READING NOTE: Object Detection by Labeling Superpixels
来源:互联网 发布:365抽奖软件破解版 编辑:程序博客网 时间:2024/04/30 04:17
TITLE: Object Detection by Labelling Superpixels
AUTHOR: Yan, Junjie and Yu, Yinan and Zhu, Xiangyu and Lei, Zhen and Li, Stan Z.
FROM: CVPR2015
CONTRIBUTIONS
- Convert object detection problem into super-pixel labelling problem, which could avoid false negatives caused by proposals and could take advantages from global contexts.
- Conduct an energy function considering appearance, spatial context and numbers of labels.
METHOD
- The image is partitioned into a set of super-pixels, denoted as
P={p1,p2,...,pN} . - An energy function
E(L) is calculated to measure the corresponding label configuration for each super-pixels, whereL={l1,l2,...,lN} . - The problem is transfered to select an
L to minimiseE(L) .
SOME DETAILS
The energy function is conducted as
where
Data Cost
Super-pixels usually does not have enough semantic information, so corresponding regions are classified and their costs are propagated to super-pixels. In this work, RCNN is used to generate and classify semantic regions. The region set of
where
where
Smooth Cost
The smooth cost is conducted for the reason that 1) adjacent super-pixels often have the same label and 2) super-pixels belonging to the same label should have similar apprearance. This attribute is measured by
where
where
Label Cost
The label cost is used to encourage less number of labels and its defination is
where
ADVANTAGES
- Super-pixels are compact and perceptually meaningful atomic regions for images.
- Avoid false negatives caused by inappropriate proposals generated by algorithms suchas Selective Search and BING.
- Super-pixel based method is a trade-off of Pixel based and Proposal based algorithm, leading to accurate and fast results.
DISADVANTAGES
- The CNN used in RCNN and the parameters in the energy function are learned separately.
- The region generated might not cover all the super-pixels.
- Time consumption is high. Its speed is 1fps for each 128 proposals on a NVIDIA Telsa K40 GPU. However, 128 proposals might not be enough.
- READING NOTE: Object Detection by Labeling Superpixels
- READING NOTE: Feature Pyramid Networks for Object Detection
- READING NOTE: SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection
- READING NOTE: R-FCN: Object Detection via Region-based Fully Convolutional Networks
- READING NOTE: R-FCN: Object Detection via Region-based Fully Convolutional Networks
- READING NOTE: Object Detection from Video Tubelets with Convolutional Neural Networks
- READING NOTE: PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection
- READING NOTE: Beyond Skip Connections: Top-Down Modulation for Object Detection
- Reading Note: Deformable Part-based Fully Convolutional Network for Object Detection
- Reading Note
- READING NOTE: Semantic Object Parsing with Graph LSTM
- READING NOTE: Learning to Detect Human-Object Interactions
- Reading Note: DSOD: Learning Deeply Supervised Object Detectors from Scratch
- [Paper note] Feature Pyramid Networks for Object Detection
- READING NOTE: Pushing the Limits of Deep CNNs for Pedestrian Detection
- READING NOTE: A Pursuit of Temporal Accuracy in General Activity Detection
- Sanliency detection ---my reading
- object detection
- 两个栈实现队列
- Java 通过 Jni 调用 C++代码
- Spring模拟aop静态代理案例<一>
- Cocos2d-x-------------------------------------------Label数字文字描边
- Proxy(代理)设计模式
- READING NOTE: Object Detection by Labeling Superpixels
- Android SDK 开发范例大全 ---3.14控制不同的文字字体
- 旧I/O实现的通道之Flip_clear VS 输入输出通道联通
- Linux下安装两个mysql5.5以上版本
- 初识云计算的三种服务模式 (IaaS SaaS PaaS)
- (java)Pascal's Triangle
- myeclipse自动生成实体类
- nginx日志简单认识
- 织梦 channelartlist 按指定的typeid排序[推荐]