Search

For accessing images from huge repository in an easy manner, the images are required to be properly indexed. Content-Based Image Retrieval (CBIR) is a field which deals with finding solutions to such problems. This paper proposes a new multiresolution descriptor namely, Local Derivative Laplacian Co-occurrence Pattern (LDLCP) for CBIR. Gray level image is subjected to four-level Laplacian of Gaussian filtering in order to perform multiresolution processing of image. Local Derivative Pattern descriptors of resulting four-level filtered image is computed to extract local information from the image. Finally, the Gray-Level Co-occurrence Matrix is used for constructing feature vector. Corel-1K and Corel-5K datasets have been used to test the proposed descriptor and its performance is measured using precision and recall metrics.

The scope of unmanned aerial vehicles (UAVs), also known as “drone technology,” is increasing, with various applications in the field of remote sensing and environment. UAVs not only provide high-resolution, real-time data, but also have different applications for end users. They have become an essential tool for land surveyors because traditional land survey methods are expensive and time-consuming, requiring trained professionals and many hours to measure a single plot of land. With the advancement of UAVs, we can significantly reduce the cost. In this study, we have collected UAV data in Malaysia to acquire information about the plantation management practices, as well as oil palm health assessment. Our results showed that multispectral data collected from a UAV-borne MicaSense RedEdge camera is useful for identifying physiological stress in mature oil palm plants, which clearly illustrates stunted tree crown with low value of normalized difference vegetation index (NDVI).

The advent of low-cost cameras and smartphones have made the task of image capturing quite easy nowadays. This has resulted in the collection of large number of unorganized images. Accessing images from large repository of unorganized images is quite challenging. There is a need of such systems which help in proper organization and easy access of images. The field of image retrieval, using text or image, attempts to solve this problem. While text-based retrieval systems are quite popular, they suffer from certain drawbacks. The other type of image retrieval system, which is Content-based Image Retrieval (CBIR) system, uses image features to search for relevant images. This chapter discusses the concept multiresolution feature descriptors for CBIR. For capturing varying level of details, single resolution processing of image proves to be insufficient. The use of multiresolution descriptors prove to be quite efficient in capturing complex foreground and background details in an image. This chapter discusses the important properties and advantages of multiresolution feature descriptors. Furthermore, this chapter proposes a CBIR technique using a novel multiresolution feature descriptor. The proposed method constructs feature vector by capturing shape feature in a localized manner. The experimental results show the effectiveness of the proposed method.

When a disease outbreaks in a population the information about disease prevalence induces behaviour changes in the susceptible population. This causes the susceptible individuals to adopt protective and precautionary measures. Thus this fraction of susceptible population may be virtually immune to the infection for some time. As the immunity degrades with passage of time, a time delay in waning of immunity is also accounted in the model. Thus, in this study, a delay differential equation model for the dynamics of infectious diseases is proposed and analysed which accounts for the effect of information on the susceptible population. The model analysis is carried out and it is found that the disease free equilibrium exists unconditionally, whereas a unique infected equilibrium is obtained when the basic reproduction number (R0) is greater than one. Also, the disease free equilibrium is locally stable independent of delay when R0 1, the model exhibits rich and complex dynamics in presence of time delay. The occurrence of oscillatory behaviour of the population around the infected equilibrium via Hopf bifurcation is observed analytically. Numerical simulation is performed to discuss and analyse the analytical results.

Due to the availability of large number of digital images, development of an efficient content-based indexing and retrieval method is required. This paper proposes a moment based image retrieval method. Image is divided into blocks and geometric moment of each block is calculated followed by computation of distance between block moments of query image and database images. Then threshold, using distance values, is applied to retrieve images similar to the query image. Performance of the proposed method is compared with other state-of-the-art image retrieval methods on the basis of results obtained on Corel-1000 database. The comparison shows that the proposed method gives better results in terms of precision and recall as compared to the other image retrieval methods.

Introduction.- Remote sensing-based determination of conifer needle flushing phenology over boreal-dominant regions.- Information System for Integrated Watershed Management using Remote Sensing and GIS.- Sensitivity Exploration of SimSphere Land Surface Model Towards its Use for Operational Products Development from Earth Observation Data.- Remote estimation of land surface temperature for different LULC features of a moist deciduous tropical forest region.- Geospatial Strategy for Estimation of Soil Organic Carbon in Tropical Wildlife Reserve.- A Comparative Assessment Between the Application of Fuzzy Unordered Rules Induction Algorithm and J48 Decision Tree Models in spatial Prediction of Shallow Landslides at Lang Son City, Vietnam.

Newly emerged hyperspectral techniques make it possible to acquire images in narrow and continuous spectral bands, providing significant improvements when compared with broad bands. In this work total chlorophyll, chlorophyll-a and chlorophyll-b were estimated, which have been used to find an empirical relationship with the hyperspectral data. The vegetation indices used in this study are Red Edge Inflection Point (REIP), Normalized Difference Vegetation Index (NDVI), Soil Adjustment Vegetation Index (SAVI) and Structure Insensitive Pigment Index (SIPI). These indices were calculated on the first derivative of reflectance obtained from the field. The REIP value was calculated using a four point interpolation technique. The REIP value for fertilizer plots was found higher than for control, indicating a better health of crop in the fertilizer plots. Stepwise regression analysis was employed to estimate the linear regression algorithm for chlorophyll retrieval. The analysis shows that REIP and NDVI served as best predictor for total chlorophyll and chlorophyll-b estimation, while REIP was found suitable for Chlorophyll-a estimation. A global sensitivity analysis method was developed to estimate the uncertainty associated with the proposed chlorophyll retrieval algorithms.

Flooding is one of the severe disaster causes mass demolition of properties and affected human lives. In hazardous flood of year 2006, 90–95 % of Surat city, India, was under water and so that local planner as well as decision makers need accurate information on the spatial distribution, magnitude, depth of flooding and land use affected by such floods. Surat city is majorly partitioned into seven different zones named north zone, east zone, central zone, south zone, south-east zone, south-west zone, and west zone. Purpose of this study is to determine inundation of water in low laying areas of west zone. By procedure of Geo-reference along with Ground Control Point (GCP) and GPS points, 0.5 m interval contour map for west zone is introduced. Digitization of contour through GIS software and Digital Elevation Model (DEM) of West Zone through ArcGIS software is carried out. Probable submergence area for rescue work is also scrutinized. Graph of submergence area of West Zone according Town Planning Scheme (TPS) versus water level and flood Inundation map are generated which specify that West Zone and its TPS are low lying areas in Surat whose 20–25 km2 area will be submerge when water level exceeds 12 m height (MSL). The accuracy and validation of DEM is calculated by comparison with actual observed data at the time of flooding.

Recent advances in remote sensing can map the lithological and geological parameters in a synoptic way and hence opens up new dimensions in archaeological research. This work delineates accurate mappings of sandstone located and documented in the form of a suite of prehistoric rock-shelter sites in the Mirzapur district of Central India. Artificial Neural Network (ANN) and Maximum Likelihood Classification (MLC) techniques have been used to identify, classify and map the region under study using IRS-P6 Advanced Wide Field Sensor (AWiFS). Interpretation of data processing revealed that ANN performed better than MLC for mapping sandstone in and around the area of Mirzapur. A conspicuous pattern has been detected where the painted sandstone shelters followed the natural sandstone or host-rock formations revealing the painting activity. This demonstrates prehistoric social choice in terms of the production and consumption of rock art and the importance of local geology that governs this activity.