Nalini N

Prahlad Anand, Qiranul Saadiyean, Aniruddh Sikdar et al.

This study aims to learn a translation from visible to infrared imagery, bridging the domain gap between the two modalities so as to improve accuracy on downstream tasks including object detection. Previous approaches attempt to perform bi-domain feature fusion through iterative optimization or end-to-end deep convolutional networks. However, we pose the problem as similar to that of image translation, adopting a two-stage training strategy with a Generative Adversarial Network and an object detection model. The translation model learns a conversion that preserves the structural detail of visible images while preserving the texture and other characteristics of infrared images. Images so generated are used to train standard object detection frameworks including Yolov5, Mask and Faster RCNN. We also investigate the usefulness of integrating a super-resolution step into our pipeline to further improve model accuracy, and achieve an improvement of as high as 5.3% mAP.

Keenu Chandra, Maroof Mushtaq, Nalini N

Blockchain is currently one of the fastest-growing technologies in the field of Computer Science. It has found a prevalent use in financial applications like cryptocurrency, for example, Bitcoin and Ethereum. They have been able to bring an unforeseen disruption in the field of finance. However, permissionless Blockchains like these have some downsides, namely the computation cost of the Proof of Work algorithm, maximum allowed size for a block, decrease in intelligibility with the increase of the number of blocks in the chain, domination of nodes with higher computing power as miners and validators. These factors have restricted the adoption of permissionless blockchain technology outside the field of finance, such as in medical or legal fields. This paper proposes a solution to these problems using a permissioned blockchain. It does not require a computationally expensive consensus mechanism as permissioned chains call for trust between participating organizations which is achieved via exclusive invitations. We have utilized a third-party orderer to maintain the trust between organizations.