English  |  正體中文  |  简体中文  |  Items with full text/Total items : 43312/67235
Visitors : 2138613      Online Users : 9
RC Version 5.0 © Powered By DSPACE, MIT. Enhanced by NTU/NCHU Library IR team.

Please use this identifier to cite or link to this item: http://nchuir.lib.nchu.edu.tw/handle/309270000/154564

標題: 時間視覺顯著特徵圖與其應用
Temporal Visual Saliency Map and its Application
作者: 楊智翔
Yang, Zhi-Xiang
Contributors: 黃春融
Chun-Rong Huang
關鍵字: 影片視覺顯著特徵圖;軌跡熵值
Video saliency map;trajectory entropy
日期: 2012
Issue Date: 2013-11-21 10:56:50 (UTC+8)
Publisher: 資訊網路多媒體研究所
摘要: 本篇論文提出了一個基於軌跡熵(Entropy)值的方法以偵測影片中的視覺顯著特徵圖。藉由在影片中偵測並追蹤這些特徵點,我們特別設計一個軌跡表示法來代表此段影片。接下來,我們的方法參考影片中物體長期的移動軌跡來減輕只評估相鄰畫面間的運動變化所造成的雜訊。在實驗結果中,我們的方法能夠正確地得到在影片中移動時間長度不同物體的軌跡,然後利用計算各條軌跡的運動速度及加速度的熵值進而得到時空視覺顯著特徵圖。
This paper presents a novel method for detecting video saliency maps based on trajectory entropy. Our method utilizes long-term motions to alleviate short-term noises, and leads to spatially and temporally coherent saliency maps. Specifically, a set of collaborative trajectories, which are extracted by detecting and tracking salient points in the video frames, is used to represent a given video. We show that the object motions of various temporal lengths in the video can be faithfully captured by these trajectories, and the saliency maps can hence be established by taking the entropies of each trajectory with respect to velocity and acceleration into account. The experimental results demonstrate the effectiveness of our approach.
Appears in Collections:[依資料類型分類] 碩博士論文

Files in This Item:

File SizeFormat






聯絡網站維護人員:wyhuang@nchu.edu.tw,04-22840290 # 412。

DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU/NCHU Library IR team Copyright ©   - Feedback