Indian Institute of Technology Bhubaneswar

About: Indian Institute of Technology Bhubaneswar is a education organization based out in Bhubaneswar, India. It is known for research contribution in the topics: Large Hadron Collider & Computer science. The organization has 1185 authors who have published 3132 publications receiving 48832 citations.

On the dynamical downscaling and bias correction of seasonal‐scale winter precipitation predictions over North India

Abstract: This is the peer reviewed version of the following article: Tiwari, P. R., Kar, S. C., Mohanty, U. C., Dey, S., Sinha, P., Raju, P. V. S. and Shekhar, M. S., ‘On the dynamical downscaling and bias correction of seasonal-scale winter precipitation predictions over North India’, quarterly Journal of the Royal Meteorological Society, Vol. 142 (699):2398-2410, June 2016, which has been published in final form at DOI: https://doi.org/10.1002/qj.2832. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving. © 2016 Royal Meteorological Society

Query-Based Video Synopsis for Intelligent Traffic Monitoring Applications

Abstract: Synopsis of a long-duration video has many applications in intelligent transportation systems. It can help to monitor traffic with lesser manpower. However, generating meaningful synopsis of a long-duration video recording can be challenging. Often summarized outputs include redundant contents or activities that may not be helpful to the observer. Moving object trajectories are possible sources of information that can be used to generate the synopsis of long-duration videos. The synopsis generation faces challenges due to object tracking, grouping of the trajectories with respect to activity type, object category, and contextual information, and generating smooth synopsis according to a query. In this paper, we propose a method to generate meaningful and smooth synopsis of long-duration videos according to the users’ query. We have tracked moving objects and adopted deep learning to classify the objects into known categories (e.g., car, bike, and pedestrians). We then identify regions in the surveillance scene with the help of unsupervised clustering. Each tube (spatiotemporal object trajectory) is represented by the source and the destination. In the final stage, we take a query from the user and generate the synopsis video by smoothly blending the appropriate tubes over the background frame through energy minimization. The proposed method has been evaluated on two publicly available datasets and our own surveillance datasets. We have compared the method with popular state-of-the-art techniques. The experiments reveal that the proposed method is superior to the existing techniques and it produces visually seamless video synopsis.

Short communication: A robust evolutionary feedforward active noise control system using Wilcoxon norm and particle swarm optimization algorithm

Abstract: The conventional filtered-x least mean square (FxLMS) algorithm commonly employed for active noise control (ANC) is sensitive to disturbances acquired by the error microphone and yields poor performance in such scenario. To circumvent this problem, in this paper, a Wilcoxon FxLMS (WFxLMS) algorithm is proposed and used in the design of an efficient ANC which is robust to outliers in the secondary path and immune to burst noise acquired by the error microphone. It is demonstrated through simulation study that under such situation the proposed algorithm outperforms the traditional FxLMS algorithm. A particle swarm optimization (PSO) algorithm based robust ANC system, which does not require the modeling of the secondary path is also derived in the paper. Improved performance of the robust evolutionary ANC system over L2 norm based evolutionary ANC system is also shown.

A hybrid feature and discriminant classifier for high accuracy handwritten Odia numeral recognition

Abstract: Unconstrained handwritten character recognition is a major research area where there is a lot of scope for improving accuracy. There are many statistical, structural feature extraction techniques being proposed for different languages. Many classifier models are combined with these features to obtain high recognition rates. There still exists a gap between the recognition accuracy of printed characters and unconstrained handwritten scripts. Odia is a popular and classical language of the eastern part of India. Though the research in Optical Character Recognition (OCR) has advanced in other Indian languages such as Devanagari and Bangla, not much attention has been given to Odia character recognition. We propose a hybrid feature extraction technique using Kirsch gradient operator and curvature properties of handwritten numerals, followed by a feature dimension reduction using Principal Component Analysis (PCA). We use Modified Quadratic Discriminant Function (MQDF), Discriminative Learning Quadratic Discriminant Function (DLQDF) classifiers as they provide high accuracy of recognition and compare both the classifier performances. We verify our results using the Odia numerals database of ISI Kolkata. The recognition accuracy for Odia numerals with our proposed approach is found to be 98.5%.