Detection of rows in crops planted as rows is fundamental to site specific management of agricultural farms. Unmanned Aerial Vehicles are increasingly being used for agriculture applications. Images acquired using Low altitude remote sensing is analysed. In this paper we propose the detection of rows in an open field tomato crop by analyzing images acquired using remote sensing from an Unmanned Aerial Vehicle. The Unmanned Aerial Vehicle used is a quadcopter fitted with an optical sensor. The optical sensor used is a vision spectrum camera. Spectral-spatial methods are applied in processing the images. K-Means clustering is used for spectral clustering. Clustering result is further improved by using spatial methods. Mathematical morphology and geometric shape operations of Shape Index and Density Index are used for spatial segmentation. Six images acquired at different altitudes are analysed to validate the robustness of the proposed method. Performance of row detection is analysed using confusion matrix. The results are comparable for the diverse image sets analyzed. 

Real-time object tracking is one of the most crucial tasks in the field of computer vision. Many different approaches have been proposed and implemented to track an object in a video sequence. One possible way is to use mean shift algorithm which is considered to be the simplest and satisfactorily efficient method to track objects despite few drawbacks. This paper proposes a different approach to solving two typical issues existing in tracking algorithms like mean shift: (1) adaptively estimating the scale of the object and (2) handling occlusions. The log likelihood function is used to extract object pixels and estimate the scale of the object. The Extreme learning machine is applied to train the radial basis function neural network to search for the object in case of occlusion or local convergence of mean shift. The experimental results show that the proposed algorithm can handle occlusion and estimate object scale effectively with less computational load making it suitable for real-time implementation.

In this paper, urban growth of Bangalore region is analyzed and discussed by using multi-temporal and multi-spectral Landsat satellite images. Urban growth analysis helps in understanding the change detection of Bangalore region. The change detection is studied over a period of 39 years and the region of interest covers an area of 2182 km2. The main cause for urban growth is the increase in population. In India, rapid urbanization is witnessed due to an increase in the population, continuous development has affected the existence of natural resources. Therefore observing and monitoring the natural resources (land use) plays an important role. To analyze changed detection, researcher’s use remote sensing data. Continuous use of remote sensing data helps researchers to analyze the change detection. The main objective of this study is to monitor land cover changes of Bangalore district which covers rural and urban regions using multi-temporal and multi-sensor Landsat - multi-spectral scanner (MSS), thematic mapper (TM), Enhanced Thematic mapper plus (ETM+) MSS, TM and ETM+ images captured in the years 1973, 1992, 1999, 2002, 2005, 2008 and 2011. Temporal changes were determined by using maximum likelihood classification method. The classification results contain four land cover classes namely, built-up, vegetation, water and barren land. The results indicate that the region is densely developed which has resulted in decrease of water and vegetation regions. The continuous transformation of barren land to built-up region has affected water and vegetation regions. Generally, from 1973 to 2011 the percentage of urban region has increased from 4.6% to 25.43%, mainly due to urbanization.

In this paper, we have proposed an Automatic Aerial Video Processing System for analyzing land surface features. Analysis of aerial video is done in three steps a) Image pre-processing b) Image registration and c) Image segmentation. Using the proposed system, we have identified Land features like Vegetation, Man-Made Structures and Barren Land. These features are identified and differentiated from each other to calculate their respective areas. Most important feature of this system is that it is an instantaneous video acquisition and processing system. In the first step, radial distortions of image are corrected using Fish-Eye correction algorithm. In the second step, the image features are matched and then images are stitched using Scale Invariant Feature Transform (SIFT) followed by Random Sample Consensus (RANSAC) algorithm. In the third step, the stitched images are segmented using Mean Shift Segmentation and different structures are identified using RGB model. Here we have used a hybrid system to identify Man-Made Structures using Fuzzy Edge Extraction along with Mean Shift segmentation. The results obtained are compared with the ground truth data, thus evaluating the performance of the system. The proposed system is implemented using Intel's OpenCV.

Visual cryptography is considered to be a vital technique for hiding visual data from intruders. Because of its importance, it finds applications in various sectors such as E-voting system, financial documents and copyright protections etc. A number of methods have been proposed in past for encrypting color images such as color decomposition, contrast manipulation, polynomial method, using the difference in color intensity values in a color image etc. The major flaws with most of the earlier proposed methods is the complexity encountered during the implementation of the methods on a wide scale basis, the problem of random pixilation and insertion of noise in encrypted images. This paper presents a simple and highly resistant algorithm for visual cryptography to be performed on color images. The main advantage of the proposed cryptographic algorithm is the robustness and low computational cost with structure simplicity. The proposed algorithm outperformed the conventional methods when tested over sample images proven using key analysis, SSIM and histogram analysis tests. In addition, the proposed method overshadows the standard method in terms of the signal to noise ratio obtained for the encrypted image, which is much better than the SNR value obtained using the standard method. The paper also makes a worst case analysis for the SNR values for both the methods.

Image compression is the methodology of reducing the data space required to store an image or video. It finds great application in transferring videos and images over the web to reduce data transfer time and resource consumption. A number of methods based on DCT and DWT have been proposed in the past like JPEG, MPEG, EZW, SPIHT etc. The paper presents a review comparison between DCT and DWT compression techniques based on multiple important evaluation parameters like (i) mean squared error and SNR for different threshold values (ii) SNR values and mean squared error for different coefficients (iii) SNR values and mean squared error for different window size. In addition, the paper also makes two advanced studies (i) CPU utilization and compression ratio for different window sizes (ii) SNR and compression with different compression ratio. The experimentation is performed on multiple 8x8 jpeg images.