Visual Perception for Autonomous Driving
1. 像素差的绝对值(SAD, Sum of Absolute Differences)
2. 像素差的平方和(SSD, Sum of Squared Differences)
3. 图像的相关性(NCC, Normalized Cross Correlation)
4. Census 局部空间结构 汉明距离 匹配代价
5. AD + Census
6. SD + Census
7. ...
Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches
输入:两个图像块
输出:匹配代价 Match Cost
two img --->two CNN ----> 连接(concatenate)----> 全连接 ----->相似性得分(similarity score)
Small patch size
“Big” network(~600K)
Binary prediction
two img --->two CNN ---->标准化(normalizer)----->点乘(dot product) ----->相似性得分(similarity score)
Dot-product
Small network
Hinge loss
two img --->two CNN(共享权重)---------->相关性----->
Full content
Dot-product
Larger patch
Log loss
1. 预处理,数据增强 Preprocessing, data-augmentation
2. 网络: 梯度聚合 network: gradient aggregated
3. SGD; Batch Normalization 批量化
代价聚合 Cost-aggregation
1.平均邻近位置 Averaging neighboring locations
2.奇特的“邻居” 外点(遮挡点+不稳定)
全局能量函数
SGM(Stereo Processing by Semi-Global Matching and Mutual Information)
CRF
dynamic programming
Border fixing(CNN)
Left-right consistency
Further smooth
Outlier detector
Z = fB/d
z:深度
f:相机焦距
d:像素点视差
Y = (u - cy)*Z/f
X = (v - cx)*Z/f