I''m Javad Ibrahimli, an Electronics and Communication Engineering student at Istanbul Technical University, specializing in Computer Vision and Artificial Intelligence. I focus on end-to-end AI and Computer Vision project development, from version control to production deployment.
My expertise includes Vision Transformers (ViTs), Vision Language Models (VLMs), real-time vision systems, and signal processing. I build complete AI systems covering project architecture, model development, MLOps, and deployment optimization.
I integrate computer vision with sensor fusion using LiDAR, RADAR, cameras, and GPS for autonomous applications.
Current Focus: Vision language models, autonomous perception systems, edge AI optimization, and production MLOps infrastructure
|
Computer Vision
Deep Learning for Vision
|
3D Vision & Scene Understanding
AI Optimization & Deployment
|
|
Autonomous Tomato Farm Robot Autonomous Vehicle Motion Planning PID Controller Path Planning | 📹 Demo |
Label Mender Advanced Lane Detection | 📹 Demo GPS Publisher for ROS2 |
- Edge-Deployable Deep Segmentation of Breast Ultrasound Images via Optimized U-Net - Optimized U-Net architecture for real-time medical image segmentation on edge devices
- Urban Noise Classification Using Machine Learning Algorithms - Comprehensive ML approach for smart city noise pollution monitoring
- AI-Driven Detection of Network Traffic Anomalies - ML-based anomaly detection validated through OMNeT++ simulation
- Machine Learning Models for Heart Attack Prediction - Predictive analytics for cardiovascular risk assessment
For more projects, publications, and detailed information, please visit javadibrahimli.github.io
| Category | Technologies |
|---|---|
| Languages | Python C++ CUDA |
| Frameworks | PyTorch TensorFlow OpenCV ROS2 TorchVision |
| Optimization | ONNX TensorRT Edge Deployment MLOps |
| Tools | Docker Git Gazebo OMNeT++ PyQt5 |



