Select Language



Biwi Kinect头部姿势数据库

Biwi Kinect头部姿势数据库

340 浏览
0 喜欢
3 次下载
0 条讨论
Action/Event Detection Classification

Biwi Kinect Head Pose Database 是一个人头部姿势图像数据集,包含 15000 多张,20个不同人的头部姿势的图像。Because cheap co......

数据结构 ? 5.6G

    Data Structure ?

    * 以上分析是由系统提取分析形成的结果,具体实际数据为准。

    Biwi Kinect Head Pose Database 是一个人头部姿势图像数据集,包含 15000 多张,20个不同人的头部姿势的图像。

    Because cheap consumer devices (e.g., Kinect) acquire row-resolution, noisy depth data, we could not train our algorithm on clean, synthetic images as was done in our previous CVPR work. Instead, we recorded several people sitting in front of a Kinect (at about one meter distance). The subjects were asked to freely turn their head around, trying to span all possible yaw/pitch angles they could perform.

    To be able to evaluate our real-time head pose estimation system, the sequences were annotated using the automatic system of, i.e., each frame is annotated with the center of the head in 3D and the head rotation angles.

    The dataset contains over 15K images of 20 people (6 females and 14 males - 4 people were recorded twice). For each frame, a depth image, the corresponding rgb image (both 640x480 pixels), and the annotation is provided. The head pose range covers about +-75 degrees yaw and +-60 degrees pitch. Ground truth is provided in the form of the 3D location of the head and its rotation.

    Even though our algorithms work on depth images alone, we provide the RGB images as well. Please note that this is a database acquired with frame-by-frame estimation in mind, not tracking. For this reason, some frames are missing.

    The database is made available for research purposes only. You are required to cite our work whenever publishing anything directly or indirectly using the data:

         author = {Fanelli, Gabriele and Dantone, Matthias and Gall, Juergen and Fossati, Andrea and Van Gool, Luc},
         title = {Random Forests for Real Time 3D Face Analysis},
         journal = {Int. J. Comput. Vision},
         year = {2013},
         month = {February},
         volume = {101},
         number = {3},
         pages = {437--458}




    • 分享你的想法


    所需积分:20 去赚积分?
    • 340浏览
    • 3下载
    • 0点赞
    • 收藏
    • 分享