Estimating the camera direction of a geotagged image using reference images

Millions of smart phones and GPS-equipped digital cameras sold each year, as well as photo-sharing websites such as Picasa and Panoramio have enabled personal photos to be associated with geographic information. It has been shown by recent research results that the additional global positioning system (GPS) information helps visual recognition for geotagged photos by providing valuable location context. However, the current GPS data only identifies the camera location, leaving the camera viewing direction uncertain within the possible scope of 360°. To produce more precise photo location information, i.e. the viewing direction for geotagged photos, we utilize both Google Street View and Google Earth satellite images. Our proposed system is two-pronged: (1) visual matching between a user photo and any available street views in the vicinity can determine the viewing direction, and (2) near-orthogonal view matching between a user photo taken on the ground and the overhead satellite view at the user geo-location can compute the viewing direction when only the satellite view is available. Experimental results have shown the effectiveness of the proposed framework.     

Estimating life-form cover fractions in California sage scrub communities using multispectral remote sensing

The California sage scrub (CSS) community type in California's Mediterranean-type ecosystems is known for its high biodiversity and is home to a large number of rare, threatened, and endangered species. Because of extensive urban development in the past fifty years, this ecologically significant community type is highly degraded and fragmented. To conserve endangered CSS communities, monitoring internal conditions of communities is as crucial as monitoring distributions of the community type in the region. Vegetation type mapping and field sampling of individual plants provide ecologically meaningful information about CSS communities such as spatial distribution and species compositions, respectively. However, both approaches only provide spatially comprehensive information but no information about internal conditions or vice versa. Therefore, there is a need for monitoring variables which fill the information gap between vegetation type maps and field-based data. A number of field-based studies indicate that life-form fractional cover is an effective indicator of CSS community health and habitat quality for CSS-obligated species. This study investigates the effectiveness of remote sensing approaches for estimating fractional cover of true shrub, subshrub, herb, and bare ground in CSS communities of southern California. Combinations of four types of multispectral imagery ranging from 0.15 m resolution scanned color infrared aerial photography to 10 m resolution SPOT 5 multispectral imagery and three image processing models - per-pixel, object-based, and spectral mixture models - were tested.An object-based image analysis (OBIA) routine consistently yielded higher accuracy than other image processing methods for estimating all cover types. Life-form cover was reliably predicted, with error magnitudes as low as 2%. Subshrub and herb cover types required finer spatial resolution imagery for more accurate predictions than true shrub and bare ground types. Positioning of sampling grids had a substantial impact on the reliability of accuracy assessment, particularly for cover estimates predicted using multiple endmember spectral mixture analysis (MESMA) applied to SPOT imagery. Of the approaches tested in this study, OBIA using pansharpened QuickBird imagery is one of the most promising approaches because of its high accuracy and processing efficiency and should be tested for more heterogeneous CSS landscapes. MESMA applied to SPOT imagery should also be examined for effectiveness in estimating factional cover over more extensive habitat areas because of its low data cost and potential for conducting retrospective studies of vegetation community conditions.     

Estimating camera and object translation in the presence of camera rotation

This paper deals with stereo camera-based estimation of sensor translation in the presence of modest sensor rotation and moving objects. It also deals with the estimation of object translation from a moving sensor. The approach is based on Gabor filters, direct passive navigation, and Kalman filters.Three difficult problems associated with the estimation of motion from an image sequence are solved. (1) The temporal correspondence problem is solved using multi-scale prediction and phase gradients. (2) Segmentation of the image measurements into groups belonging to stationary and moving objects is achieved using the Mahalanobis distance. (3) Compensation for sensor rotation is achieved by internally representing the inter-frame (short-term) rotation in a rigid-body model. These three solutions possess a circular dependency, forming a cycle of perception. A seeding process is developed to correctly initialize the cycle. An additional complication is the translation-rotation ambiguity that sometimes exists when sensor motion is estimated from an image velocity field. Temporal averaging using Kalman filters reduces the effect of motion ambiguities. Experimental results from real image sequences confirm the utility of the approach.Financial support from the Natural Science and Engineering Research Council (NSERC) of Canada is acknowledged.     

Quantitative analysis and hyperspectral remote sensing of the nitrogen nutrition index in winter wheat

ABSTRACT

The nitrogen nutrition index (NNI) is a quantitative and reliable indicator of the nitrogen nutrition distribution or status of crops. The timely and accurate estimation of the NNI is crucial in agriculture management. In this study, the quantitative analysis and hyperspectral remote sensing modelling of the NNI were conducted, in which the hyperspectral remote sensing data and NNI data at different growth stages of winter wheat were measured using ground and unmanned aerial vehicle (UAV) carrying high spectrometer equipment. First, the NNIs of the four growth stages of winter wheat were calculated and statistically analyzed. Then, the hyperspectral characteristics at different growth stages and various NNIs were examined. Second, the representation wavebands of the hyperspectral data, which were sensitive to the NNI of winter wheat, were acquired and evaluated. In addition, hyperspectral models were established and comparatively assessed for the NNI estimation. Finally, the hyperspectral characteristics and the remote sensing estimation of the NNIs were determined on the basis of UAV-based hyperspectral data. The results are as follows. (1) As the NNIs of winter wheat changed, the characteristic of the red shift, the variations in the red edge position, and the near-infrared waveband range of the hyperspectral data became apparent. (2) The green band, red edge, and near-infrared were sensitive to the NNIs of winter wheat, and they could be effectively used for estimating the NNI. Moreover, the multiple statistical regression models, which were based on representative wavebands, performed well in estimating the NNI results for the different growth stages of winter wheat.     

Estimating and mapping grass phosphorus concentration in an African savanna using hyperspectral image data

We tested the utility of imaging spectroscopy and neural networks to map phosphorus concentration in savanna grass using airborne HyMAP image data. We also sought to ascertain the key wavelengths for phosphorus prediction using hyperspectral remote sensing. The remote sensing of foliar phosphorus has received very little attention as compared to nitrogen, yet it plays an equally important role in explaining the distribution and feeding patterns of herbivores. Band depths from two continuum‐removed absorption features as well as the red edge position (REP) were input into a backpropagation neural network. Following a series of experiments to ascertain the optimum wavelengths, the best trained neural network was used to predict and ultimately to map grass phosphorus concentration in the Kruger National Park. The results indicate that the best trained neural network could predict phosphorus distribution with a coefficient of determination of 0.63 and a root mean square error (RMSE) of 0.07 (28% of the mean observed phosphorus concentration) on an independent test data set. Our results also show that the absorption feature located in the shortwave infrared (R _2015–2199) contains more information on phosphorus distribution, a region that has hardly been explored before in most spectroscopic experiments for phosphorus as compared to the visible bands. Overall, the study demonstrates the potential of imaging spectroscopy in mapping grass phosphorus concentration in savanna rangelands.     

Estimating fractional snow cover from MODIS using the normalized difference snow index

Snow-cover information is important for a wide variety of scientific studies, water supply and management applications. The NASA Earth Observing System (EOS) Moderate Resolution Imaging Spectroradiometer (MODIS) provides improved capabilities to observe snow cover from space and has been successfully using a normalized difference snow index (NDSI), along with threshold tests, to provide global, automated binary maps of snow cover. The NDSI is a spectral band ratio that takes advantage of the spectral differences of snow in short-wave infrared and visible MODIS spectral bands to identify snow versus other features in a scene. This study has evaluated whether there is a “signal” in the NDSI that could be used to estimate the fraction of snow within a 500 m MODIS pixel and thereby enhance the use of the NDSI approach in monitoring snow cover. Using Landsat 30-m observations as “ground truth,” the percentage of snow cover was calculated for 500-m cells. Then a regression relationship between 500-m NDSI observations and fractional snow cover was developed over three different snow-covered regions and tested over other areas. The overall results indicate that the relationship between fractional snow cover and NDSI is reasonably robust when applied locally and over large areas like North America. The relationship offers advantages relative to other published fractional snow cover algorithms developed for global-scale use with MODIS. This study indicates that the fraction of snow cover within a MODIS pixel using this approach can be provided with a mean absolute error less than 0.1 over the range from 0.0 to 1.0 in fractional snow cover.     

Estimating the leaf area index in Indian tropical forests using Landsat-8 OLI data

Leaf area index (LAI) is a key vegetation biophysical parameter and is extensively used in modelling of phenology, primary production, light interception, evapotranspiration, carbon, and nitrogen dynamics. In the present study, we attempt to spatially characterize LAI for natural forests of Western Ghats India, using ground based and Landsat-8 Operational Land Imager (OLI) sensor satellite data. For this, 41 ground-based LAI measurements were carried out across a gradient of tropical forest types, viz. dry, moist, and evergreen forests using LAI-2200 plant canopy analyser, during the month of March 2015. Initially, measured LAI values were regressed with 15 spectral variables, including nine spectral vegetation indices (SVIs) and six Landsat-8 surface reflectance (ρ) variables using univariate correlation analysis. Results showed that the red (ρ_red), near-infrared (ρ_NIR), shortwave infrared (ρ_SWIR1, ρ_SWIR2) reflectance bands (R² > 0.6), and all SVIs (R² > 0.7) except simple ratio (SR) have the highest and second highest coefficient of determination with ground-measured LAI. In the second step, to select significant (high R², low root mean square error (RMSE), and p-level < 0.05) SVIs to determine the best representative model, stepwise multiple linear regression (SMLR) was implemented. The results indicate that the SMLR model predicted LAI with better coefficient of determination (R² = 0.83, RMSE = 0.78) using normalized difference vegetation index, enhanced vegetation index, and soil-adjusted vegetation index variables compared to the univariate approach. The predicted SMLR model was used to estimate a spatial map of LAI. It is desirable to evaluate the stability and potentiality of regional LAI models in natural forest ecosystems against the operationally accepted Moderate Resolution Imaging Spectroradiometer (MODIS) global LAI product. To do this, the Landsat-8 pixel-based LAI map was resampled to 1 km resolution and compared with the MODIS derived LAI map. Results suggested that Landsat-8 OLI-based VIs provide significant LAI maps at moderate resolution (30 m) as well as coarse resolution (1 km) for regional climate models.     

Passive ranging using a moving camera

This article addresses the problem of determining the 3-dimensional locations of salient points in the environment of a moving camera based on a monocular image sequence obtained by the camera. The camera's translational and rotational velocities are assumed to be known approximately via inertial sensors. The motion of the camera is represented by a constant velocity model. Salient points in the image sequence are extracted using Gabor wavelets and tracked using labeled graph matching. The 3-D positions of the selected environmental points relative to the camera are then estimated recursively using an extended Kalman filter (EKF), after initialization by two-frame motion stereo. The motion parameters of the camera are also refined simultaneously. Experimental results on real data are given. © 1992 John Wiley & Sons, Inc.     

Estimating 40 years of nitrogen deposition in global biomes using the SCIAMACHY NO2 column

Owing to human activity, global nitrogen (N) cycles have been altered. In the past 100 years, global N deposition has increased. Currently, the monitoring and estimating of N deposition and the evaluation of its effects on global carbon budgets are the focus of many researchers. NO₂ columns retrieved by space-borne sensors provide us with a new way of exploring global N cycles and these have the ability to estimate N deposition. However, the time range limitation of NO₂ columns makes the estimation of long timescale N deposition difficult. In this study we used ground-based NO_x emission data to expand the density of NO₂ columns, and 40 years of N deposition (1970–2009) was inverted using the multivariate linear model with expanded NO₂ columns. The dynamic of N deposition was examined in both global and biome scales. The results show that the average N deposition was 0.34 g N m^–2 year^–1 in the 2000s, which was an increase of 38.4% compared with the 1970s’. The total N deposition in different biomes is unbalanced. N deposition is only 38.0% of the global total in forest biomes; this is made up of 25.9%, 11.3, and 0.7% in tropical, temperate, and boreal forests, respectively. As N-limited biomes, there was little increase of N deposition in boreal forests. However, N deposition has increased by a total of 59.6% in tropical forests and croplands, which are N-rich biomes. Such characteristics may influence the effects on global carbon budgets.     

Edge detection in multispectral images using the self-organizing map

In this paper, two new methods for edge detection in multispectral images are presented. They are based on the use of the self-organizing map (SOM) and a grayscale edge detector. With the 2-dimensional SOM the ordering of pixel vectors is obtained by applying the Peano scan, whereas this can be omitted using the 1-dimensional SOM. It is shown that using the R-ordering based methods some parts of the edges may be missed. However, they can be found using the proposed methods. Using them it is also possible to find edges in images which consist of metameric colors. Finally, it is shown that the proposed methods find the edges properly from real multispectral airplane images. The size of the SOM determines the amount of found edges. If the SOM is taught using a large color vector database, the same SOM can be utilized for numerous images.     

Estimating the position of a moving object based on test disturbance of camera position

The problem of estimating the coordinates of a moving object based on visual data arises in numerous applications, starting from robotic and ending with the consumer market of portable devices. Traditional algorithms for solving this problem require either additional devices or significant constraints on the possible motion of the object. In this work, we present a new approach to tracking the object that lets us estimate its position under sufficiently general conditions. The method is based on randomizing the camera location independently of the object’s motion; since the test disturbance we choose is independent, it lets us construct a feasible iterative pseudogradient estimation algorithm.     

Estimating aboveground tree biomass and leaf area index in a mountain birch forest using ASTER satellite data

Biomass and leaf area index (LAI) are important variables in many ecological and environmental applications. In this study, the suitability of visible to shortwave infrared advanced spaceborne thermal emission and reflection radiometer (ASTER) data for estimating aboveground tree and LAI in the treeline mountain birch forests was tested in northernmost Finland. The biomass and LAI of the 128 plots were surveyed, and the empirical relationships between forest variables and ASTER data were studied using correlation analysis and linear and non‐linear regression analysis. The studied spectral features also included several spectral vegetation indices (SVI) and canonical correlation analysis (CCA) transformed reflectances. The results indicate significant relationships between the biomass, LAI and ASTER data. The variables were predicted most accurately by CCA transformed reflectances, the approach corresponding to the multiple regression analysis. The lowest RMSEs were 3.45 t ha^?1 (41.0%) and 0.28 m²m^?2 (37.0%) for biomass and LAI respectively. The red band was the band with the strongest correlation against the biomass and LAI. SR and NDVI were the SVIs with the strongest linear and non‐linear relationships. Although the best models explained about 85% of the variation in biomass and LAI, the undergrowth vegetation and background reflectance are likely to affect the observed relationships.     

Three-diemensional scanner software using a video camera

This paper presents a software development for the obtaining in an automatic way of three-dimensional models of objects (e.g. sculptures, mechanical pieces). Nowadays, there is available software which is able to create three-dimensional models of objects using laser systems, but they are pretty expensive (up to 120,000 €) due to the high technology used for data capture (laser scanner). On the other hand, the software depicted in this paper develops a new process that captures the data with a simple digital video camera and a motorized pedestal (about 1200 €). This way, more than 1300 images of the object are obtained. The later analysis of the edges of all these images will completely define the geometry of the object. So, this software is able to create accurate digital models with a resolution that varies from hundreds to one million of points. In order to export these three-dimensional models the software generates VRML, or ASCII files. These models are very useful in sciences like computer graphics, architecture, mechanics, automated mapping/facilities management, etc.     

People tracking using a network-based PTZ camera

In this paper, we propose a method for online upper body tracking using an IP PTZ camera. This type of camera uses a built-in Web server resulting in variable response times when sending control commands. Furthermore, communicating with a Web server involves network delays. Thus, because the camera is inside a control loop, the effective frame rate that can be processed by a computer vision method is irregular and in general low (2–6 fps). Our tracking method has been specifically designed to perform in such conditions. It detects, at every frame, candidate blobs using motion detection, region sampling, and region color appearance. The target is detected among candidate blobs using a fuzzy classifier. Then, a movement command is sent to the camera using the target position and speed. The proposed method can cope with low frame rate, and thus with large motion of the target, even in the case of a fast walk. Results show that our system has a good target detection precision (>88%) and low track fragmentation, and the target is almost always localized within 1/6th of the image diagonal from the image center.     

Episode detection in videos captured using a head-mounted camera

With the advent of wearable computing, personal imaging, photojournalism and personal video diaries, the need for automated archiving of the videos captured by them has become quite pressing. The principal device used to capture the human-environment interaction with these devices is a wearable camera (usually a head-mounted camera). The videos obtained from such a camera are raw and unedited versions of the visual interaction of the wearer (the user of the camera) with the surroundings. The focus of our research is to develop post-processing techniques that can automatically abstract videos based on episode detection. An episode is defined as a part of the video that was captured when the user was interested in an external event and paid attention to record it. Our research is based on the assumption that head movements have distinguishable patterns during an episode occurrence and these patterns can be exploited to differentiate between an episode and a non-episode. Here we present a novel algorithm exploiting the head and body behaviour for detecting the episodes. The algorithms performance is measured by comparing the ground truth (user-declared episodes) with the detected episodes. The experiments show the high degree of success we achieved with our proposed method on several hours of head-mounted video captured in varying locations.     

Estimating grassland biomass and leaf area index using ground and satellite data

We compared estimates of regional biomass and LAI for a tallgrass prairie site derived from ground data versus estimates derived from satellite data. Linear regression models were estimated to predict LAI and biomass from Landsat-TM data for imagery acquired on three dates spanning the growing season of 1987 using co-registered TM data and ground measurements of LAl and biomass collected at 27 grassland sites. Mapped terrain variables including burning treatment, land-use, and topographic position were included as indicator variables in the models to acccount for variance in biomass and LAI not captured in the TM data. Our results show important differences in the relationships between Kauth-Thomas greenness (from TM), LAI, biomass and the various terrain variables. In general, site-wide estimates of biomass and LAI derived from ground versus satellite-based data were comparable. However, substantial differences were observed in June. In a number of cases, the regression models exhibited significantly higher explained variance due to the incorporation of terrain variables, suggesting that for areas encompassing heterogeneous landcover the inclusion of categorical terrain data in calibration procedures is a useful technique.     

Egomotion estimation of a range camera using the space envelope

In this paper we present a method to compute the egomotion of a range camera using the space envelope. The space envelope is a geometric model that provides more information than a simple segmentation for correspondences and motion estimation. We describe a novel variation of the maximal matching algorithm that matches surface normals to find correspondences. These correspondences are used to compute rotation and translation estimates of the egomotion. We demonstrate our methods on two image sequences containing 70 images. We also discuss the cases where our methods fail, and additional possible methods for exploiting the space envelope.     

Estimating leaf nitrogen concentration from similarities in fresh and dry leaf spectral bands using a model population analysis framework

Fresh leaf spectral reflectance is primarily influenced by leaf water content and structural aspects such as the inter-cellular spaces within the spongy mesophyll, which also interfere with the estimation of the leaf nitrogen content. It is therefore essential to identify spectral bands that are least affected by the above perturbing factors for improving leaf nitrogen estimation for fresh leaves across any landscape. Wavelengths selection plays a vital role in identifying the best spectral features for assessing leaf nitrogen concentration from hyperspectral data of dry and fresh leaves. The primary objective of this study was to determine typical optimal bands for leaf nitrogen estimation from spectra (400–2500 nm) of whole fresh and dry leaves for the same specimens of Eucalyptus grandis. This was achieved via the use of competitive adaptive re-weighted sampling (CARS), and Monte Carlo cross-validation-competitive adaptive re-weighted sampling (MCCV-CARS) band selection approaches. Bands selected (931 nm, 1003 nm, 1027 nm, 1036 nm, 1177 nm, and 1180 nm) via the MCCV-CARS approach yielded the highest estimation accuracy for both fresh predicted coefficient of determination (R²_cal) = 0.82 and predicted root mean square error (RMSE_P) = 0.14) and dry leaves (R²_P = 0.88 and RMSE_P = 0.13) when compared to CARS (2044 nm, 2107 nm, and 2188 nm) only. The identified spectral features could be relevant for assessing leaf nitrogen concentration for different seasons, for example, wet to dry season.     

Monitoring transparency in inland water bodies using multispectral images

The aim of this research was to monitor transparency in inland water bodies from water reflectance field measurements and also from high and medium spatial resolution sensors. The most suitable band to measure transparency was determined by sampling irradiance, water reflectance and transparency at different depths. The results of this sampling show that the wavelength range 520–600 nm is the most suitable band for measuring transparency. Reflectance in this band was regressed against transparency field data to derive an empirical equation for transparency estimation. This equation was assessed using data from Landsat Thematic Mapper (TM) images from 1992 and Daedalus 1268 Airborne Thematic Mapper (ATM) data from 1997. The difference in the errors in the data observed between the two dates was attributed to the fact that in 1997 the sampling time was less than 3 h (1.5 h before and after the acquisition of the image), which allowed similar solar illumination conditions to be maintained, while in 1992 the sampling time was much longer. Once the equation was verified, water transparency monitoring was performed for a set of satellite images obtained from 1984 to 2000. The maps show that transparency in the water bodies responds to seasonal trends. Furthermore, this analysis enabled trophic state and Ecological Quality Ratio (EQR) transparency maps to be generated, which are very useful for the management of water bodies.     

Estimating the number of clusters using a windowing technique

Clustering is the process of partitioning a set of patterns into disjoint and homogeneous meaningful groups (clusters). A fundamental and unresolved issue in cluster analysis is to determine how many clusters are present in a given set of patterns. In this paper, we present the z-windows clustering algorithm, which aims to address this problem using a windowing technique. Extensive empirical tests that illustrate the efficiency and the accuracy of the propsoed method are presented. The text was submitted by the authors in English. Basilis Boutsinas. Received his diploma in Computer Engineering and Informatics in 1991 from the University of Patras, Greece. He also conducted studies in Electronics Engineering at the Technical Education Institute of Piraeus, Greece, and Pedagogics at the Pedagogical Academy of Lamia, Greece. He received his PhD on Knowledge Representation from the University of Patras in 1997. He has been an assistant professor in the Department of Business Administration at the University of Patras since 2001. His primary research interests include data mining, business intelligence, knowledge representation techniques, nonmonotonic reasoning, and parallel AI. Dimitris K. Tasoulis received his diploma in Mathematics from the University of Patras, Greece, in 2000. He attained his MSc degree in 2004 from the postgraduate course “Mathematics of Computers and Decision Making” from which he was awarded a postgraduate fellowship. Currently, he is a PhD candidate in the same course. His research activities focus on data mining, clustering, neural networks, parallel algorithms, and evolutionary computation. He is coauthor of more than ten publications. Michael N. Vrahatis is with the Department of Mathematics at the University of Patras, Greece. He received the diploma and PhD degree in Mathematics from the University of Patras in 1978 and 1982, respectively. He was a visiting research fellow at the Department of Mathematics, Cornell University (1987–1988) and a visiting professor to the INFN (Istituto Nazionale di Fisica Nucleare), Bologna, Italy (1992, 1994, and 1998); the Department of Computer Science, Katholieke Universiteit Leuven, Belgium (1999); the Department of Ocean Engineering, Design Laboratory, MIT, Cambridge, MA, USA (2000); and the Collaborative Research Center “Computational Intelligence” (SFB 531) at the Department of Computer Science, University of Dortmund, Germany (2001). He was a visiting researcher at CERN (European Organization of Nuclear Research), Geneva, Switzerland (1992) and at INRIA (Institut National de Recherche en Informatique et en Automatique), France (1998, 2003, and 2004). He is the author of more than 250 publications (more than 110 of which are published in international journals) in his research areas, including computational mathematics, optimization, neural networks, evolutionary algorithms, and artificial intelligence. His research publications have received more than 600 citations. He has been a principal investigator of several research grants from the European Union, the Hellenic Ministry of Education and Religious Affairs, and the Hellenic Ministry of Industry, Energy, and Technology. He is among the founders of the “University of Patras Artificial Intelligence Research Center” (UPAIRC), established in 1997, where currently he serves as director. He is the founder of the Computational Intelligence Laboratory (CI Lab), established in 2004 at the Department of Mathematics of University of Patras, where currently he serves as director.