Imran Nawar
About me
I'm an AI and Computer Vision Researcher from Peshawar, Pakistan. I received my Bachelor's degree in Computer Science from Islamia College University, Peshawar. Currently, I am a Research Assistant at the Digital Image Processing Lab (DIP Lab) under the supervision of Dr. Muhammad Sajjad. My journey started with web development in college, and I have evolved into exploring cutting-edge topics in Artificial Intelligence, with a strong focus on Scene Understanding and Autonomous Navigation.
See moreExperience
Digital Image Processing Lab (DIP Lab)
July 2024 - Present
Research Assistant
Peshawar, Pakistan
- Major research topics: Autonomous Navigation, Object Detection, Image Segmentation.
- Conducting research for democratizing Autonomous Driving research.
- Teaching Assistant for courses:
- Data Visualization (DSC 635)
- Digital Image Processing (COMP416)
- Advanced Programming (COMP327)
Digital Image Processing Lab (DIP Lab)
Nov 2023 - June 2024
Undergraduate Student Researcher
Peshawar, Pakistan
- Developed an autonomous navigation prototype for a BS thesis using affordable hardware like Jetson Nano.
- Designed and built an autonomous car from scratch:
- Integrated hardware components.
- Optimized pretrained deep learning models for object detection and road segmentation.
- Implemented a control module for obstacle avoidance with a monocular camera.
- Created an RFID-based door lock system using an Arduino microcontroller.
Projects
Check out some of my work here
Deep Learning Assisted Autonomous Navigation over Economical Hardware: Implemented a cost-effective autonomous driving system on NVIDIA Jetson Nano. Utilized SSD-MobileNet for object detection and FCN-ResNet34 for road segmentation.
Developed a model using the FER-2013 dataset to classify emotions. Achieved optimal performance with CLIP ViT-B/32, balancing accuracy and speed for real-time applications.
Created a Streamlit app for pneumonia detection using ResNet18 with 80% test accuracy. Deployed on Hugging Face Spaces for real-world accessibility.
Trained models to classify happy, sad, and surprise emotions using MediaPipe-extracted landmarks. Achieved 77.7% accuracy with Logistic Regression.
Technologies
These are the technologies I've worked with
PYTHON
PYTORCH
OPENCV
C++
SCIKIT-LEARN
Git
Education
Bachelor of Science in Computer Science
Islamia College University, Peshawar (2020-24)
Intermediate in Computer Science (HSSC)
Islamia College, Peshawar (2018-20)
Check out some of my certificates
.webp)
Contact
My inbox is always open. Whether you have a question or just want to say hi, I will try my best to get back to you!