Arbind Agrahari Baniya

System Development Researcher (Signal Processing and Analysis; Computing and Processing; Components, Circuits, Devices and Systems)

Melbourne, Australia

Researcher with skills and interests in Computer Vision, Machine Learning, Data Science, and Data-Centric Smart Solutions for addressing real-world issues. Currently responsible for project planning, requirement elicitation, solution design and development for bee-to-tree pollination traceability solutions at Ag Vic Research, focusing on data standards, data exchanges between integrated systems and data pipelines using microservices in cloud infrastructure. Also, undertaking Ph.D. research in Computer Vision, specifically on deep learning-based quality enhancement of different forms of visual signals, including emerging immersive multimedia, working with big data, high-performance computing, empirical evaluation and analysis, and algorithm design and development. Passionate about contributing to the development of data-driven and smart solutions for various domains and industries, particularly with an agricultural focus and to help advance the state-of-the-art.


  • Improved histogram-based anomaly detector with the extended principal component features
  • A Novel Data Pre-processing Technique: Making Data Mining Robust to Different Units and Scales of Measurement
  • IRRISENS: An IoT Platform Based on Microservices Applied in Commercial-Scale Crops Working in a Multi-Cloud Environment
  • Self-Healing Systems: Through Autonomic Computing
  • SPAD+: An Improved Probabilistic Anomaly Detector based on One-dimensional Histograms
  • STIFS: Spatio-Temporal Input Frame Selection for Learning-based Video Super-Resolution Models
  • Omnidirectional Video Super-Resolution using Deep Learning
  • Online Video Super-Resolution using Unidirectional Recurrent Model
  • Spatiotemporal Dynamics and Frame Features for Improved Input Selection in Video Super-Resolution Models
  • Online Video Super-Resolution using Information Replenishing Unidirectional Recurrent Model
  • Current State, Data Requirements and Generative AI Solution for Learning-based Computer Vision in Horticulture
  • A Methodical Study of Deep Learning Based Video Super-Resolution
  • A Data Ecosystem for Orchard Research and Early Fruit Traceability
  • Frame Selection Using Spatiotemporal Dynamics and Key Features as Input Pre-processing for Video Super-Resolution Models
  • Omnidirectional Video Super-Resolution Using Deep Learning
  • Online Video Super-resolution using Information Replenishing Unidirectional Recurrent Model
  • Requirements engineering framework for human-centered artificial intelligence software systems
  • Enabling clustering algorithms to detect clusters of varying densities through scale-invariant data preprocessing
  • A Survey of Deep Learning Video Super-Resolution

Arbind Agrahari Baniya's public data