頁籤選單縮合
題名 | 利用多重影像匹配獲取測量車影像點位之物空間坐標=Determination of Object Point Coordinates by MMS Image Sequences Using Multiple Image Matching |
---|---|
作者姓名(中文) | 謝佳諭; 曾義星; | 書刊名 | 航測及遙測學刊 |
卷期 | 15:3 2010.09[民99.09] |
頁次 | 頁263-279 |
分類號 | 440.98 |
關鍵詞 | 測量車影像序列; 多影像匹配; 物空間匹配; 多視窗匹配; MMS image sequences; Multi-image matching; Matching in object space; Multiple window matching; |
語文 | 中文(Chinese) |
中文摘要 | 測量車影像序列富含測量車行經路線帶狀的空間資訊,透過測量車的定位及定向系統,得影像的內外方位,因此可利用影像共軛點以前方交會計算興趣物點的物空間坐標,而共軛點的獲取,相較於人工點選,利用多影像匹配方法獲取更具效率。但存在於影像的尺度變化、視角不同及遮蔽問題可能影響匹配的正確性,因此本研究將於物空間進行影像匹配,並配合假設面的建立,改善尺度變化及視角不同的問題,更利用影像挑選機制及利用多視窗匹配減輕遮蔽問題的影響。實驗結果顯示:特徵點位匹配成功率達90%;而控制點的坐標求取,具50公分的準確度,10公分的精度,若改善定位系統之穩定性,將可提高點位坐標的準確度。 |
英文摘要 | The coordinates of interested points can be determined by space intersection of the images, whose interior and exterior orientation parameters are determined from the navigation and calibration data. Obtaining conjugate points of image sequences by image matching is much more efficient than manual measurement. However the factors of scale variations, different field of view, and occlusion may result in incorrect matching points. In this research, image matching in object space with virtual surface is proposed to overcome the problem of matching in image space. The process to filter out occluded images is proposed, and the remaining useful images are kept for multiple image matching with multiple windows, which is developed to ease the problems caused by complex backgrounds. The test results of the experiments show the proposed method can deliver correct matching results good to about 90%. The determined coordinates are about 10 cm in precision, and about 50 cm in accuracy. Accuracy can be improved, if the positioning and orientation system of the MMS can be improved. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。