各算法代码分散在不同子目录,应使用最新版本 M3T 目录下的代码;README 未给出安装与运行步骤,需进入对应子目录查看各自说明
DLR 开源的 3D 物体跟踪算法合集,从连续图像帧估计物体相对相机的 6DoF 位姿
收录 3D 目标跟踪方向的论文与配套 C++ 算法实现,覆盖多体、铰接物体、多模态和实时位姿估计,方便复现和对比各类方法。
核心能力
- 按论文分目录发布 RBGT、SRT3D、ICG 等跟踪算法
- 用稀疏高斯建模区域外观做 6DoF 位姿估计
- 融合区域与深度信息跟踪无纹理物体
- 支持多体与运动学结构跟踪
- 每个目录含复现论文结果所需代码
容易踩的坑
暂无 release 数据(可能没有发版,或尚未同步)。
用户点评
登录用户的真实使用记录,可按版本和硬件筛选还没有人点评。第一个说出真实体验的人最有价值。
3D Object Tracking
Tracking objects and kinematic structures in 3D space and determining their poses and configurations is an essential task in computer vision. Its application ranges from augmented reality to robotic perception. Given consecutive image frames, as well as 3D meshes and kinematic information, the goal is to robustly estimate the rotation and translation of all bodies relative to a camera. While the problem has been thoroughly studied, many challenges such as partial occlusions, appearance changes, motion blur, background clutter, object ambiguity, and real-time requirements still exist.
In this repository, we will continuously publish algorithms and code of our ongoing research on 3D object tracking. The folders for the different algorithms include everything necessary to reproduce results presented in our papers. Note that the code for each new paper also includes an updated version of previous work. If you want to use our tracker in your own project or application, please use the code from the latest publication. Currently, the latest version of our code can be found in the folder M3T.
Algorithms
- RBGT Stoiber M, Pfanne M, Strobl KH, Triebel R, Albu-Schäffer A (2020) A Sparse Gaussian Approach to Region-Based 6DoF Object Tracking. In: Asian Conference on Computer Vision
- SRT3D Stoiber M, Pfanne M, Strobl KH, Triebel R, Albu-Schäffer A (2022) SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World. In: International Journal of Computer Vision
- ICG Stoiber M, Sundermeyer M, Triebel R (2022) Iterative Corresponding Geometry: Fusing Region and Depth for Highly Efficient 3D Tracking of Textureless Objects. In: Conference on Computer Vision and Pattern Recognition
- ICG+ Stoiber M, Elsayed M, Reichert AE, Steidle F, Lee D, and Triebel R (2023) Fusing Visual Appearance and Geometry for Multi-modality 6DoF Object Tracking. Submitted to: IEEE/RSJ International Conference on Intelligent Robots 2023
- Mb-ICG Stoiber M, Sundermeyer M, Boerdijk W, Triebel R (2023) A Multi-body Tracking Framework - From Rigid Objects to Kinematic Structures. Submitted to: IEEE Transactions on Pattern Analysis and Machine Intelligence
- M3T Stoiber M (2023) Closing the Loop: 3D Object Tracking for Advanced Robotic Manipulation. Dissertation submitted to the Technical University of Munich