卫星图像中的车辆分析--A Large Contextual Dataset for Classification, Detection and Counting of Cars
2017-09-30 15:03
543 查看
A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning
ECCV2016
https://gdo-datasci.ucllnl.org/cowc/
本文针对卫星图像中的车辆分析建立了一个新的数据库:Cars Overhead with Context (COWC),然后使用几个 CNN网络对该数据库进行了分析:主要是分类、检测、计数
首先来看看这个新的数据库 Cars Overhead with Context (COWC)
数据库含有 32716个不同的车,来自6个不同的图像库,图像覆盖的区域包括:Toronto Canada [5], Selwyn New Zealand [6], Potsdam [7] and Vaihingen Germany [8], Columbus [9] and Utah [4] United States。
我们的数据库还标记了 58247个有用的负样本,这些样本和正样本比较相似,难以区分,Examples of these are boats, trailers, bushes and A/C units
context is included around targets. Context can help tell us something may not be a car (is sitting in a pond?) or confirm it is a car (between other cars, on a road).
我们对输入图像做了一个归一化,不用考虑车辆的尺度问题。 standardized to 15cm per pixel at ground level from their original resolutions. This makes cars range in size from 24 to 48 pixels。 车辆在图像中的尺寸是 24-48像素之间。有灰度图像,也有彩色图像。
quality, appearance or rotation 这些都是不可控的,需要通过算法来解决
图像是像素级标记的,每个车在其中心点标记一个 dot
The image set is annotated by single pixel points. All cars in the annotated images have a dot placed on their center
对 occlusions, Large trucks, Vans and pickups 做了相应的约定。
我们从卫星图像中间隔的裁出图像块分别作为训练图像和测试图像
测试场景
这里我们对新的数据库上完成三个任务:
1)two-class classifier,即判断图像块中有无车辆
2) detection and localization
3) vehicle counting 这里没有密度图,走检测计数的路线
4 Classification and Detection
设计了一个新的网络结构
我们从卫星图像中裁出 256 × 256 大小的图像块
a set of 308,988 training patches and 79,447 testing patches
4.1 Does Context Help?
从上面可以看出,context 增加到一定之后,性能就下降了。
4.2 Detection
5 Counting
我们是对卫星图像分块计数的。
5.2 Counting Efficiency
ECCV2016
https://gdo-datasci.ucllnl.org/cowc/
本文针对卫星图像中的车辆分析建立了一个新的数据库:Cars Overhead with Context (COWC),然后使用几个 CNN网络对该数据库进行了分析:主要是分类、检测、计数
首先来看看这个新的数据库 Cars Overhead with Context (COWC)
数据库含有 32716个不同的车,来自6个不同的图像库,图像覆盖的区域包括:Toronto Canada [5], Selwyn New Zealand [6], Potsdam [7] and Vaihingen Germany [8], Columbus [9] and Utah [4] United States。
我们的数据库还标记了 58247个有用的负样本,这些样本和正样本比较相似,难以区分,Examples of these are boats, trailers, bushes and A/C units
context is included around targets. Context can help tell us something may not be a car (is sitting in a pond?) or confirm it is a car (between other cars, on a road).
我们对输入图像做了一个归一化,不用考虑车辆的尺度问题。 standardized to 15cm per pixel at ground level from their original resolutions. This makes cars range in size from 24 to 48 pixels。 车辆在图像中的尺寸是 24-48像素之间。有灰度图像,也有彩色图像。
quality, appearance or rotation 这些都是不可控的,需要通过算法来解决
图像是像素级标记的,每个车在其中心点标记一个 dot
The image set is annotated by single pixel points. All cars in the annotated images have a dot placed on their center
对 occlusions, Large trucks, Vans and pickups 做了相应的约定。
我们从卫星图像中间隔的裁出图像块分别作为训练图像和测试图像
测试场景
这里我们对新的数据库上完成三个任务:
1)two-class classifier,即判断图像块中有无车辆
2) detection and localization
3) vehicle counting 这里没有密度图,走检测计数的路线
4 Classification and Detection
设计了一个新的网络结构
我们从卫星图像中裁出 256 × 256 大小的图像块
a set of 308,988 training patches and 79,447 testing patches
4.1 Does Context Help?
从上面可以看出,context 增加到一定之后,性能就下降了。
4.2 Detection
5 Counting
我们是对卫星图像分块计数的。
5.2 Counting Efficiency
相关文章推荐
- 论文笔记 A Large Contextual Dataset for Classification,Detection and Counting of Cars with Deep Learning
- 立体匹配综述阅读心得之Classification and evaluation of cost aggregation methods for stereo correspondence
- Region Covariance: A Fast Descriptor forDetection and Classification算法流程简介
- 《A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimat
- DropBand:A Simple and Effective Method for Promoting the VHR Scene Classification Accuracy of CNN
- Some 3D Graphics (rgl) for Classification with Splines and Logistic Regression (from The Elements of Statistical Learning)(转)
- 车型识别“A Large-Scale Car Dataset for Fine-Grained Categorization and Verification”
- 论文阅读-《Ensemble of Part Detectors for Simultaneous Classification and Localization》
- 卫星图像分割--Effective Use of Dilated Convolutions for Segmenting Small Object Instances
- 论文笔记:Research and Implementation of a Multi-label Learning Algorithm for Chinese Text Classification
- (论文分析) Object Detection -- Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection
- More 3D Graphics (rgl) for Classification with Local Logistic Regression and Kernel Density Estimates (from The Elements of Statistical Learning)(转)
- 卫星图像分割--Effective Use of Dilated Convolutions for Segmenting Small Object Instances
- 论文笔记_A Large-Scale Car Dataset for Fine-Grained Categorization and Verification
- 车辆检测“Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model”
- Classification and evaluation of cost aggregation methods for stereo correspondence
- Image Analysis, Classification, and Change Detection in Remote Sensing: With Algorithms for ENVI/IDL, Second Edition
- 图像检测1-R-CNN-Rich featurehierarchies for accurate object detection and semantic segmentation
- Region Covariance: A Fast Descriptor for Detection and Classification算法总结