Asad Ullah

My responsibilities include development of visual recommendation system utilizing deep learning techniques to address various computer vision challenges, including image retrieval, image segmentation, and visual compatibility etc.

I was responsible for the development of deep learning-based prediction models for the risk perceived by driver-passenger of an autonomous vehicle. I performed successful data pre- processing using a novel method. And used Long Short-term Memory Networks and Convolutional Neural Network to build prediction models.

I was responsible for the development of components ADAS components and their implementation on embedded ECU. The projects also included monocular car mounted speed es- timation system and lane departure warning system. I utilised Machine Learning and computer vision methods to complete the tasks. I also got hands on experience with CAN communi- cation, AUTOSAR standards, Restbus simulation, Requirement and Validation Process.