不穩定亮度變化之即時影像追蹤色彩系統演算法研究

A Real-time Color-based Object Tracking Algorithm to Irregular Illumination Variations

王碩裕(Shou-Yu Wang)

指導教授 ： 章明

中原大學/工學院/機械工程研究所/碩士(2002年)

https://doi.org/10.6840/cycu200200586

摘要

本研究提出一種新的色彩系統演算法，此色彩系統演算法以改良式H.S.I.色彩系統所建構而成，藉由H.S.I.色彩系統不受明亮度影響的架構下，本研究發展出一套亦不受明亮度影響的影像追蹤系統，在色彩系統轉換運算時間之效率上，R.G.B.色彩系統轉換至本研究之色彩系統的時間相較於轉換至傳統H.S.I.色彩系統時間可縮短70 ﹪，以轉換一張640×480像素的圖為例，在Intel P2-400電腦下，使用傳統H.S.I.色彩系統需0.312秒，而本研究之色彩系統平均僅需0.095秒，因此藉由本研究所發展出之色彩系統演算法，將能達到即時影像追蹤的功能。

關鍵字

色彩系統演算法

並列摘要

In this article we present a new color space algorithm for object tracking. This new color space algorithm can be free of illumination variations, because this new color space algorithm is robust for H.S.I. color space algorithm. And the time for R.G.B. color space transforming into this new color space algorithm is very short. For example, the average time of transforming a picture of 640×480 pixels is 0.095 seconds for using this new color space algorithm on a 400Mhz Pentium II PC. But for H.S.I. color space algorithm the average time is 0.312 seconds. This new color space algorithm can reduce the computational time.

並列關鍵字

color space algorithm

參考文獻

2. P. Payeur, H.L. Huy, and C.M. Gosselin, "Trajectory prediction for moving objects using artificial neural networks", IEEE Transactions on Industrial Electronics, Vol. 42, Iss. 2, pp.147-158, 1995.

3. L. Xu and D.C. Hogg, "Neural network in human motion tracking - An experimental study", Image and Vision Computing, Vol.15, no.8, pp.607-615, 1997.

4. I. Haritaoglu, D. Harwood, and L.S. Davis, "W/sup 4/: real-time surveillance of people and their activities", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, Iss. 8, pp. 809-830, 2000.

5. I. Haritaoglu, D. Harwood, and L.S. Davis, "A fast background scene modeling and maintenance for outdoor surveillance", 2000. Proceedings. 15th International Conference on Pattern Recognition, Vol. 4, pp. 179-183, 2000.

6. S. Huwer and H. Niemann, "Adaptive change detection for real-time surveillance applications", 2000. Proceedings. Third IEEE International Workshop on Visual Surveillance, pp. 37-46, 2000.