【SiamRPN】《High Performance Visual Tracking With Siamese Region Proposal Network》

在这里插入图片描述

CVPR-2018

商汤科技



1 Background and Motivation

在这里插入图片描述

单目标跟踪的难点: illumination, deformation, occlusion and motion

基于深度学习的单目标跟踪精度越来越高,但是 real-time speed 还不足

作者在 SiamFC(【SiamFC】《Fully-Convolutional Siamese Networks for Object Tracking》(ECCV 2016 Workshops)) 的基础上引入 Faster RPN(【Faster RCNN】《Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks》(NIPS-2015)),提出 Siamese Region Proposal Network(SiamRPN)

让跟踪框更加的准确,并且省去多尺度测试耗费的时间

2 Related Work

  • Trackers based on Siamese network structure
  • RPN in detection
  • One-shot learning
    • Bayesian statistics based
    • meta-learning approaches

3 Advantages / Contributions

在这里插入图片描述

  • 提出 SiamRPN,which is end-to-end trained off-line with large-scale image pairs for the tracking taskf

  • irst work to formulate online tracking task as one-shot detection

  • 又快又强,achieves leading performance in VOT2015, VOT2016 and VOT2017 real-time challenges with the speed of 160 FPS

4 Method

在这里插入图片描述

Siamese subnetwork for feature extraction and region proposal subnetwork including the classification branch and regression branch for proposal generation.

template 产生的模板通道数也是 256,correlation operator 卷积核大小 4 x 4 x 2k x 256 or 4 x 4 x 4k x 256,

(1)Siamese feature extraction subnetwork

  • template branch,输入 z z z,网络 φ ( z ) \varphi(z) φ(z)

  • detection branch,输出 x x x, 网络 φ ( x ) \varphi(x) φ(x)

(2)Region proposal subnetwork

  • pair-wise correlation section
    在这里插入图片描述

    φ ( z ) \varphi(z) φ(z) -> [ φ ( z ) ] c l s [\varphi(z)]_{cls} [φ(z)]cls

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值