目标跟踪MovingTargetClassificationandTrackingfromReal-timeVideo资源-CSDN文库

目标跟踪

需积分: 10 55 浏览量 2010-10-18 20:17:40 上传评论 1 收藏 1.73MB PDF 举报

资源推荐

资源详情

资源评论

Moving Target Classiﬁcation and Tracking from Real-time Video

Alan J. Lipton Hironobu Fujiyoshi

The Robotics Institute

Carnegie Mellon University

5000 Forbes Ave

Pittsburgh, PA, 15213

email:

ajl

hironobu

raju

@cs.cmu.edu

URL: http://www.cs.cmu.edu/˜ vsam

Raju S. Patil

Abstract

This paper describes an end-to-end method for extract-

ing moving targets from a real-time video stream, classi-

fying them into predeﬁned categories according to image-

based properties, and then robustly tracking them. Moving

targets are detected using the pixel wise difference between

consecutive image frames. A classiﬁcation metric is ap-

plied these targets with a temporal consistency constraint

to classify them into three categories: human, vehicle or

background clutter. Once classiﬁed, targets are tracked by

a combinationof temporaldifferencingand templatematch-

ing.

The resulting system robustly identiﬁes targets of inter-

est, rejects background clutter, and continually tracks over

large distances and periods of time despite occlusions, ap-

pearance changes and cessation of target motion.

1. Introduction

The increasing availabilityof video sensorsand highper-

formance video processing hardware opens up exciting pos-

sibilities for tackling many video understanding problems

[9]. It is important to develop robust real-time video under-

standing techniques which can process the large amounts of

data attainable. Central to many video understanding prob-

lems are the themes of target classiﬁcation and tracking.

Historically, target classiﬁcation has been performed on

single images or static imagery [12, 7]. More recently, how-

ever, video streams have been exploited for target detection

[6, 14, 10]. Many methods like these, are computationally

expensive and are inapplicable to real-time applications, or

require specialised hardware to operate in the real-time do-

main. However, methods such as Pﬁnder [14],

[6] and

Beymer et al [2] are designed to extract targets in real-time.

The philosophy behind these techniques is the segmen-

tation of an image, or video stream, into object Vs. non-

object regions. This is based on matching regions of inter-

est to reasonably detailed target models. Another require-

ment of these systems is, in general, to have a reasonably

large number of pixels on target. For both of these rea-

sons, these methods would, by themselves, be inadequate

in a general outdoor surveillance system, as there are many

different types of targets which could be important, and it is

often not possible to obtain a large number of pixels on tar-

get. A better approach is one inwhich classiﬁcation is based

on simple rules which are largely independent of appear-

ance or 3D models. Consequently, the classiﬁcation metric

which is explored in this paper, is based purely on a target’s

shape, and not on its image content.

Furthermore, the temporal component of video allows a

temporal consistency constraint [4] to be used in the classi-

ﬁcation approach. Multiplehypotheses of a target’s classiﬁ-

cation can be maintained over time until the system is con-

ﬁdent that it can accurately classify the target. This allows

the system to disambiguate targets in the case of occlusions

or background clutter.

Many systems for target tracking are based on Kalman

ﬁlters but as pointed out by [8], they are of limited use be-

cause they are based on unimodal Gaussian densities and

hence cannot support simultaneous alternative motion hy-

potheses. A few other approaches have been devised, for

example, (a) Isard and Blake [8] present a new stochas-

tic algorithm for robust tracking which is superior to pre-

vious Kalman ﬁlter based approaches, and (b) Bregler [3]

presents a probabilistic decomposition of human dynamics

to learn and recognise human beings (or their gaits) in video

sequences.

This paper presents a much simpler method based on a

本内容试读结束，登录后可阅读更多

下载后可阅读完整内容，剩余6页未读，立即下载

评论收藏

内容反馈

zhangjingwei713

粉丝: 11
资源: 7

目标跟踪Moving Target Classification and Tracking from Real-time Vid...

最新资源

目标跟踪Moving Target Classification and Tracking from Real-time Vid...

A Twofold Siamese Network for Real-Time Object Tracking

eccv_Real-Time Compresssive Tracking

Real-Time & Stream Data Management

Real-Time BCI System Design

Vocal-Percussion-Classification-for-Real-Time-Context

室内定位文献 Classification and Comparison of Range-Based

texture-classification-based-on-BPNN-and-dictionary-master.zip

some resource of image fusion for object tracking and detection

FPGA-Based Parallel Hardware Architecture for Real-Time Image Classification

text-classification-cnn-rnn-master_RNN_CNN_

Detection and classification of peer-to-peer traffic - A survey.pdf

Matlab toolbox for classification and regression of multi-dimens

Large-Scale Video Classification with Convolutional Neural Networks

APQC Process Classification Framework (PCF) - Automotive (OEM)

video-classification-3d-cnn-pytorch-master.zip

Real-time Object Classification in Video Surveillance

机器学习分类模型 Introduction-to-ML-Classification-Models-using-scikit-learn-master.zip

imagenet-classification-with-deep-convolutional-neural-networks原版和翻译..rar

Qt 5实现串口调试助手 （源工程文件、0积分下载）

【SystemVerilog】路科验证V2学习笔记（全600页）.pdf

AutoSAR标准协议4.2.2

光伏-储能并网系统仿真.rar

NPPJSONViewer.zip

GD32替换STM32注意事项.pdf

XCP协议的规范文档

VS2015安装证书，JavaScript_ProjectSystem.msi，JavaScript_LanguageService.msi

CANoe通过CAPL脚本实现自动测试

蓝牙BLE协议中文版.pdf

最新资源

Qt 5实现串口调试助手（源工程文件、0积分下载）