ABOUT ME

My name is Ilker Bozcan. I am professional machine learning and computer vision engineer.

Currently, I am conducting my Ph.D. research on analyzing aerial images captured by drones. More specifically, I am working on object detection in challenging aerial images, and anomaly detection for aerial surveillance (finding suspucious objects, events, actions in a crowd).

I also design and develop machine learning-based solutions for my clients in my freetime, mostly for visual recognition. I like using my research and engineering skills for usefulness.

Profile Image

Skills

Probability & Statistics Computer Science & Data Structures Programming Languages Machine Learning Algorithms Software Engineering & Design Edge or Large Scale Computing Platforms

Social

Download My Resume

MY SERVICES

I help my clients to develop AI-based visual recognition systems for their services or products.

ML Development

Design, develop and optimize machine learning algorithms for different domains.

Object Detection

Identify object categories in images with the location of each object instance.

Semantic Segmentation

Label and predict objects at the pixel level, and segment image regions.

Data Classification

Classify data (image, audio, stock) into predefined categories.

Dataset Analysis

Analyze requirements of datasets and optimize data gathering process.

Research for Industry

Survey the literature for state-of-the-art methods to adapt the business.

MY PORTFOLIO

  • All
  • ML Development
  • Object Detection
  • Semantic Segmentation
  • Data Classification
  • Dataset Analysis
  • Research for Industry
image

PEDESTRIAN AND VEHICLE DETECTION IN AERIAL IMAGES

image

ANOMALY DETECTION USING DRONES

image

SKETCH RECOGNITION IN HAND-DRAWN SLIDES

MY PUBLICATIONS

[1] Bozcan, Ilker and Erdal Kayacan. "AU-AIR: A Multi-modal Unmanned Aerial Vehicle Dataset for Low Altitude Traffic Surveillance". Accepted to 2020 IEEE International Conference on Robotics and Automation (ICRA). arXiv:2001.11737. [2] Bozcan, Ilker, and Sinan Kalkan. "COSMO: Contextualized scene modeling with Boltzmann Machines." Robotics and Autonomous Systems 113 (2019): 132-148. [3] Bozcan, Ilker, et al. "What is (missing or wrong) in the scene? A Hybrid Deep Boltzmann Machine For Contextualized Scene Modeling." 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2018. [4] Doğan, Fethiye Irmak, et al. "Cinet: A learning based approach to incremental context modeling in robots." 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2018. [5] Bozcan, Ilker, and Sinan Kalkan. "Combining Different Knowledge-bases into a Single Partially-grounded Robotic Knowledge-base." (2017).
Google Scholar

CONTACT ME

Turing 0, Building 5341, Aabogade 34, 8200 Aarhus N, Denmark

+45 50 35 86 72

ilker@eng.au.dk

ilkerbozcan@hotmail.com