and the cool tree canopies. We tested this concept by flying a drone-mounted thermal infrared radiometric sensor over the wildlife-rich rainforests of Barro Colorado Island, Panama. Arboreal mammals had body temperatures around 27°C and were conspicuous in the thermal infrared imagery at night and early morning when the forest canopy was cool (23–25°C), but were difficult to detect by mid-morning, by which time the direct sunshine had heated up canopy vegetation to over 30°C. Species were difficult to identify from thermal infrared imagery alone, but could be recognized from synchronized visual images taken during the daytime. Simultaneous drone and ground-based surveys of the same area proved that the aerial thermal camera did detect high-canopy species missed by the terrestrial observer, but that substantially more animals were detected by the human than by the drone. Because animal detection was so much better at night, when species ID was difficult, we suggest that future work could combine automated detection of animals from thermal infrared imagery with flash photography or IR illumination to enable species ID during nocturnal surveys. We conclude by discussing various logistical challenges that limit the utility of drone-based thermal infrared today, but that could be overcome by continued improvement of technology and collaboration with permitting agencies.     

Coping with nonstationary environments: a genetic algorithm using neutral variation

In nonstationary environments, it is difficult to apply traditional genetic algorithms (GAs) because they use strong selection pressure and lose the diversity of individuals rapidly. We propose a GA with neutral variation that can track environmental changes. The idea of this GA is inspired by Kimura's neutral theory (1983). The scheme of this GA allows neutral characters, which do not directly affect the fitness with respect to environments, thus increasing the diversity of individuals. In order to demonstrate the properties of this GA, we apply it to a permutation problem called the ladder-network, of which the imposed alignment on the output changes regularly. We show that the GA with neutral variation can adapt better to environmental changes than a traditional GA.     

Volume estimation in a Eucalyptus plantation using multi-source remote sensing and digital terrain data: a case study in Minas Gerais State,Brazil

In this study, we tested the effectiveness of stand age, multispectral optical imagery obtained from the Landsat 8 Operational Land Imager (OLI), synthetic aperture radar (SAR) data acquired by the Sentinel-1B satellite, and digital terrain attributes extracted from a digital elevation model (DEM), in estimating forest volume in 351 plots in a 1,498 ha Eucalyptus plantation in northern Minas Gerais state, Brazil. A Random Forest (RF) machine learning algorithm was used following the Principal Component Analysis (PCA) of various data combinations, including multispectr al and SAR texture variables and DEM-based geomorphometric derivatives. Using multispectral, SAR or DEM variables alone (i.e. Experiments (ii)–(iv)) did not provide accurate estimates of volume (RMSE (Root Mean Square Error) > 32.00 m³ ha^?1) compared to predictions based on age since planting of Eucalyptus stands (Experiment (i)). However, when these datasets were individually combined with stand age (i.e. Experiments (v)–(vii)), the RF models resulted in better volume estimates than those obtained when using the individual multispectral, SAR and DEM datasets (RMSE < 28.00 m³ ha^?1). Furthermore, a model that integrated the selected variables of these data with stand age (Experiment (viii)) improved volume estimation significantly (RMSE = 22.33 m³ ha^?1). The large and increasing area of Eucalyptus forest plantations in Brazil and elsewhere suggests that this new approach to volume estimation has the potential to support Eucalyptus plantation monitoring and forest management practices.     

Dwelling in the canyons: Dwelling detection in urban environments using GPS,Wi-Fi,and geolocation

A fundamental part of studying human mobility is to detect dwelling. When we dwell we are not necessarily stationary, but move around in a confined area. Most of our significant places are indoors, which hampers the detection using GPS. In this work, we discuss three different sensor sources when used for dwelling detection in urban environments: GPS, Wi-Fi and geolocation. Our study is based on data collected on mobile phones in cities of various sizes in four European countries. Based on this data, we compare several methods (i) for classifying whether a user was dwelling and (ii) for determining dwelling locations.     

Mapping of coral reefs using hyperspectral CASI data; a case study: Fordata,Tanimbar, Indonesia

Airborne remote sensing with a CASI‐550 sensor has been used to map the benthic coverage and the bottom topography of the Pulau Nukaha coral reef located in the Tanimbar Archipelago (Southeast Moluccas, Eastern Indonesia). The image classification method adopted was performed in three steps. Firstly, five geomorphological reef components were identified using a supervised spectral angle mapping algorithm in combination with data collected during the field survey, i.e. benthic cover type, percentage cover and depth. Secondly, benthic cover mapping was performed for each of the five geomorphological components separately using an unsupervised hierarchical clustering algorithm followed by class aggregation using both spectral and spatial information. Finally, 16 benthic cover classes could be labelled using the benthic cover data collected during the field survey. The overall classification accuracy, calculated on the biological diverse fore reef, was 73% with a kappa coefficient of 0.63. A reliable bathymetric model (up to a depth of 15 m) of the Pulau Nukaha reef was also obtained using a semi‐analytical radiative transfer model. When compared with independent in‐situ depth measurements, the result proved relatively accurate (mean residual error: ?0.9 m) and was consistent with the seabed topography (Pearson correlation coefficient: 86%).     

Mapping DNA by stochastic relaxation: a new approach to fragment sizes

Instead of the traditional manipulations with given fixed fragment lengths in the restriction map construction a method of varying the lengths is proposed and realized under the simulated annealing algorithm scheme. The described approach has no upper limit on the number of fragments mapped with even ordinary hardware. A program has been derived from the algorithm combined with the last-squares refinement procedure for both linear and circular maps. The algorithm's ability to pick up missed maps is illustrated and the problem of reducing the number of solutions is discussed.     

Independent traction control for uneven terrain using stick-slip phenomenon: application to a stair climbing robot

Mobile robots are being developed for building inspection and security, military reconnaissance, and planetary exploration. In such applications, the robot is expected to encounter rough terrain. In rough terrain, it is important for mobile robots to maintain adequate traction as excessive wheel slip causes the robot to lose mobility or even be trapped. This paper proposes a traction control algorithm that can be independently implemented to each wheel without requiring extra sensors and devices compared with standard velocity control methods. The algorithm estimates the stick-slip of the wheels based on estimation of angular acceleration. Thus, the traction force induced by torque of wheel converses between the maximum static friction and kinetic friction. Simulations and experiments are performed to validate the algorithm. The proposed traction control algorithm yielded a 40.5% reduction of total slip distance and 25.6% reduction of power consumption compared with the standard velocity control method. Furthermore, the algorithm does not require a complex wheel-soil interaction model or optimization of robot kinematics.     

Groundwater assessment through an integrated approach using remote sensing,GIS and resistivity techniques: a case study from a hard rock terrain

Satellite data have been widely used in conjunction with Geographic Information System (GIS) techniques in groundwater resource management. Satellite data are useful for extracting various thematic maps required for groundwater assessment. In this study, Indian Remote Sensing (IRS) 1D LISS III and Landsat Thematic Mapper (TM)/Enhanced TM (ETM+) digital data, and digital elevation models (DEMs) from the Shuttle Radar Topography Mission (SRTM) along with other collateral data were analysed to create various thematic maps (geomorphology, landuse, lithology, lineament, soil, drainage density, river gradient and slope maps) required for groundwater modelling in a hard rock terrain of Bargarh district, Orissa, India. These thematic maps were assigned suitable weights and different rankings to the individual classes within each thematic map using Saaty's Analytical Hierarchy Process (AHP). A raster‐based empirical GIS model was developed for integrating the thematic maps to locate suitable groundwater prospective zones. The integrated thematic maps were in turn used to compute the Groundwater Potential Index (GWPI). GWPI values calculated in the study area were found to vary from 0.175 to 0.940. These GWPI values have been classified into various classes: very poor (<0.4), poor (0.4–0.5), moderate (0.5–0.6), good (0.6–0.7), very good (0.7–0.8) and excellent (>0.8). A final map showing very poor to excellent groundwater prospective zones was prepared. The results thus obtained were subsequently cross‐checked with resistivity survey and pumping test data. Very poor GWPI zones show low yields of 0.5 lps from weathered granite of resistivity 20–100 Ω m and thickness 0.5–6 m, while excellent GWPI zones show high yields of 5–7 lps from highly fractured granite of resistivity 100–300 Ω m and thickness 14–31 m. The results obtained from integration of the various thematic maps on the GIS platform produced a good match with the resistivity and pumping test data.     

GMSK-SLAM: a new RGB-D SLAM method with dynamic areas detection towards dynamic environments

As a research hotspot in the field of robotics, Simultaneous localization and mapping (SLAM) has made great progress in recent years, but few SLAM algorithms take dynamic or movable targets in the scene into account. In this paper, a robust new RGB-D SLAM method with dynamic area detection towards dynamic environments named GMSK-SLAM is proposed. Most of the existing related papers use the method of directly eliminating the whole dynamic targets. Although rejecting dynamic objects can increase the accuracy of robot positioning to a certain extent, this type of algorithm will result in the reduction of the number of available feature points in the image. The lack of sufficient feature points will seriously affect the subsequent precision of positioning and mapping for feature-based SLAM. The proposed GMSK-SLAM method innovatively combines Grid-based Motion Statistics (GMS) feature points matching method with K-means cluster algorithm to distinguish dynamic areas from the images and retain static information from dynamic environments, which can effectively increase the number of reliable feature points and keep more environment features. This method can achieve a highly improvements on localization accuracy in dynamic environments. Finally, sufficient experiments were conducted on the public TUM RGB-D dataset. Compared with ORB-SLAM2 and the RGB-D SLAM, our system, respectively, got 97.3% and 90.2% improvements in dynamic environments localization evaluated by root-mean-square error. The empirical results show that the proposed algorithm can eliminate the influence of the dynamic objects effectively and achieve a comparable or better performance than state-of-the-art methods.

     

Mapping fire scars in a southern African savannah using Landsat imagery

The spectral, spatial and temporal characteristics of the Landsat data record make it appropriate for mapping fire scars. Twenty-two annual fire scar maps from 1972–2002 were produced from historical Landsat imagery for a semi-arid savannah landscape on the South Africa–Botswana border, centred over Madikwe Game Reserve (MGR) in South Africa. A principal components transformation (PCT) helped differentiate the spectral signal of fire scars in each image. A simple, nonparametric, supervised classification (parallelepiped) of the PCT data differentiated burned and unburned areas. During most years, fire occurrences and the percentage of area burned annually were lowest in Botswana, highest in MGR, and intermediate in South Africa outside MGR. These fire scar maps are aiding MGR managers, who are endeavouring to restore a more active fire regime following decades of fire exclusion.     

Delineating dambo catenary soil-landscape units using aerial gamma-ray and terrain data: a comparison of classification approaches

Soil data are largely absent for most of Africa. For landscapes with recognizable catenary elements, this data gap can be filled by mapping the catenary units and assigning them with known soil properties. An example is the landscape map for a region with dambos in central Uganda, which shows the four catenary units in order from well-drained to seasonal wetland: uplands, margins, floors, and bottoms. However, this map was created using optical data, which are cost prohibitive and are also limited by cloud cover. We evaluated the potential of freely available aerial gamma-ray spectrometry (AGRS) data as an alternative source of classification inputs. Analysis of variance based upon field data for a region with dambos in central Uganda showed gamma activity to differ along the catenary sequence, with landscape position explaining an appreciable proportion of variation of potassium (28%), thorium (27%), and uranium (46%). Using the three gamma channels, together with terrain indices derived from the Shuttle Radar Topography Mission (SRTM) digital elevation model (DEM) as inputs, three classifiers were evaluated – conditional inference trees (CITs), random forests (RF), and multinomial-iterative self-organizing data analysis (ISODATA). While untransformed terrain and gamma predictors were used for the first two methods, we applied the ISODATA classification to landscape unit probability maps generated using multinomial principal components regression. For the CIT classification, all decision rules were based on terrain data, which might explain why the map was slightly less accurate (unweighted kappa = 0.61, linear weighted kappa = 0.73) than the map created using a RF classifier (unweighted kappa = 0.63, linear weighted kappa = 0.74), where both terrain and gamma predictors were used. But the existence of artefacts of margins within uplands in the map based on CIT modelling, and not that created using RF, is because the former missed the smoothing effect of gamma, attributed to zonal differences in activity of all three gamma channels. The multinomial-ISODATA predictions were poor (unweighted kappa = 0.56, linear weighted kappa = 0.67), partly because the regression model could not adequately resolve differences between bottoms and floors. However, we did find the probability maps generated using multinomial regression to be useful end products that capture the continuous nature of landscape unit transitions. It is important to note that in this study we used 90 m grid resolution gamma and terrain data to predict features that transition over distances of less than 10 m, so better results might be possible with finer-resolution gamma and terrain data.     

Mapping LAI in a Norway spruce forest using airborne laser scanning

In this study we demonstrate how airborne laser scanning (ALS) can be applied to map effective leaf area index (LAI_e) in a spruce forest, after being calibrated with ground based measurements. In 2003 and 2005, ALS data and field estimates of LAI_e were acquired in a Norway spruce forest in SE Norway. We used LI-COR's LAI-2000® Plant canopy analyzer (“LAI-2000”) and hemispherical images (“HI”) for field based estimates of LAI_e. ALS penetration rate calculated from first echoes and from first and last echoes was strongly related to field estimates of LAI_e. We fitted regression models of LAI_e against the log-transformed inverse of the ALS penetration rate, and in accordance with the Beer-Lambert law this produced a linear, no-intercept relationship. This was particularly the case for the LAI-2000, having R² values > 0.9. The strongest relationship was obtained by selecting ALS data from within a circle around each plot with a radius of 0.75 times the tree height. We found a slight difference in the relationship for the two years, which can be attributed to the differences in the ALS acquisition settings. The relationship was valid across four age classes of trees representing different stages of stand development, except in one case with newly regenerated stands which most likely was an artifact. Using LAI_e based on HI data produced weaker relationships with the ALS data. This was the case even when we simulated LAI-2000 measurements based on the HI data.     

Active measurements of antenna diversity performances using a specific test‐bed,in several environments

The diversity performances of the wireless devices operating in a multipath propagation environment are usually presented in terms of correlation coefficient, diversity gain and effective diversity gain. These parameters can be measured in reverberation chamber. This paper presents some active measurements of antenna diversity performances on a small wireless terminal in several realistic environments. The measurements were performed in the WiMax band, i.e. at 3.5 GHz, in a reverberation chamber where the channel is statistically uniform, in a real indoor propagation channel, and in an outdoor‐to‐indoor environment. The diversity performances are evaluated by using a specific test‐bed constituted by an arbitrary signal generator and two radio‐frequency digitizers. The effectiveness of diversity is presented in terms of effective diversity gain, signal to noise ratio, bit error rate and frame error rate. © 2010 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2010.