https://dspace.iiti.ac.in:8080/jspui/handle/123456789/9660 2026-05-12T17:06:10Z https://dspace.iiti.ac.in:8080/jspui/handle/123456789/13344 Title: On ground objectiIdentification using drones Authors: Gupta, Rahul Kumar; Singh, Abhinoy Kumar [Guide] Abstract: The field of drones and object tracking and detection is vast. It is a computer technology related to computer vision and image processing which detects certain semantics objects from a certain set of classes in digital images and videos. It has a wide area of applications including video surveillance, mapping , image retrieval etc. Many active research is still going on this field and it is continuously evolving .The technology of drones is in high demand today as its usage and applications are increasing day by day. Many countries are investing heavily in drone technology for its military and civil purposes .This report will give a brief idea of algorithms used for object tracking and detection, drone hardware and its related setup and software. 2022-11-30T00:00:00Z https://dspace.iiti.ac.in:8080/jspui/handle/123456789/13343 Title: On ground objectiIdentification using drones Authors: Kumar, Shri Krishan; Singh, Abhinoy Kumar [Guide] Abstract: The field of drones and object tracking and detection is vast. It is a computer technology related to computer vision and image processing which detects certain semantics objects from a certain set of classes in digital images and videos. It has a wide area of applications including video surveillance, mapping , image retrieval etc. Many active research is still going on this field and it is continuously evolving .The technology of drones is in high demand today as its usage and applications are increasing day by day. Many countries are investing heavily in drone technology for its military and civil purposes .This report will give a brief idea of algorithms used for object tracking and detection, drone hardware and its related setup and software. 2022-11-30T00:00:00Z https://dspace.iiti.ac.in:8080/jspui/handle/123456789/10419 Title: Time series classification in resource constrained environments Authors: Bhanushali, Krishna; Srivastava, Abhishek [Guide] Abstract: The analysis of time series is becoming prevalent across various scientific and engineering disciplines, where the e↵ectiveness and scalability of time series mining techniques depend on the design choices made while representing, indexing and comparing the time series. A lot of the existing algorithms in the field of time series classification can be resource intensive, making it difficult to apply them in an IoT environment, where we have several constraints on resources, with the need to process data being streamed from multiple sensors at the same time. The primary aim of this project is to implement an online time series classification algorithm which can work even in constrained environments. Keywords: Time Series Vectors, Classification, Clustering 2022-05-26T00:00:00Z https://dspace.iiti.ac.in:8080/jspui/handle/123456789/10418 Title: Fingerprint matching using a deep learning based approach Authors: Patel, Smit; Surya Prakash [Guide] Abstract: As we move towards a technological driven era, the traditional methods of data or personnel verification are becoming redundant and easier to crack. Biometric authentication has emerged as a very promising technique as it uses features of human body which are unique to every individual. In an effort to adopt recent developments in Machine Learning (ML) and Natural Language Processing (NLP) and apply them to the domain of biometric verification, I propose a novel Vision Transformer (ViT) based Siamese Network (SN) framework for fingerprint match ing. Our primary focus is holistic and a end-to-end pipeline has been constructed and implemented using an ensemble of task-specific algorithms to procure the best possible result from the model. I have also endeavoured to identify specific problems on the application of ViT to our problem statement and introduced two major mod ifications, Shifted Patch Tokenization (SPT) and Localized Self Attention (LSA) to tackle those shortcomings effectively. I propose two variations for the model, namely Intermediate-Merge (IM) Siamese Network and Late Merge (LM) Siamese Network and test the performances on a fingerprint dataset from IIT Kanpur. Keywords: Fingerprint Matching, Vision Transformer, Siamese Networks, Deep Learning 2022-05-27T00:00:00Z