遥感目标检测数据库

更新时间:2019.09.10

  • DIOR (Li et al., 2019)
    Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
    23,463 images
    190,288 object instances
    20 classes
    OneDrive
    BaiduWangpan
  • HRRSD (Zhang et al., 2019)
    Hierarchical and Robust Convolutional Neural Network for Very High-Resolution Remote Sensing Object Detection
    21,761 images
    55,740 object instances
    13 classes
    Github
  • SAR-Ship-Dataset (Wang et al. 2019)
    A SAR Dataset of Ship Detection for Deep Learning under Complex Backgrounds
    210 images
    43,819 object instances
    1 class (ship)
    Github
  • DOTA (Xia et al., 2018)
    DOTA: A Large-scale Dataset for Object DeTection in Aerial Images
    2,806 images
    188, 282 object instances
    15 classes
    Captain
  • RSOD-Dataset
    Accurate Object Localization in Remote Sensing Images Based on Convolutional Neural Networks
    Elliptic Fourier transformation-based histograms of oriented gradients for rotationally invariant object detection in remote-sensing images
    976 images
    6,950 object instances
    4 classes (plane, playground, tank, highway)
    Github
  • NWPU VHR‐10 (Cheng et al., 2016a)
    Multi-class geospatial object detection and geographic imageclassification based on collection of part detectors
    800 images
    3,775 object instances
    10 classes
    OneDrive
    BaiduWangpan
  • COWC (Mundhenk et al., 2016)
    A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning
    ____ images
    32,716 object instances
    4 classes (different type cars)
    COWC
  • UCAS‐AOD (Zhu et al., 2015a)
    Orientation Robust Object Detection in Aerial Images Using Deep Convolutional Neural Network
    910 images
    6,029 object instances
    2 classes (plane, vehicle)
    BaiduWangpan (key: ppef)
    hyper.ai
  • 3
    点赞
  • 26
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值