Our work spans multiple domains, including healthcare, robotics, environmental monitoring, agriculture, education, sports, and workplace safety, where we address challenges such as reliable decision support, safe human–machine interaction, and efficient multimodal data analysis. By combining theory-driven approaches with real-world applications, we aim to push the boundaries of how computer vision, artificial and bioinspired intelligence can positively impact society.
Our core research areas include:
- Image Processing & Computer Vision
- Biomedical imaging and diagnostic applications
- Hyperspectral imaging (HSI)
- 2D/3D vision-based perception
- Scene understanding and object recognition
- Adversarial robustness and trustworthy computer vision
- Computer vision for sports analytics (performance tracking, injury prevention, motion analysis)
- Safety and surveillance vision systems (industrial safety, workplace monitoring, crowd analysis)
- Vision for robotics and autonomous systems (navigation, grasping, manipulation)
- Remote sensing and environmental monitoring (aerial/drone imagery, satellite analysis)
- Vision-based human–computer interaction (gesture, gaze, affect recognition)
- Bioinspired Robotics
- Perception & Vision in Robotics
- Tactile sensing and haptics for robotic manipulation
- Multi-Agent & Collaborative Robotics
- Embodied intelligence for adaptive robotic systems
- Artificial Intelligence (AI)
- Machine learning and deep learning algorithms
- Large vision–language and multimodal models
- Federated and privacy-preserving AI methods
- AI applications in healthcare, safety, and robotics
- Neurocognitive Systems
- Brain-inspired neural architectures and computation
- Memory, attention, and reasoning mechanisms in AI
- Cognitive modeling for adaptive and resilient intelligence
- Neurocognitive architectures for perception–action loop
- Neurocognitive robotics: integrating vision, touch, and action