Suma Dawn

Remote sensing image registration techniques: a survey

Image Registration is the first step towards using remote sensed images for any purpose. Despite numerous techniques being developed for image registration, only a handful has proved to be useful for registration of remote sensing images due to their characteristic of being computationally heavy. Recent flux in technology has prompted a legion of approaches that may suit divergent remote sensing applications. This paper presents a comprehensive survey of such literatures including recently developed techniques.

Advanced free-form deformation and Kullback–Lieblier divergence measure for digital elevation model registration

Registration is the process of transforming various images of the same object, place, etc. to confer one coordinate system, be they multimodal, multi-temporal of the same place or images of different places having certain common characteristics. Many methods have been tried for image registration; however, only a handful of methods may be said to work for digital elevation model (DEM) registration. The motivation of the present work is to perform a robust and efficient algorithm to perform Elevation model image registration. In this paper, we present a new approach for DEM registration, particularly for multimodal or multi-temporal DEMs. For time efficient, robust and precise registration of DEMs, a novel idea has been proposed using rational DMS-spline volumes (Xu et al. in J Comput Sci Technol 23(5):862–873, 1996; McDonnell and Qin in J Gr Tools 12(3):24–41, 2007) (the term DMS is acronym for the three authors, namely Dahmen et al. in Math Comput 59(199):97–115, 1997). This is based on the usage of arbitrary topology lattices (MacCracken and Joy in 23rd annual conference on computer graphics and interactive techniques proceedings. ACM-SIGGRAPH, pp 181–188, 1996; Feng et al. in Vis Comput Int Comput Gr 22(1):28–42, 2005). Using free-form deformation has lead to the usage of global and local transformations for registration of candidate image domain to reference image domain. Also, a similarity measure based on Kullback–Leibler divergence (KLD) has been used for measuring robustness of the method so proposed. The task of registration is achieved by minimizing the cost function using rational DMS-spline functions for local registration. After experimentations, the results show that the registration process, of registration of candidate DEM to reference DEM, could be completed successfully. Comparison of similarity measurement methods such as mutual information, correlation coefficient and peak signal-to-noise ratio with that of KLD-based has been performed. Comparative study with existing works suggests that the presented scheme is better, when compared with respect to above mentioned parameters.

Collaborative teaching in large classes of computer science courses

Collaborative teaching was applied by eight teachers for teaching nearly 700 students in four different sections of three different computer science courses with section strength varying from 120-240. Different forms of collaborative teaching were tried. Collaborative teaching at JIIT, Noida has turned out to be successful for large classes of the strength of 100 and above.

Corrective Self Defence Training Unit using sensing of Kinect Maps

In the sports fields and technology, the accuracy of an athlete can never be monitored with 100% accuracy with naked eyes. Moves that are done by an athlete or a sports person in the game such as his stride length and the stride frequency cannot be easily seen by a person and hence, detection and correction of the minute mistakes that are being made are overlooked. For instance, while doing push-ups a person‟s head, neck, waist and ankle should be in a single straight line. In this paper, we discuss a sports training system which uses Microsoft Kinect for motion sensing. The infrared depth stream translates the presence of a user in real world, into digital space by tracking his/her joint coordinates. As per our empirical studies, Kinect maps the x,y and z coordinates of 20 primary joints of the body. This data forms the basis of our calculations as elaborated in the literature. This work gives a basis of how movements and postures may be corrected by the use of sensors like Kinect in an effective and efficient manner. General Terms Kinect, Motion Sensing, Sports, Training, Sports Training, Gestures, HMM.

A Novel Non-rigid Free-form Deformation for Consistent Registration of Digital Elevation Models

The paper presents a novel non-rigid transformation for Digital Elevation Model (DEM) registration. This is based on symmetric diffeomorphic transformation which is inverse consistent as well. Registration allows for spatial alignments between the image pairs – reference and candidate images - under consideration and is necessary so that useful information can be integrated for further tasks. In general, DEM registrations task is to present a suitable transformation such that the candidate DEM becomes aligned to the reference DEM and that both may then be presented together. We have used modified B-spline based free-form deformation for non-rigid transformation using constrained parameters for making our model diffeomorphic and inverse consistent. It uses iterative learning for the formation of deformation model as per the proposed constraints. It has been able to map small scale as well as large scale deformations using the proposed technique and has been experimented with images having various terrain types. The proposed framework for the registration of DEMs has proven to be successful and gives favorable results when compared to existing techniques as well. The algorithm proposed in this literature has been tested for multimodal, multi-view, multi-temporal and multi-resolution images of the same area, and images having overlapping areas and also for existence of small holes and missing data. It has been extended to include not only a consitent single-reference-multiple-candidate registrations but also to find candidate DEMs for registration if not already provided.

Military Simulator - A Case Study of Behaviour Tree and Unity based architecture

paper we show how the combination of Behaviour Tree and Utility Based AI architecture can be used to design more realistic bots for Military Simulators. In this work, we have designed a mathematical model of a simulator system which in turn helps in analyzing the results and finding out the various spaces on which our favorable situation might exist, this is done geometrically. In the mathematical model, we have explained the matrix formation and its significance followed up in dynamic programming approach we explained the possible graph formation which will led improvisation of AI, latter we explained the possible geometrical structure of the matrix operations and its impact on a particular decision, we also explained the conditions under which it tend to fail along with a possible solution in future works.

Wearable Assistance Device for Visually Disabled

There are 37 million visually disable people in this world [1]. Advances in computer human interface and 3D world perception permit production of affordable and user friendly devices to assist the visually disabled [3]. This research paper presents a different approach in wearable computing using open source software and inexpensive hardware to assist the visually disabled section of population. General Terms Wearable Computing

Multimedia, animation, and computer graphics — Mapping of study of virtual characters to cognitive understanding

Seeing helps us understand better is an old saying. In engineering sciences, with the flurry of multimedia technologies, teaching and learning paradigms have shifted, problem-solving methods have evolved, optimization is the new buzzword and mathematical and scientific analyses have taken the front row for working. In this work we have explored the objectives of studying and understanding the elements and initial nuances of gaming; reasoning how the work created by students have helped them map to the concepts of computer graphics; studying the characterization of game movers; and studying the impact on learning using animation as a tool. These objectives have been studies using the case studies of games; and by designing and developing these games have assisted in the better perception of concepts of graphics and how tools can be used to present these ideas so as to make learning a passion rather than an anxiety.