欢迎来到中科图云!

电子邮箱

密码

注册 忘记密码?

ITCVD

图像来自一个飞越荷兰恩斯赫德的高出地面330米(Slagboom en Peeters,2017 )的飞机平台。图像是在天底视图和斜视图中拍摄的。135张车辆的135张图像用于训练,其余38张图像用5545辆车辆进行测试。使用边界框手动注释数据集中的每个车辆,边界框表示为(x,y,w,h),其中(x,y)是框的左上角的坐标,(w,h) )分别是盒子的宽度和高度。


The images were taken from an airplane platform which flied over Enschede, The Netherlands, in the height of ca 330m above the ground (Slagboom en Peeters, 2017). The images are taken in both nadir view and oblique view. The tilt angle of oblique view is 45 degrees. The Ground Sampling Distance (GSD) of the nadir images is 10cm. 135 images with 23543 vehicles are used for training and the remaining 38 images with 5545 vehicles for testing. Each vehicle in the dataset is manually annotated using a bounding box which is denoted as (x,y,w,h), where (x,y) is the coordinate of the left-up corner of the box, and (w,h) is the width and height of the box respectively.


Reference:


Yang M Y, Liao W, Li X, et al. Deep Learning for Vehicle Detection in Aerial Images[C]//2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 2018: 3079-3083.

Yang M Y, Liao W, Li X, et al. Vehicle Detection in Aerial Images[J]. arXiv preprint arXiv:1801.07339, 2018.