基於影像處理之速度估測系統

Velocity Estimation System based on Image Processing

楊浩(Hao Yang)

指導教授 ： 朱鴻棋

朝陽科技大學/資訊學院/資訊與通訊系/碩士(2015年)

摘要

隨著影像處理技術的快速進步，各種新的應用已被開發出來，例如：物件追踪、高度測量、空間測量、擴增實境、車輛速度預警、機器人視覺等等應用。而影像處理的優點是，可以進行圖像的修飾、辨識以及分析，並利用數位影像做出以上的應用，而且這些應用陸續的增加中。影像處理的缺點，例如是需要測量高精準度的應用，會因為硬體設備好壞使得拍取影像源時產生誤差，雖然跟實際使用現有的測速儀器相比測速精準略為較低，利用影像處理法還是可以做修正補償的方法來讓量測結果接近真實。近年來行動裝置的普及和其硬體功能的提升，在攝影鏡頭的硬體效能更是快速提升，隨著硬體提升和其便利性，許多利用攝影鏡頭的應用陸續增加，在影像處理的許多應用可以慢慢的轉移到手機上面，所以本文提出基於影像處理之估測速度系統，利用影像處理的方法進行速度估測的功能實行在行動裝置上，只要持有行動裝置就可以使用本系統進行簡單的速度估測。本研究所提出的速度估測系統分為四個部分包括被測物體抓取、影像校正、軌跡追踪和物體速度估測。在最後本研究實驗結果可得到測速的平均誤差為3 %左右這證明我們的方法在測速有一定的準確度。

關鍵字

目標追蹤 ； 影像測速

並列摘要

The various new applications such as object tracking, altitude measurement, spatial measurement, augmented reality, vehicle speed warning, robot vision, etc. have been developed with the progress of image processing technologies. Moreover, those applications based on digital image processing technologies by which photo editing, recognition and analysis are advantageously accomplished have been increasing constantly. The image processing technologies, however, incurs some drawbacks such as errors of a captured image source induced by hardware in applications of high-precision measurement. In contrast to traditional technologies with higher precision, the image processing technologies which rely on error offset techniques still allow measured results to edge closer to reality. In recent years, the mobile devices with hardware functions improved are available to the general public. In this regard, the fast improved hardware efficiency and convenience of photographic lenses accelerate more applications, for example, the image processing applications have been transferred to mobile phones gradually. In this research, we offer an image-based speed estimation system which depends on image processing technologies for simple speed measurement in a mobile device held by a user. The speed estimation system in our research features four functions such as acquisition of an object to be measured, image correction, trajectory tacking and speed estimation. As shown in experimental results, the measured speeds with the mean error of 3.1% demonstrated a certain degree of precision of the speed estimation system.

並列關鍵字

Velocity estimation ； object tracking

參考文獻

[3] K.Z. Lee, ”A SimpleCalibration Approach to Single View Height Estimation,” Ninth Conference on Computer and Robot Vision (CRV), pp. 161-166, May. 2012.

[4] C.T. Chuang, W.Y. Wang , C.P. Tsai ,Y.H. Chien , and M.C. Lu, ”An image-based area measurement system,” International Conference on System Science and Engineering (ICSSE), pp. 644-648, June. 2011.

[6] 黃世傑， “基於視覺測速之車速預警系統”國立成功大學工程科學研究所碩士論文。2012

[7] Z. Zhang,“A Flexible New Technique for Camera Calibration,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, pp. 1330-1334, Nov. 2000.

[9] J. Stephen, and D.Olivier, “A theory of self-calibration of a moving camera,” International Journal of Computer Vision, vol. 8, pp. 123-151, Aug. 1992.