Muhammad Moosa
About
Muhammad Moosa is a researcher at NTNU, where he contributes to the national PheNo infrastructure focused on AI-driven plant phenotyping. His work involves designing and implementing machine learning and computer vision models for high-resolution imaging data, including drone, LiDAR, and multispectral sources, to accelerate plant breeding and climate adaptation research. Alongside research, he has worked as a backend developer, specializing in Python, FastAPI, REST APIs, and Dockerized deployments, with additional experience in authentication, containerization, and scalable database design.
He has co-authored publications in Computers in Biology and Medicine (Elsevier, IF 7.7) and presented at international conferences such as IPTA and AIAI, with a focus on self-supervised learning, detection, and tracking. His technical expertise spans object detection (YOLO-X, EfficientDet, YOLO-NAS), object tracking (SORT, ByteTrack, DeepSORT), and backend engineering.
Background
-
BS (Software Engineering) – Sukkur IBA University, Pakistan (2017–2021)
- MS (Applied Computer Science) – Norwegian University of Science and Technology (NTNU), Norway (2022–2024)
Research Interests
-
Computer vision (object detection, tracking, re-identification)
-
AI-driven plant phenotyping and precision agriculture
-
Deep learning, self-supervised learning, model optimization
Teaching
- Artificial Intelligence (PROG2051) – Student Assistant (Spring 2023 & 2024)
- Database Management Systems (IDATG2204) – Student Assistant (Spring 2023)
- Back-end Web Development (IDG2003) – Student Assistant (Autumn 2023)
- Programming and Numerics (TDT4127) – Student Assistant (Autumn 2023)
Research
This project aims to build a national infrastructure for plant phenotyping. Plant phenotyping is the description and characterization of complex plant traits using non-destructive image analysis-based tools. Phenotyping is currently a major bottleneck in plant science, agronomy and plant breeding.
The PheNo infrastructure addresses several priorities in the Strategies for National Bioresource Infrastructure in Norway, including adaptation to climate change, the needs for a green transition and the integration of new technologies, digitalization, automation and robotization. By providing state-of-the-art, unique plant phenotyping facilities to support the needs of research and education in Norway, the PheNo infrastructure will enable faster breeding of new varieties and sustainable production systems adapted to the changing Norwegian climate, based on innovations in genetics, phenomics and the integration of robotics and data science.
Norway will now join several European countries that have established national phenotyping platforms, and PheNo will become a Norwegian node in the European Strategic Forum for Research Infrastructure (ESFRI) roadmap project EMPHASIS (European Infrastructure for multi-scale Plant Phenomics and Simulation for food security in a changing climate) and provide opportunities for phenotyping under the unique Nordic growing conditions at high latitudes.
Publications
2024
-
Moosa, Muhammad;
Yamin, Muhammad Mudassar;
Hashmi, Ehtesham;
Beghdadi, Azeddine Boutkhil;
Imran, Ali Shariq;
Cheikh, Faouzi Alaya.
(2024)
SMT: Self-supervised Approach for Multiple Animal Detection and Tracking.
IFIP Advances in Information and Communication Technology
Academic article
2023
-
Ali, Subhan;
Akhlaq, Filza;
Imran, Ali Shariq;
Kastrati, Zenun;
Daudpota, Sher Muhammad;
Moosa, Muhammad.
(2023)
The enlightening role of explainable artificial intelligence in medical & healthcare domains: A systematic literature review.
Computers in Biology and Medicine
Academic literature review
Journal publications
-
Moosa, Muhammad;
Yamin, Muhammad Mudassar;
Hashmi, Ehtesham;
Beghdadi, Azeddine Boutkhil;
Imran, Ali Shariq;
Cheikh, Faouzi Alaya.
(2024)
SMT: Self-supervised Approach for Multiple Animal Detection and Tracking.
IFIP Advances in Information and Communication Technology
Academic article
-
Ali, Subhan;
Akhlaq, Filza;
Imran, Ali Shariq;
Kastrati, Zenun;
Daudpota, Sher Muhammad;
Moosa, Muhammad.
(2023)
The enlightening role of explainable artificial intelligence in medical & healthcare domains: A systematic literature review.
Computers in Biology and Medicine
Academic literature review