Container spreader pose tracking dataset
收藏资源简介：
This dataset contains image sequences that feature a moving quay crane spreader in a port environment while unloading a container cargo vessel. A container crane spreader is a device that is installed on a crane and used to lift containers after attaching onto them. The sequences were acquired from a viewpoint similar to that of the crane operator using a camera installed next to the operator’s cabin at a height of approximately 20 meters above the quay. The camera thus moves with the crane, resulting in a non-stationary image background. The dataset is organized into several RAR archives, one for each sequence. In addition to the undistorted image frames, it includes for every sequence a text file whose each line consists of the frame id for every image, the spreader’s bounding box and the spreader’s 6D pose (Rodrigues vector for the orientation, and the translation vector). The axis-aligned 2D bounding box is in the format x0 y0 w h where (x0, y0) is the top left corner and w x h its size, all in pixels. The spreader’s pose is defined with respect to the camera coordinate frame. Also included are the camera intrinsics matrix K for each sequence along with a common 3D mesh model for the spreader. The spreader’s mesh model is supplied in PLY format. For a certain image frame, a model vertex M transforms to the camera coordinate system as R*M + t, R and t being the spreader’s pose (R is the equivalent rotation matrix). The homogeneous coordinates of that vertex’s projection on the image frame are K*(R*M + t). The dataset can support research on topics such as object localization, object detection, pose estimation, tracking, etc. If you use this dataset in your research work, you are kindly asked to cite the following paper in your publications: M. Lourakis and M. Pateraki, "Markerless Visual Tracking of a Container Crane Spreader," 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021, pp. 2579-2586, doi: 10.1109/ICCVW54120.2021.00291.
本数据集包含港口环境下，岸桥吊具（quay crane spreader）装卸集装箱船的移动图像序列。岸桥吊具是安装于起重机之上、用于抓取并起吊集装箱的专用装置。该图像序列由安装在司机室旁、距岸桥顶面约20米高度的摄像机采集，拍摄视角与起重机司机的操作视野高度近似。由于摄像机随起重机同步运动，因此图像背景为非静止状态。本数据集以多个RAR压缩包形式组织存储，每个压缩包对应一个独立的图像序列。除未经过失真校正的图像帧外，每个序列还附带一个文本文件：文件每行依次记录对应图像的帧ID、吊具的轴对齐2D边界框（axis-aligned 2D bounding box），以及吊具的6D位姿——旋转部分采用罗德里格斯向量（Rodrigues vector）表示，平移部分为平移向量。轴对齐2D边界框的格式为x0 y0 w h，其中(x0, y0)为边界框左上角顶点的像素坐标，w与h分别为边界框的宽与高，单位均为像素。吊具的位姿定义基于摄像机坐标系。此外，每个序列还附带对应的摄像机内参矩阵K，以及通用的吊具3D网格模型（3D mesh model）：网格模型采用PLY格式（PLY format）存储。对于某一图像帧，网格顶点M可通过变换R*M + t转换至摄像机坐标系，其中R与t为吊具的位姿参数（R为等效旋转矩阵）。该顶点在图像帧上的投影的齐次坐标（homogeneous coordinates）为K*(R*M + t)。本数据集可支撑目标定位、目标检测、位姿估计、目标跟踪等相关研究方向。若在研究工作中使用本数据集，请在发表成果中引用如下论文：M. Lourakis与M. Pateraki所著《Markerless Visual Tracking of a Container Crane Spreader》，发表于2021 IEEE/CVF国际计算机视觉研讨会（ICCVW 2021），页码2579-2586，DOI: 10.1109/ICCVW54120.2021.00291。
