Pervasive Artificial Intelligence Research (PAIR) Labs

Drones and Computer Vision

Pervasive Artificial Intelligence Research (PAIR) Labs

Drones and Computer Vision

NCTU – Professor Ching-Chun Huang

Research：

Video Compression based on Generative Model
(PI: Hsueh-Ming Hang / Co-PI: Ching-Chun Huang)

Core Technologies

Currently we have following the core technologies(1)Object Detection and Tracking(2)Depth Completion(3)Parking Lot Vacancy Detection System(4)AI Video Compression and Image/Video Restoration(5)Medical Image Analysis(6)Image Style Transfer(7)IoT Wearable Device for Localization and Guidance System(8)Automatic HVAC control system(9)3D Skeleton Detection and Tracking(10)Head Pose Estimation System(11)UAV-Density Estimation(12)3D Simultaneous Localization and Mapping(SLAM)

Applications

1. Smart Traffic
2. Image Analysis/Restoration
3. Smart Building
4. AR-VR
5. Smart Robot
6. Medical Image Analysis

Technology Transfer

1. Research on the improvement of the accuracy of wireless indoor positioning in view of device differences
2. Research on the simultaneous positioning and mapping based on panoramic cameras in robot vacuums
3. Research on the image based outdoor parking space detection
4. Research on the outdoor parking space detection based on deep learning, geomagnetic sensing network, and LoRa IoT communication
5. Research on the image segmentation and depth map inpainting based on RGBD cameras
6. Head pose estimation
7. Crowd density estimation by merging multiple heterogeneous sensors
8. Automatic HVAC control system

Technologies with Potential for Technology Transfer or Industry-Academia Collaboration

1.Self-driving system based on 2D and 3D object detection and recognition
2.Video super resolution based on the deep learning
3. Dynamic and boosting network for recursive image super-resolution

Drones and Computer Vision