Defence Terrain Research Laboratory

Delhi, India

Defence Terrain Research Laboratory

Delhi, India
Time filter
Source Type

Chaturvedi P.,Defence Terrain Research Laboratory | Srivastava S.,Defence Terrain Research Laboratory | Kaur P.B.,Thapar University
Advances in Intelligent Systems and Computing | Year: 2017

Rainfall induced landslides account for over 200 deaths and loss of over Rs.550 crores annually in Himalaya. Literature suggests sensors based site specific Early Warning System (EWS) to be feasible and economic to curtail losses due to landslides for high risk areas. Area selected for current study is Tangni landslide located in Chamoli district of Uttarakhand state, India due to high anticipated risk to the local community residing nearby. For realization of EWS, a near real time instrumentation setup was installed on the slope. The setup measures pore water pressure, sub-surface deformations, and surface displacements along with rainfall. Regression analysis models are developed using antecedent rainfall and deformation data which are further used to find out thresholds for sensors based on z-scores. In future using the results from the sensors installed in the field and laboratory characterizations, numerical analyses will be applied to develop a process based model. © Springer Nature Singapore Pte Ltd. 2017.

Jaimini U.,Lakshmi Niwas Mittal Institute of Information Technology | Panchal V.K.,Defence Terrain Research Laboratory
Proceedings - 2013 International Conference on Emerging Trends in Communication, Control, Signal Processing and Computing Applications, IEEE-C2SPCA 2013 | Year: 2013

Swarm Intelligence has emerged as an important technique among various computational techniques due to its effieciency and robustness of the solution. The authors have categorized the different swarm intelligence techniques based on the agents population involved and on space-time variation to get an optimal solution to a problem. © 2013 IEEE.

Arora G.,Banasthali University | Rana S.,Manipal University India | Panchal V.K.,Defence Terrain Research Laboratory
ICROIT 2014 - Proceedings of the 2014 International Conference on Reliability, Optimization and Information Technology | Year: 2014

The main motive of Ant Colony Optimization (ACO) is to find the shortest path from the ants' nest to the food source by sensing the amount of pheromone (a chemical secreted by ants which is used as the communication system) on the different paths available. In this paper, we propose a novel methodology which solves the problem of an ant facing an obstacle in its path from the nest to the food source, in which case the conventional ACO may fail. This work proposes a modified ant colony optimization by introducing the concept of perception radius, for enabling the ants to find the path to the food source even if there is any break in the pheromone trail. The Travelling Salesman Problem, as an example, is solved using the proposed modified ACO and the results obtained are compared with Dijkstra's algorithm. It is clearly demonstrated that our methodology not only works well when breaks or hurdles are encountered by ants but also provides efficient results. © 2014 IEEE.

Gupta N.,Bhagwan Parshuram Institute of Technology | Panchal V.K.,Defence Terrain Research Laboratory
International Geoscience and Remote Sensing Symposium (IGARSS) | Year: 2011

Mixed pixels are usually the biggest reason for lowered success in classification accuracy. Aiming at the characteristics of remote sensing image classification, the mixed pixel problem is one of the main factors that affect the improvement of classification precision in image. How to decompose the mixed pixels precisely and effectively for multispectral/hyper spectral remote sensing images is a critical issue for the quantitative research. As Remote sensing data is widely used for the classification of types of land cover such as vegetation, water body thus Conflicts are one of the most characteristic attributes in satellite multilayer imagery. Conflict occurs in tagging class label to mixed pixels that encompass spectral response of different land cover on the ground element. In this paper we attempted to present a new approach for resolving the mixed pixels using Biogeography based optimization. The paper deals with the idea of tagging the mixed pixel to a particular class by finding the best suitable class for it using the concept of immigration and emigration. © 2011 IEEE.

Goel S.,University of Delhi | Sharma A.,University of Delhi | Panchal V.K.,Defence Terrain Research Laboratory
Communications in Computer and Information Science | Year: 2011

Remote sensing is the most relevant science that permits us to acquire information about the surface of the land, without having actual contact with the area being observed. Amongst the multiple uses of remote sensing, one of the most important has been its use in solving the problem of land cover mapping. Multi spectral classification of remotely sensed data has been widely used to generate thematic Land-Use/Land-Cover maps. Two of the extensively used algorithms for image classification are Self Organizing Feature Maps (SOFM) and Ant Colony Optimization. Although both are bio-inspired optimization techniques, however combining them is a challenging task, especially in the field of remote sensing. In this paper, we have used a Self Organizing Ant Algorithm for Classification of remotely sensed data. Also, we have suggested a new reinforcement factor for the pheromone updation. A test of algorithm is conducted by classifying a high resolution, multi-spectral satellite image of Alwar Region. Results obtained are encouraging. © 2011 Springer-Verlag Berlin Heidelberg.

Sam L.,Defence Terrain Research Laboratory | Gahlot N.,Defence Terrain Research Laboratory | Prusty B.G.,Defence Terrain Research Laboratory
Arabian Journal of Geosciences | Year: 2015

The main objectives of this study were to estimate the dune celerity and sand flux in an arid environment (Gadra in Barmer District in Thar Desert, Rajasthan, India) using multi-temporal remote sensing data. Dunal shift estimation and interdunal space estimation, which are crucial for calculating sand flux, were also performed. We applied this method to two Cartosat-1 scenes (stereopairs) of years 2010 and 2011. Co-registration of Optically Sensed Images and Correlation was utilized to meet the above mentioned objectives. The mean dune shift for the study area for a year was estimated to be 1.25 m. Mean dune celerity was estimated as 0.0034 m/day or 1.24 m/year. Mean sand flux was estimated to be 0.0156 or 5.69 m3/m/year. Based on the results of the dune migration pattern, the co-registration accuracy was found to be 0.70 pixels, wherein the pixel resolution of input data was 2.50 m. This indicates that the root mean square error (RMSE) is about 1.60 m. However, our results demonstrated that dune celerity is 1.24 m per annum, which is within the RMSE level of the analysis. Therefore, this corroborates with the results that during the approximately 1-year time period, there is no apparent movement of the sand dunes in the study area. © 2013, Saudi Society for Geosciences.

Mangai U.G.,Indian Institute of Technology Madras | Samanta S.,Indian Institute of Technology Madras | Das S.,Indian Institute of Technology Madras | Chowdhury P.R.,Defence Terrain Research Laboratory
IETE Technical Review (Institution of Electronics and Telecommunication Engineers, India) | Year: 2010

For any pattern classification task, an increase in data size, number of classes, dimension of the feature space, and interclass separability affect the performance of any classifier. A single classifier is generally unable to handle the wide variability and scalability of the data in any problem domain. Most modern techniques of pattern classification use a combination of classifiers and fuse the decisions provided by the same, often using only a selected set of appropriate features for the task. The problem of selection of a useful set of features and discarding the ones which do not provide class separability are addressed in feature selection and fusion tasks. This paper presents a review of the different techniques and algorithms used in decision fusion and feature fusion strategies, for the task of pattern classification. A survey of the prominent techniques used for decision fusion, feature selection, and fusion techniques has been discussed separately. The different techniques used for fusion have been categorized based on the applicability and methodology adopted for classification. A novel framework has been proposed by us, combining both the concepts of decision fusion and feature fusion to increase the performance of classification. Experiments have been done on three benchmark datasets to prove the robustness of combining feature fusion and decision fusion techniques.

Kumar A.,The LNM Institute of Information Technology | Panchal V.K.,Defence Terrain Research Laboratory
Proceedings of ICCCS 2014 - IEEE International Conference on Computer Communication and Systems | Year: 2014

Discretization of continuous features is both a requirement and a way of performance enhancement for many machine learning algorithms. In this paper, we review previous work on continuous feature discretization, apply different discretization algorithms for image classification of a satellite remote sensing image and conduct an empirical evaluation of several methods. © 2014 IEEE.

Gupta S.,Jaypee Institute of Information Technology | Arora A.,Jaypee Institute of Information Technology | Panchal V.K.,Defence Terrain Research Laboratory | Goel S.,University of Delhi
Communications in Computer and Information Science | Year: 2011

Remote sensing image classification in recent years has been a proliferating area of global research for obtaining geo-spatial information from satellite data. In Biogeography Based Optimization (BBO), knowledge sharing between candidate problem solutions or habitats depends on the migration mechanisms of the ecosystem. In this paper an extension to Biogeography Based-Optimization is proposed for image classification by incorporating the non-linear migration model into the evolutionary process. It is observed in recent literature that sinusoidal migration curves better represent the natural migration phenomenon as compared to the existing approach of using linear curves. The motivation of this paper is to apply this realistic migration model in BBO, from the domain of natural computing, for natural terrain features classification. The adopted approach calculates the migration rate using Rank- based fitness criteria. The results indicate that highly accurate land-cover features are extracted using the extended BBO technique. © 2011 Springer-Verlag.

Jaimini U.,Lakshmi Niwas Mittal Institute of Information | Panchal V.K.,Defence Terrain Research Laboratory
ICROIT 2014 - Proceedings of the 2014 International Conference on Reliability, Optimization and Information Technology | Year: 2014

In Swarm Intelligence, every single agent works in a group as a system to solve a problem. There is no centralized force governing the system. Each agent uses its own wisdom to work and collaborate with its fellow agents to constitute a swarm intelligence. Therefore, wisdom plays a key role in swarm intelligence. Without wisdom problem solving is an impossible task in every domain of life. This combination of Wisdom and Swarm is known as WisSwarm (Wisdom in Swarm) © 2014 IEEE.

Loading Defence Terrain Research Laboratory collaborators
Loading Defence Terrain Research Laboratory collaborators