【计算机视觉】Object Proposal之BING++
来源:互联网 发布:网络命令大全 编辑:程序博客网 时间:2024/06/13 23:01
本文是对 BING 算法的升级,主要是在快的同时保持定位精度
两个 + 分别对应: edge-based recursive boxes as one “+”, and MTSE-based superpixel merging as the other “+”
Object Detection Recall (DR):which is the ratio of the number of correctly detected objects and the total number of objects in the dataset
Proposal Localization Quality measured in terms of average best overlap (ABO)
mean average best overlap (MABO)
Key insight: 我们注意到好的候选区域框是刚刚包含物体,edge 特征可以用于检测物体边缘
2 Problems in BING
poor proposal localization quality
3 Our Solution: BING++
(1) We take proposals from BING as input.
(2) We then recursively update current bounding boxes based on their current locations and surrounding edge points to form new bounding boxes. This process is recursed until we find
(3) We finally apply fast super-pixel merging techniques to further refine the output bounding boxes of (2) and output final object proposals
算法流程:
结果对比:
- 【计算机视觉】Object Proposal之BING++
- 【计算机视觉】Object Proposal之BING理解
- 【计算机视觉】detection/region/object proposal 方法综述文章
- 【计算机视觉】detection/region/object proposal 方法综述文章
- BING++: A Fast High Quality Object Proposal Generator at 100fps
- 计算机视觉之路
- 计算机视觉之路
- object proposal的综述
- 计算机视觉 之 在iOS上测试跟踪算法Visual Object Tracking Algorithm
- 【计算机视觉】BING: Binarized Normed Gradients for Objectness Estimation at 300fps
- 开始计算机视觉之路~~~
- 计算机视觉之线性滤波
- 计算机视觉之分类器
- 计算机视觉之语义分割
- Object Proposal(OP)综述
- 【计算机视觉】Selective Search for Object Recognition论文阅读1
- 【计算机视觉】Selective Search for Object Recognition论文阅读2
- 【计算机视觉】Selective Search for Object Recognition论文阅读3
- Raft算法国际论文全翻译
- spring线程池ThreadPoolExecutor配置并且得到任务执行的结果
- Android4.4屏幕不休眠&不锁屏
- Compilation with Make in Caffe.ImportError: No module named _caffe
- ViewPager+GridView实现美团商品分类
- 【计算机视觉】Object Proposal之BING++
- Java反射机制
- JAVA-JNI中jfieldID
- javaMail SMTPSendFailedException: 554 DT:SPM 163 smtp4
- 固态硬盘4K对齐
- 垂直手风琴5级菜单!用js+jquery动态加载菜单,附上源码hezhu和注释
- web开发的页面布局
- GreenDao的配置及基本操作
- 获取Gif的时间