Research

Current Research

Sensor Fusion using Equivariant and Foundation Models

More detail coming soon!

Past Research & Projects

SE3ET: SE(3)-Equivariant Transformer for Low-Overlap Point Cloud Registration

We propose SE3ET, an SE(3)-equivariant registration framework that employs equivariant point convolution and equivariant transformer design to learn expressive and robust geometric features. 

[GitHub]

SE(3)-Equivariant Point Cloud-based Place Recognition (CoRL 2022)

Learned SE(3)-invariant global descriptors are more robust to matching inaccuracy and failure in severe rotation and translation configurations.

[Paper] [Github]

A New Framework for Registration of Semantic Point Clouds from Stereo and RGB-D Cameras

A novel nonparametric rigid point cloud registration framework that jointly integrates geometric and semantic measurements such as color or semantic labels into the alignment process and does not require explicit data association.

[Paper][arXiv][GitHub][Video]

Mini Cheetah Perception

Added camera and computational resource to perform semantic mapping on mini cheetah.

SIFT Flow CVO

Used SIFT-flow as additional labels to improve Continuous Visual Odometry (CVO).

[GitHub]

Computer Vision-Based Navigation System for Visually Impaired Person

Developed a computer vision-based system that can navigate someone visually impaired to the targeted door with object detection, object tracking, and visual SLAM.

[Paper] [GitHub]

Structured Light 3D Reconstruction

Reconstructed an underwater scene in 3D, using structured light systems that project light patterns on the objects and enable the reconstruction of its structure, despite the low texture and low contrast of underwater images.

 

 

Pest Surveillance System

Constructed an IoT-based wireless imaging and sensor node system for remote greenhouse pest monitoring, with 90% accuracy of pest classification using deep neural network, enabling farmers easily notice amount change of pest in real-time.

[Paper]

Plant Growth Monitoring System

Built a Plant Growth Monitoring System to monitor the growth of Cordyceps militaris using Qt, OpenCV and Raspberry Pi.

A Novel Nitinol Spherical Occlusion Device for Liver Cancer

A novel nitinol “spherical occlusion device” concept that is able to reduce the blood flow to cancer cells by deploying it in the upstream hepatic artery supplying blood to the liver. Moreover, it could carry multiple chemotherapy or radioactive drugs for delivery directly to the target site.

[Paper