News
- Our paper RGB-D Camera Calibration and Trajectory Estimationfor Indoor Mapping, Liang Yang, Ivan Dryanovski, Roberto G. Valenti, George Wolberg, Jizhong Xiao, is accepted by Autonomous Robots, in which we proposed a ‘feature model’ based RGB-D visual odometry system for a computationally-constrained mobile platform, and we also introduce a general depth calibration method to remove systematic errors in the depth readings of the RGB-D camera. [Code coming soon](), Paper PDF
- Our paper Concrete Defects Inspection and 3D Mapping using CityFlyer Quadrotor Robot, Liang Yang, Bing Li, Wei Li, Howard James Jarrell Brand, Biao Jiang, Jizhong Xiao, is accepted by IEEE/CAA Journal of Automatica Sinica. Paper is here, Code and Data. 2020
- Our Paper GPR-based Subsurface Object Detection and Reconstruction Using Random Motion and DepthNet, Jinglun Feng*, Liang Yang *, Haiyan Wang, Yifeng Song, Jizhong Xiao, is accepted by ICRA 2020. Paper, code, and dataset appear soon.
- Our Paper Driver Drowsiness Behavior Detection and Analysis Using Vision-Based Multimodal Features for Driving Safety, Rui Li, Howard Brand, Aditya Gopinath, Srivatsav Kamarajugadda, Liang Yang, Weitian Wang, Bing Li, is accepted and published in WCX SAE World Congress Experience 2020. Paper is here.
- Our Paper Visual Odometry with a Single-Camera Stereo Omnidirectional System by Carlos Jaramillo and Liang Yang and Pablo Munoz and Yuichi Taguchi and Jizhong Xiao, is accepted by Machine Vision and Applications, Springer. We proposed a Single-Camera Stereo Omnidirectional System which is able to be robust for visual odometry task under highly crowded and dynamic environment.
Our Paper Towards Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenes by Haiyan Wang, Xuejian Rong, Liang Yang, Yingli Tian, is accepted by British Machine Vision Conference (BMVC), 2019, as oral. We were working toward point segmentation in a semi-superwised approach.
Our Paper Deep Neural Network based Visual Inspection with 3D Metric Measurement of Concrete Defects using Wall-climbing Robot Has been Accepted by 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019).
Our Paper Visual-GPS: Ego-Downward and Ambient Video based Person Location Association has been accepted by IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2019. Please email me if you are interested.
Our Paper Visual SHM for Concrete Infrastructure Using a Wall-climbing Robot has been accepted by 9th International Conference on Structural Health Monitoring of Intelligent Infrastructure 2019. Looking forward to see you at St. Louis.
Released the dataset for paper: Semantic Metric 3D Reconstruction for Concrete Inspection (Authors are: Liang Yang, Bing Li, Wei Li, Biao Jiang, and Jizhong Xiao), 2018 CVPRW. Please check here Code and Data. Also check here for our previous work: concrete structure inspection Code and Data.
See how things really be interesting combining 3D and 2D, the indoor semantic segmentation and reconstruction, wait for my further paper work:
