My portfolio showcases various projects/reserch outputs throughout my career.
For the last three years I have been working as a Reserch Fellow and my mentor Prof Erik Champion asked me to sumarrise our works. So, I have developed three posters to showcase what we have been done. The frist one, presents the books we have published and the seminars and workshops organised. The second one, presents my works on #Photogrammetry and works from our two PhD students. The third one, displays my photogrammetry #workflow which I have developed with #FOSS software, online tutorials (at #Udemy) and sample of works.
Learning from Australian Banknote
Wildflower Language in the Wild: Phone-based Object Detection, Machine Learning and Augmented Reality
Before colonisation, there were over 250 languages spoken in Australia. Today only thirteen Indigenous languages are still being taught to children (AIATSIS 2019). We aim to develop a fun and easy way to teach and learn the local Indigenous names of wildflowers using a mobile device. This paper presents the development of a prototype phone application that runs on a local machine, recognises local wildflowers through its camera, and plays associated sounds and displays associated text in the Noongar language using Machine Learning and Augmented Reality technologies. Based on MobileNets model on the TensorFlow platform, the app has been developed with customed datasets and sound files; while using Vuforia, Unity and Android Studio for camera tracking, interaction design and deployment respectively. At this time, the prototype can only recognise ten local flowers, with 85%~99% of accuracy. We are working with a larger dataset towards developing the full application.
Study HMDs & Their Features
Description of the posters
Augmented Reality for Realstate Marketing
The main challenge here is the optimisation of the 3D model.
Recreating the Histoic Speech of Sk. Mujibur Rahman, March 1971