READING NOTE: Object Detection from Video Tubelets with Convolutional Neural Networks
2016-05-25 18:48
555 查看
TITLE: Object Detection from Video Tubelets with Convolutional Neural Networks
AUTHER: Kai Kang, Wanli Ouyang, Hongsheng Li, Xiaogang Wang
ASSOCIATION: The Chinese University of Hong Kong
FROM: arXiv:1604.04053
A special temporal convolutional neural network is proposed to incorporate temporal information into object detection from video.
Image object proposal. The regions are generated in each frame by Selective Search and classified by AlexNet of 200 categories. It is a similar method to R-CNN. The region with scores lower than a threshold are remove and the rest are the proposals.
Obejct proposal scoring. The proposals are scored by a 30-category classifier deprived from GoogleNet. And the proposals with higher scores are kept.
High-confidence proposal tracking. The proposals with higher scores are tracked and the overlapped proposals are pressed using IOU. The trackes are tubelet proposals.
Tublet box perturbation and max-pooling. As the tracking result may drift, multiple regions are generated around tubelet proposals. All the regions are sent to the CNN in step 2 and sorted by the scores. Select the region of highest score to replace the one in tubelet.
Temporal convolution and re-scoring. Temporal Convolutional Network (TCN) is proposed that uses 1-D serial features including detection scores, tracking scores, anchor offsets and generates temporally dense prediction on every tubelet box. The tubelet with high detection score are regarded as detection result. However, TCN has not been well explained in this work
Too many CNN operations.
AUTHER: Kai Kang, Wanli Ouyang, Hongsheng Li, Xiaogang Wang
ASSOCIATION: The Chinese University of Hong Kong
FROM: arXiv:1604.04053
CONTRIBUTIONS
A complete multi-stage framework is proposed for object detection in videos.A special temporal convolutional neural network is proposed to incorporate temporal information into object detection from video.
METHOD
The main steps of the method is shown in the following figure.Image object proposal. The regions are generated in each frame by Selective Search and classified by AlexNet of 200 categories. It is a similar method to R-CNN. The region with scores lower than a threshold are remove and the rest are the proposals.
Obejct proposal scoring. The proposals are scored by a 30-category classifier deprived from GoogleNet. And the proposals with higher scores are kept.
High-confidence proposal tracking. The proposals with higher scores are tracked and the overlapped proposals are pressed using IOU. The trackes are tubelet proposals.
Tublet box perturbation and max-pooling. As the tracking result may drift, multiple regions are generated around tubelet proposals. All the regions are sent to the CNN in step 2 and sorted by the scores. Select the region of highest score to replace the one in tubelet.
Temporal convolution and re-scoring. Temporal Convolutional Network (TCN) is proposed that uses 1-D serial features including detection scores, tracking scores, anchor offsets and generates temporally dense prediction on every tubelet box. The tubelet with high detection score are regarded as detection result. However, TCN has not been well explained in this work
ADVANTAGES
The TCN help reduce the negative effect caused by the large variations of detection scores along the same track.DISADVANTAGES
Too many stages.Too many CNN operations.
相关文章推荐
- FreeType, FFmpeg, SDL, 图像处理软件, Mac OS X, Objective-C
- iOS开发实用技巧—Objective-C中的各种遍历(迭代)方式
- Objective-C 和 Swift互相操作
- READING NOTE: R-FCN: Object Detection via Region-based Fully Convolutional Networks
- ORA-12838: cannot read/modify an object after modifying it in parallel
- uva,132 Bumpy Objects (凸包,角度)
- JavaScript基础——引用类型(一)Object类型、Array类型
- objective-c学习推荐网站
- ImportError: libcudart.so.7.0: cannot open shared object file: No such file or directory
- objective-c中关联引用的底层实现
- [ObjectC]Objective-C内存管理之---属性修饰词
- QT与JavaScript互调 javaScriptWindowObjectCleared()信号
- javascript调用qt javaScriptWindowObjectCleared()信号
- objective-c启用ARC时的内存管理
- IllegalArgumentException:Bean object must not be null
- struts2启动报错com/opensymphony/xwork2/spring/SpringObjectFactory.java:220:-1
- 关于ORA-04021的解决办法(timeout occurred while waiting to lock object)
- java入门教程-4.9Java Object类
- [Ruby笔记]13.Ruby object .replace("") .dup .freeze
- Objective-C ---NSFileManager NSFileHandle (梳理整理)