智慧型交通監控系統之在真實世界變動頻寬下的自動移動物體擷取METHOD AND APPARATUS FOR MOVING OBJECT DETECTION USING FISHER’S LINEAR DISCRIMINANT BASED RADIAL BASIS FUNCTION NETWORK

專利類型

發明

專利國別 (專利申請國家)

美國

專利申請案號

14/210,465

專利證號

US 9,286,690 B2

專利獲證名稱

智慧型交通監控系統之在真實世界變動頻寬下的自動移動物體擷取METHOD AND APPARATUS FOR MOVING OBJECT DETECTION USING FISHER’S LINEAR DISCRIMINANT BASED RADIAL BASIS FUNCTION NETWORK

專利所屬機關 (申請機關)

國立臺北科技大學

獲證日期

2016/03/15

技術說明

在交通監控系統中的自動移動物體擷取逐漸地受到重視。在真實世界的變動頻寬下，影像傳輸時常會遭受到不穩定的頻寬等因素，位元率控制機制會被啟用來調整最適合的位元頻寬，造成了變動的頻寬出現。然而，因為在頻寬不斷的變動情形下，移動物體的偵測非常的困難。本文提出一個基於Fisher線性判別之RBF類神經網路的新式移動物體偵測演算法來達到在真實世界中的精確和完整移動物體偵測。量化和值化的實驗結果顯示我們的方法明顯的勝過其他傳統知名的移動物體偵測演算法。 Motion detection plays an important role in video surveillance system. Video communications over wireless networks can easily suffer from network congestion or unstable bandwidth, especially for embedded application. A rate control scheme produces variable bit-rate video streams to match the available network bandwidth. However, effective detection of moving objects in variable bit-rate video streams is a very difficult problem. This paper proposes an advanced approach based on the counter-propagation network through artificial neural networks to achieve effective moving object detection in variable bit-rate video streams. In this paper, we compare our method with other state-of-the-art methods. The overall results show that our proposed method substantially outperforms other state-of-the-art methods by Similarity and F1 accuracy rates of 83.34% and 89.71%, respectively.

備註

本會(收文號1120059208)同意該校112年9月4日北科大產學字第1127900224號函申請終止維護專利

連絡單位 (專責單位/部門名稱)

專利技轉組

連絡電話

02-87720360

網址