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 & Higgs boson. The organization has 1185 authors who have published 3132 publications receiving 48832 citations.

Temporal Unknown Incremental Clustering Model for Analysis of Traffic Surveillance Videos

Abstract: Optimized scene representation is an important characteristic of a framework for detecting abnormalities on live videos. One of the challenges for detecting abnormalities in live videos is real-time detection of objects in a non-parametric way. Another challenge is to efficiently represent the state of objects temporally across frames. In this paper, a Gibbs sampling-based heuristic model referred to as temporal unknown incremental clustering has been proposed to cluster pixels with motion. Pixel motion is first detected using optical flow and a Bayesian algorithm has been applied to associate pixels belonging to a similar cluster in subsequent frames. The algorithm is fast and produces accurate results in $\Theta (kn)$ time, where $k$ is the number of clusters and $n$ the number of pixels. Our experimental validation with publicly available data sets reveals that the proposed framework has good potential to open up new opportunities for real-time traffic analysis.

COVID-19 lockdowns induced land surface temperature variability in mega urban agglomerations in India.

Abstract: The COVID-19 pandemic forced a nationwide lockdown in India for months when close to 1.3 billion people were confined to their homes. An abrupt halt in the majority of the urban activities reduced the generation of anthropogenic heat which often exacerbates the Urban Heat Island (UHI) effect in the urban pockets of the country. We studied the lockdown impact on seven highly populated and polluted mega urban agglomerations across India, namely Delhi, Ahmedabad, Hyderabad, Kolkata, Mumbai, Bengaluru and Chennai, using near-anniversary Landsat 8 data. The results revealed that the lockdowns have improved the air quality and reduced the Land Surface Temperature (LST) and hence the UHI effect over these cities. Each of the cities experienced an improved Air Quality Index (AQI) ranging from 18 to 151 units except Chennai (with a marginal 8 units increase in AQI), a decrease in mean LST in the range of 0.27 °C to 7.06 °C except Kolkata which showed an increment by ∼4 °C, and a reduction in daily averaged air temperature ranging from 0.3 °C to 10.88 °C except Hyderabad which witnessed an increase of 0.09 °C during the lockdown (April 2020) compared to the previous years (April 2019 and 2018). Delhi exhibited the maximum positive impact of the lockdown in all aspects with two-fold improved air quality, and Ahmedabad showed the least improvement. In addition to the variations in regional land use and land cover and proportion of essential industries that remained operational throughout the lockdown, the geographic location, topography, local meteorology and climate were some of the other factors also responsible for either aiding or overcompensating the large scale LST variabilities observed in these cities. These results hint at an unprecedented opportunity to evaluate the effectiveness of periodic planned lockdowns as a possible mitigating measure to reduce LST spikes and degraded air quality in urban areas in the future.