license: bsd-3-clause
A collection of models employed for semantic perception on smart egde sensors. The Collection includes models for
- person, object, and robot detection
- person, object, and robot keypoint estimation
- semantic segmentation of indoor scenes
- instance segmentation of tables and chairs
- person detection in IR images
- person re-id
References:
Simon Bultmann, Raphael Memmesheimer, and Sven Behnke:
External Camera-based Mobile Robot Pose Estimation for Collaborative Perception with Smart Edge Sensors
In Proceedings of IEEE International Conference on Robotics and Automation (ICRA), London, UK, June 2023.
Paper;
Video
Julian Hau, Simon Bultmann, and Sven Behnke:
Object-level 3D Semantic Mapping using a Network of Smart Edge Sensors
In Proceedings of 6th IEEE International Conference on Robotic Computing (IRC), Naples, Italy, December 2022.
Paper;
Video
Simon Bultmann and Sven Behnke:
3D Semantic Scene Perception using Distributed Smart Edge Sensors
In Proceedings of 17th International Conference on Intelligent Autonomous Systems (IAS), Zagreb, Croatia, June 2022.
Paper;
Video;
Code Nvidia Jetson Sensorboard;
Code Backend
Simon Bultmann and Sven Behnke:
Real-Time Multi-View 3D Human Pose Estimation using Semantic Feedback to Smart Edge Sensors
In Proceedings of Robotics: Science and Systems (RSS), July 2021.
Paper;
Video;
Code;