传感器(英文名称:transducer/sensor)是一种检测装置,能感受到被测量的信息,并能将感受到的信息,按一定规律变换成为电信号或其他所需形式的信息输出,以满足信息的传输、处理、存储、显示、记录和控制等要求。

VIP内容

题目: Moving Objects Detection with a Moving Camera: A Comprehensive Review

摘要:

在大约30年的时间里,许多研究团队致力于在各种挑战性环境中检测移动对象的大挑战。最初的应用涉及静态相机,但随着移动传感器的兴起,对移动相机的研究也逐渐出现。在这项调查中,我们建议识别和分类在文献中发现的不同的现有的方法。为此,我们建议根据场景表示的选择:一个平面或多个部分来对这些方法进行分类。在这两类方法中,根据8种不同的方法进行分组:全景背景减法、双摄像头、运动补偿、子空间分割、运动分割、平面+视差、多平面、分块图像分割。本文介绍了静态相机的方法以及静态相机和移动相机的挑战。本文还对公开数据集和评价指标进行了研究。

作者简介:

Marie-Neige Chapel,2017年9月在里昂第一大学获得计算机科学博士学位,博士论文题目是“运动物体检测与运动相机”。研究重点是在摄像机运动引起的视频流中,运动物体的真实运动与视运动的区别。并且提出了一种新的方法,使用几何线索来分类特征点为静态或移动。通过对物体的静态估计,通过对三维欧几里得距离随时间的比较,可以区分运动的物体和运动相机视频流中的静态物体。个人主页:https://mnchapel.github.io/

成为VIP会员查看完整内容
0
16

最新论文

Sweep coverage is to realize the periodic coverage of targets by planning the periodic sweeping paths of mobile sensors. It is difficult for sensors to reduce energy consumption by reducing the moving distances. Therefore, charging technology is the best way to extend the lifetime of the sweep coverage network. This paper studies the sweep coverage of rechargeable sensors: the sensors are rechargeable, constantly sweep between the target points and the charging stations not only tp meet the periodic coverage requirement of the target points, but also need to return to the charging stations during the charging period to avoid running out of energy. This paper proposes the general definition of Chargeable Sweep Coverage (CSC) problem for the first time, and studies the complexity of the CSC problem by analyzing CSC problems under different constraints, and then proposes two kinds of CSC problems under special constraints: 1) The sensors need to return to their original charging stations for charging; 2) The sensors can go to different charging stations for charging, and the number of charging stations is 2. Both of these problems are NP-hard. In this paper, these two problems are modeled as the maximum set coverage problem, and the approximation algorithms are obtained by reducing the number of candidate paths to polynomials. The validity and scalability of the proposed algorithms is proved by theoretical proof and experimental simulation.

0
0
下载
预览
Top