多種影像融合技術與物件軌跡探測之應用

近幾年，影像融合在影像處理的領域裡成為重要的議題，影像融合的目標為透過整合所有的同個場景的輸入影像，並依照其互補性資訊產生一個重組性的影像[1]。影像融合在場景觀察的增強性扮演重要的角色，由不同影像裝置所捕捉到的影像，藉由結合其各個不同的細節處資訊融合成包含最多且豐富的影像資訊，達到提升影像增強的目的。以系統層面來說，在輸入的來源影像可分成不同形態的輸入影像感應器或是可調式的不同參數設定之感應器。例如:不同的曝光度、不同的焦距、不同的光線來源。而輸出的結果融合影像比起輸入的影像擁有更適合人類或是機器感知的視覺效果，因此影像融合是個有效率的工具且被廣用於許多重要的應用。如: 醫學圖像學、顯微成像，遙感，計算機視覺和機器人。除此之外，我修改了傳統的顯著處偵測演算法的缺點，透過結合影像相減概念，修正顯著處偵測到冗餘的部分，將此命名為:『顯著處偵測基於影像相減』。而顯著處偵測通常應用在辨識出靜態『影像』中視覺會注意的區塊，因此我試圖將此應用在偵測動態『影片』中顯著的部分。透過此方式可以抓取出每一個影像幀，則可表示出影片中正在移動的物體。最後，我整合先前提到的不同曝光度的影融合法，以及影像相減顯著處偵測演算法，將兩系統整合達到最終的輸出結果圖，完成探測移動物體軌跡之目標，並且是富有高品質的影像增強效果。在展示部分，我們提供一些應用結果，包含偵測球類領域上的球體運動軌跡，以及監視器下的人物移動之過程。

關鍵字

影像融合；顯著處偵測

並列摘要

In recent years, image fusion has become an important issue in image processing community. The target of image fusion is to generate a composite image by integrating the complementary information from multiple source images of the same scene[1]. Image fusion play a role of enhancing the perception of a scene by combining detail information captured by different imaging sensors.For system, the input source images can be acquired from either different types of imaging sensors or a sensor whose optical parameters can be changed, e.g., at different exposure levels, at different focus levels, at different light source. And the output called fused image will be more suitable for human or machine perception than any individual source image. Image fusion has been used as an effective tool for many important applications, which include medical imaging, microscopic imaging, remote sensing, computer vision, and robotics. Besides, I revised the disadvantage of traditional Saliency Detection algorithm and made a combination of Image Subtraction concept to solve the defect of redundant detection named “Boosting Saliency Detection with Image Subtraction (BSD)”.Furthermore, Boosting Saliency Detectionis applied to recognize the noticeable part in image. I attempted to make use of the system on video detection. Using BSD, we can extracteach of saliency part in each frame, which represent moving object in the video. Last, I integrated both of Exposure Image Fusion and Boosting Saliency Detection algorithm to reach the final goal of moving object tracking with image quality enhancement. And present some applications in trajectory of ball in sport field and motion tracking under the monitor

並列關鍵字

image fusion ； Saliency Detection

參考文獻

[1] Yu Liu ,Shuping Liu a ,Zengfu Wang, A general framework for image fusion based on multi-scale transform and sparse representation, 2014

[2] Jianbing Shen, Ying Zhao, Shuicheng Yan, and Xuelong Li, Exposure Fusion Using Boosting Laplacian Pyramid, 2014

[3] T. Mertens, J. Kautz and F. Van Reeth, Exposure Fusion: A Simple and Practical Alternative to High Dynamic Range Photography, 2009

[4] Deepali Sale, Rajashree Bhokare, and Dr. Madhuri A. Joshi, Multiresolution Image Fusion Approach For Image Enhancement, 2015

[5] MALIK J. and PERONA P.: Preattentive texture discrimination with early vision mechanism. Journal of the Optical Society of America 7, 5 (May 1990), 923–932.

國際替代計量

多種影像融合技術與物件軌跡探測之應用

全文下載

主題瀏覽