Aryan's research while affiliated with Chandigarh University and other places

Indoor relocalization is vital for both robotic tasks like autonomous exploration and civil applications such as navigation with a cell phone in a shopping mall. Some previous approaches adopt geometrical information such as key-point features or local textures to carry out indoor relocalization, but they either easily fail in an environment with visually similar scenes or require many database images. Inspired by the fact that humans often remember places by recognizing unique landmarks, we resort to objects, which are more informative than geometry elements. In this work, we propose a simple yet effective object-based indoor relocalization approach, dubbed AirLoc. To overcome the critical challenges of object reidentification and remembering object relationships, we extract object-wise appearance embedding and inter-object geometric relationships. The geometry and appearance features are integrated to generate cumulative scene features. This results in a robust, accurate, and portable indoor relocalization system, which outperforms the state-of-the-art methods in room-level relocalization by 9.5% of PR-AUC and 7% of accuracy. In addition to exhaustive evaluation, we also carry out real-world tests, where AirLoc shows robustness in challenges like severe occlusion, perceptual aliasing, viewpoint shift, and deformation.

COVID-19 originated in Wuhan, China, in December 2019, and there have been over 464.5 million infected cases, and 6.08 million individuals have died worldwide. Effective detection of COVID-19 has been an essential task for stopping its quick spread and ultimately saving precious lives. This paper considers radiological examination using chest X-rays as patients with COVID-19 infections are likely to be adequately recognized using chest radiography pictures. Although many machine learning/deep learning techniques have been developed, their approach is likely to suffer problems like generalization error, high variance, overfitting, etc., due to limited dataset size. By producing predictions with numerous models rather than only one model, the ensemble model can overcome the disadvantages of deep learning. So, in this paper, we propose an ensemble deep learning method for detecting COVID-19 using chest X-ray images. On a combination of DenseNet, InceptionV3, and MobileNet, we got the best validation accuracy of 96.20% and testing accuracy of 92.45%. We hope this approach will help detect COVID-19 early and reduce further spread.