Yale-cmu-berkeley
文章: Yale-CMU-Berkeley dataset for robotic manipulation research
1. 数据库组成
每个物体有:
(1) 600张高清晰的RGB图像(像素:4272*2848)
(2) 600张RGBD图像(像素:rgb:1280*1024; depth: 640*480)
(3) five sets of textured three-dimensional geometric models
(4) Segmentation masks and calibration information for each image
2. 相机型号:
These data are acquired using the BigBIRD Object Scanning Rig and Google Scanners
(1) BigBIRD Object Scanning Rig
该装置由五对相机组成: five 12.2 megapixel Canon Rebel T3 RGB cameras and five PrimeSense Carmine 1.08 RGB-D sensors, 这五对相机成四分之一圆弧放置;
The Canon Rebel T3s have APS-C sensors (22.0 mm × 14.7 mm), a pixel size of 5.2 mm, and are equipped with EF-S 18-55mm f/3.5-5.6 IS lenses.
3. 下载方式与相关网站
(1) Together with the dataset, Python scripts and a Robot Operating System node are provided to download the data, generate point clouds and create Unified Robot Description Files
(2)网站
http://ycb-benchmarks.s3-website-us-east-1.amazonaws.com/
BigBIRD
http://rll.berkeley.edu/bigbird/
文章: BigBIRD: A Large-Scale 3D Database of Object Instances
objects, we provide:
- 600 12 megapixel images, sampling the viewing hemisphere
- 600 registered RGB-D point clouds from a Carmine 1.09 sensor
- Pose information for each of the above images and point clouds
- Segmentation masks for each of the above images (and segmented point clouds)
- Merged point clouds consisting of data from all 600 viewpoints
- Reconstructed meshes from the merged point clouds