行人检测-Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry
2016-08-19 14:14
351 查看
CVPR 2016 关于行人检测的文献
手工设计特征，然后训练分类器进行行人检测。
3 Our methods
3.1. Appearance constancy and shape symmetry
这里提出了两个关于行人的特点
Appearance constancy 在水平方向，人体内的纹理基本相似，与背景有一定差异。
shape symmetry 人体在水平方向具有一定的对称性。
内部特征有时含有有用信息
手工设计特征，然后训练分类器进行行人检测。
3 Our methods
3.1. Appearance constancy and shape symmetry
这里提出了两个关于行人的特点
Appearance constancy 在水平方向，人体内的纹理基本相似，与背景有一定差异。
shape symmetry 人体在水平方向具有一定的对称性。
内部特征有时含有有用信息
内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理 
相关文章推荐
- 车辆检测“Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model”
- 行人检测--What Can Help Pedestrian Detection?
- 行人检测“Joint Deep Learning for Pedestrian Detection”
- Joint Deep Learning For Pedestrian Detection（论文笔记-深度学习：行人检测）
- 行人检测 Is Faster R-CNN Doing Well for Pedestrian Detection?
- 视盘检测 Accurate and Efficient Optic Disc Detection and Segmentation by a Circular Transformation
- 行人检测论文笔记：Ten Years of Pedestrian Detection, What Have We Learned?
- 行人检测 Is Faster R-CNN Doing Well for Pedestrian Detection?
- 行人检测论文笔记：How Far are We from Solving Pedestrian Detection?
- 行人检测“Pedestrian detection at 100 frames per second”
- 行人检测“Pedestrian Detection with Unsupervised Multi-Stage Feature Learning”
- 行人属性“Attribute Recognition by Joint Recurrent Learning of Context and Correlation”
- 背景建模或前景检测(Background Generation And Foreground Detection) 二
- 行人属性“Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Loca”
- 解读 Joint Cascade Face Detection and Alignment 人脸检测算法
- 背景建模或前景检测(Background Generation And Foreground Detection) 五 ViBe
- 背景建模与前景检测3(Background Generation And Foreground Detection Phase 3)
- 背景建模或前景检测(Background Generation And Foreground Detection) 四
- 背景建模或前景检测(Background Generation And Foreground Detection) 五 ViBe
- Andrew NG 机器学习 笔记-week9-异常检测和推荐系统（Anomaly Detection and Recommender Systems）