基於顯著特性之靜態路標偵測與辨識系統

Saliency-based Detection and Recognition of Static Waymarks

林瑋國(Wei-Guo Lin)

指導教授 ： 王聖智

國立交通大學/電機學院/電子工程系所/碩士(2010年)

https://doi.org/10.6842/NCTU.2010.01029

摘要

在本論文中，我們提出一套基於顯著特性對靜態路標的偵測與辨識系統。使用者必須取得場景影片，再於影片中圈選出靜態路標，此路標必須滿足三種物理特性: 1)強烈對比，2)簡單紋理和3)規則形狀。利用這些特性，我們設計顯著特性的偵測，此方法可以快速的在影像中找尋候選區域。於這些區域中，再利用有方向性的濾波器組合和擁有色調、飽和度和亮度的色彩空間，分別分析形狀與顏色，進而辨識是否為使用者圈選的靜態路標。在本系統中，我們將會遇到下列的困難挑戰:1)亮度變化，2)物體的縮放，與 3)旋轉，4)不同路標的形狀考量，以及5)不平衡的訓練資料。

關鍵字

路標 ； 偵測與辨識 ； 顯著

並列摘要

In this thesis, we propose a system of saliency-based detection and recognition for static waymarks. First the users have to capture the video and in the video select the static waymarks which have the three physical properties: 1) strong contrast, 2) simple texture, and 3) regular shape. Based on these properties, we design the saliency detection which can fast find the candidate region in the image. In the region, the directional filter banks and HSV color space will analyze the shape and the color respectively for recognition. With our system, we consider the following challenges:1) lighting change, 2) scale and 3) rotation of objects, 4) different shapes of waymarks, and 5) imbalanced training data.

並列關鍵字

Waymarks ； Detection and Recognition ； Saliency

參考文獻

[2] Y. Xie, L.-F. Liu, C.-H. Li, and Y.-Y. Qu, “Unifying visual saliency with hog feature learning for traffic sign detection,” IEEE Symposium on Intelligent Vehicles, pp. 24 –29, June 2009.

[3] A. de la Escalera and L. Moreno, “Road traffic sign detection and classification.” IEEE Trans. Indust. Electronics, 44:848–859, 1997.

[4] J. Miura, T. Kanda, and Y. Shirai, “An active vision system for real-time traffic signs recognition, IEEE Symposium on Intelligent Vehicles, pp. 52.57, Oct 2002.

[5] S. Lafuente-Arroyo, P. Gil-Jiménez, R. Maldonado-Bascón, F. López-Ferreras, and S. Maldonado-Bascón, “Traffic sign shape classification evaluation I: SVM using distance to borders,” in Proc. IEEE Intell. Veh. Symp., Las Vegas, NV, pp. 557–562 , Jun. 2005.

[6] L. Itti, C. Koch and E. Niebur, "A model of saliency-based visual attention for rapid scene analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, pp. 1254-1259, 1998.