使用LBP特徵之RGB-D物件檢索方法

RGB-D Object Retrieval with Local Binary Pattern Features

蔡明遠(Ming-Yuan Tsai)

指導教授 ： 杜維昌

義守大學/電機資訊學院/資訊工程學系/碩士(2018年)

摘要

隨著感測技術的日益成熟，RGB-D攝影機已大量應用在日常生活中，作為三維重建、移動追蹤、人機互動等多元用途。本研究主要探討大型RGB-D影像的物件檢索問題，首先使用背景相減法從影像中分割出物件，針對物件深度梯度的統計而得到幾何特徵，並對物件顏色量化的統計而得到顏色特徵。因物件表面中有細緻的顏色與深度變化，使用局部二值模式得到紋理特徵，並滿足物件的旋轉與縮放不變性。藉由多元特徵的資料比對，以期達到更好的物件檢索結果。

關鍵字

影像檢索 ； RGB-D影像 ； Kinect裝置 ； 特徵萃取

並列摘要

As sensing technology continues to advance, the use of RGB-D cameras in daily life has become routine, for various purposes such as three-dimensional reconstruction, moving tracking, and human-computer interaction. The research is mainly about object retrieval of large size RGB-D images. The first step is image segmentation by background difference. Then, obtain geometric features by gathering the statistics of depth image and image gradient; obtain color features by gathering the statistics of color quantification. Since the color and depth of the object’s surface slightly changes, local binary pattern is used in order to obtain the texture features, and to meet the rotational invariance and scale invariance of the object. Therefore, better results of object-detecting can be expected because of data matching of the various features.

並列關鍵字

image retrieval ； RGB-D image ； Kinect sensor ； feature extraction

參考文獻

[1] J. L. Guo and W. C. Du, “Two-Hand Gesture Recognition with Kinect Sensor,” Symposium on Digital Life Technologies, 2017.

[2] 郭家霖，基於Kinect感測裝置之雙手手勢辨識，義守大學資訊工程研究所碩士論文，2016.

[3] 郭姵萱，基於RGB-D影像之物件檢索方法，義守大學資訊工程研究所碩士論文，2017.

[4] Li Xiao and Li Xiao Hong, “Depth Image Analysis Optimized by Gradient-LBP for Gender Face Recognition,” Application Research of Computers, vol. 31, no. 11, pp. 3502-3505, 2014.

[5] 郭弘裕，基於RGB-D之影像分割方法，義守大學資訊工程研究所碩士論文，2017年。