Multi-target tracking with Single Moving Camera
引自:http://www.eecs.umich.edu/vision/mttproject.html
- Wongun Choi, Caroline Pantofaru, Silvio Savarese, "A General Framework for Tracking Multiple People from a Moving Camera", PAMI (under revision, accepted with minor revision).
- Wongun Choi and Silvio Savarese, "Multiple Target Tracking in World Coordinate with Single, Minimally Calibrated Camera", ECCV 2010 (pdf).
- Wongun Choi, Caroline Pantofaru, Silvio Savarese, "Detecting and Tracking People using an RGB-D Camera via Multiple Detector Fusion" CORP (in conjunction with ICCV) 2011 (pdf).
In this project, we aim to solve a challenging problem of multi-target tracking under unknown camera motion. To meet the most general condition of tracking applications, we did not rely on the use of stereo-camera and SfM algorithm. To cope with the unknown camera motion as well as frequent occlusion between targets, the targets were tracked in the 3D coordinate and the camera's parameters are estimated in a joint fashion. Specifically, our goals are to: i) solve the multi-object tracking problem by using a single uncalibrated moving camera; ii) handle complex scenes where multiple pedestrians are moving at the same time and occluding each other; iii) estimate the 2D/3D temporal trajectories within the camera reference system.
The key contribution of our work relies on the fact that we simultaneously estimate the camera parameters (such as focal length and camera pose) and track objects (such as pedestrians) as they move in the scene. Tracks provide cues for estimating camera parameters by using their scale and velocity in the image plane; at the same time, camera parameters can help track objects more robustly as critical prior information becomes available. This, in turn, allows us to estimate object 3D trajectories in the camera reference system. We utilize a simplified camera model that allows to find a compact (but powerful) relationship between the variables (targets and camera parameters) via camera projection constraints. The identification of a handful of feature tracks associated with the static background allows us to add additional constraints to the camera model. Eventually, we frame our problem as a maximum-posterior problem in the joint variable space. In order to reduce the (otherwise extremely) large search space caused by the high dimensionality of the representation, we incorporate MCMC particle filtering algorithm which finds the best explanation in sequential fashion. Notice that, unlike previous methods using MCMC, our method is the first that uses MCMC for efficiently solving the joint camera estimation and multi-target problem.
The second key contribution is that we obtain robust and stable tracking results (i.e. uniquely associate object identities to each track) by incorporating interaction models. Interaction between targets have been largely ignored in the object tracking literature, due to the high complexity in modeling moving targets and the consequential computational complexity. The independent assumption is reasonable when the scene is sparse (only few objects exists in the scene). In a crowded scene, however, the independent motion model often fails to account for the target's deviation from the prediction, e.g. if a collision is expected, targets will change their velocity and direction rapidly so as to avoid a collision. Thus, modeling interactions allows us to disambiguate occlusions between targets and better associate object labels to underlying trajectories. This capability is further enhanced by the fact that our trajectories are estimated in 3D rather than in the image plane. Our interaction models are coherently integrated in the graphical model introduced above.
We validate our theoretical results in a number of experiments using our own dataset (provided below) and the publicly available ETH dataset. Also, a new RGB-D dataset collected using Kinect camera mounted on a robot (will be available soon) is used to evaluate our algotithm. Please see the eccv paper and workshop paper for more details. The poster presented in ECCV is available as well.
Dataset
Semi-static datasets used in our research can be found here. All the videos were taken by a person holding a single hand-held camera. The videos contain multiple number of targets, panning of the camera, sudden camera's shakes, etc.
Result Video
Result Image
Source Code
Launch SVN client and checkout (e.g. svn co link):
- Version 0.5 release(August 7th, 2012): C++ code with a demo at http://mtt-umich.googlecode.com/svn/tags/release-0.5
Bibtex
@InProceedings{Wongun_iccvw_2011,
author = {Wongun Choi and Caroline Pantofaru and Silvio Savarese},
title = {Detecting and Tracking People using an RGB-D Camera via Multiple Detector Fusion},
booktitle = {CORP in conjunction with ICCV},
year = {2011},
}
@InProceedings{Wongun_eccv_2010,
author = {Wongun Choi and Silvio Savarese},
title = {Multiple Target Tracking in World Coordinate with Single, Minimally Calibrated Camera},
booktitle = {European Conference on Computer Vision, ECCV},
year = {2010},
}
Acknowledgement
This project is sponsored by NSF AEGER (award #1052762) and Toyota. This work is in collaboration with Dr. Caroline Pantofaru (Willow Garage).
Last Updated: September 12th, 2012
Contact : wgchoi at umich dot edu
Multi-target tracking with Single Moving Camera的更多相关文章
- Video Target Tracking Based on Online Learning—深度学习在目标跟踪中的应用
摘要 近年来,深度学习方法在物体跟踪领域有不少成功应用,并逐渐在性能上超越传统方法.本文先对现有基于深度学习的目标跟踪算法进行了分类梳理,后续会分篇对各个算法进行详细描述. 看上方给出的3张图片,它们 ...
- [Artoolkit] ARSimpleNativeCarsProj for Multi Markers Tracking
效果简直了,但代码架构有点坑,慢慢道来. libc++_shared.so应该是c++的库:libARWrapperNativeCaresExample.so也有对应的c++文件:那么,libARWr ...
- Video Target Tracking Based on Online Learning—TLD单目标跟踪算法详解
视频目标跟踪问题分析 视频跟踪技术的主要目的是从复杂多变的的背景环境中准确提取相关的目标特征,准确地识别出跟踪目标,并且对目标的位置和姿态等信息精确地定位,为后续目标物体行为分析提供足 ...
- Video Target Tracking Based on Online Learning—TLD多目标跟踪算法
TLD算法回顾 TLD(Tracking-Learning-Detection)是英国萨里大学的一个捷克籍博士生Zdenek Kalal在其攻读博士学位期间提出的一种新的单目标长时间(long ter ...
- 如何将SAP Multi Target应用部署到SAP云平台的Cloud Foundry环境去
SHINA是SAP HANA Interactive Education的缩写,是一个demo应用,用于演示如何开发SAP HANA原生应用. 这个应用包含了sample数据以及HANA数据库表,vi ...
- cvpr2015papers
@http://www-cs-faculty.stanford.edu/people/karpathy/cvpr2015papers/ CVPR 2015 papers (in nicer forma ...
- Official Program for CVPR 2015
From: http://www.pamitc.org/cvpr15/program.php Official Program for CVPR 2015 Monday, June 8 8:30am ...
- Summary on Visual Tracking: Paper List, Benchmarks and Top Groups
Summary on Visual Tracking: Paper List, Benchmarks and Top Groups 2018-07-26 10:32:15 This blog is c ...
- Vuforia开发完全指南---License Manager和Target Manager详解
License Manager和Target Manager License Manager 对于每一个用Vuforia开发的AR程序来说,都有一个唯一的license key,在Unity中必须首先 ...
随机推荐
- 微信小程序navigator跳转失效
在编写小程序时遇到一个问题:使用 <navigator url='/pages/lists/index'>...</navigator>进行跳转没有反应.控制台也没有报错,ap ...
- parity 注记词
spousal tint untold around rosy daintily unrated sheep choice showpiece chirping gala
- Python3 数据类型-字典
字典是一种可变数据类型,且可存储任意类型对象. 字典使用大括号"{}"括起来,由键(key)和值(values)组成,键只能使用不可变类型定义,值可以使用可变类型{'键':'值'} ...
- net::ERR_ABORTED ,引入js文件出现报错的解决方法
在head头里面添加 <mvc:annotation-driven enable-matrix-variables="true"></mvc:annotation ...
- POJ 2187 Beauty Contest(凸包+旋转卡壳)
Description Bessie, Farmer John's prize cow, has just won first place in a bovine beauty contest, ea ...
- nodejs笔记--与Redis的交互篇(六)
原文地址:http://www.cnblogs.com/zhongweiv/p/node_redis.html 安装前准备 win64: Install python: http://www.pyth ...
- QT界面绘制学习记录
1. MVC结构中,model必须作为类的成员变量存在,不可再函数内部申明.否则,会出现函数调用结束,model找不到的错误. 2.QcomboBox可设置为左边空白,右侧一小箭头的形式.代码:com ...
- JDK中的泛型
Java中的泛型介绍: 起因: 1. JDK 1.4 以前类型不明确: ① 装入集合的对象被当作 Object 类型对待,从而失去了自己的原有类型: ② 从集合中取出时往往需要转型,效率低下,并且容易 ...
- 3ds Max学习日记(三)
今天把第三章搞完了,学的是样条线(splines)建模的一些操作.不过实习又有新任务了,得去研究一下如何将单张图片转化为三维模型(我擦,这神马操作),所以可能没有那么多时间愉快地与3ds max玩 ...
- 理解BitSet
先来看几道面试题: 1.统计40亿个数据中没有出现的数据,将40亿个不同数据进行排序. 2.现在有1千万个随机数,随机数的范围在1到1亿之间,要求写出一种算法,将1到1亿之间没有在随机数中的数求出来. ...