運用多重亮度紅外線打光器之夜間監控前景擷取

Foreground Extraction for Night Surveillance Using Multi-intensity Infrared Illuminator

宋孟哲(Meng-Che Sung)

指導教授 ： 莊仁輝

國立交通大學/資訊學院/資訊科學與工程研究所/碩士(2014年)

https://doi.org/10.6842/NCTU.2014.00918

摘要

在夜間影像監控系統中，適當的照明對於影像品質扮演相當重要的角色。就一般紅外線打光器而言，因受限於亮度固定，可能因亮度不足造成遠距離的物體難以辨識；而光源充足的情形下，過於接近攝影機的物體則會出現影像過曝，以至於前景影像品質低落。
在本篇論文中，我們針對多重亮度紅外線打光器產生的不同亮度階層之影像進行前景擷取、挑選以及處理，進而獲得前景移動物在任何位置都適清晰適合觀察的狀態。首先，我們利用高斯混和模型對各個亮度階層的影像進行前景擷取，並透過影像品質評估，使系統能自動於各亮度中選擇出最符合人眼視覺的前景。接著，我們對於挑選出的前景邊緣將進行處理，精緻化並將不必要的部份進行修正去除。最後將挑選過最適合的前景形成新的影像輸出。

關鍵字

前景擷取 ； 夜間監控

並列摘要

In nighttime video surveillance, proper illumination plays a key role for the image quality. For ordinary IR-illuminators with fixed intensity, faraway objects are often hard to be identified due to insufficient illumination while nearby objects may suffer from over-exposure, resulting in image foreground/background of poor quality.
In this thesis we using a multi-intensity IR-illuminator to generate images with different illumination levels. After that, foreground extraction, channel selection and some processing will be execute. First, a GMM-based foreground extraction procedure is adopted for images acquired under each illumination level. With quality assessment of the outcome of such procedure, the system than selects visually most plausible foreground regions from different illumination levels to generate a set of new input data. After that, processing the edge of the foreground object with refinement and remove the unnecessary part. Finally, output a new video with the most plausible foreground object after the selection.

並列關鍵字

Foreground extraction ； Night Surveillance

參考文獻

[3] Yi-Ting Chen, Jen-Hui Chuang, Wen-Chih Teng, Horng-Horng Lin, and Hua-Tsung Chen, "Robust License Plate Detection in Nighttime Scenes Using Multiple Intensity IR-illuminator." IEEE International Symposium on Industrial Electronics (ISIE), pp. 893-898, 2012.

[6] Saeid Fazli, Hamed Moradi Pour, and Hamed Bouzari, "A Novel GMM-based Motion Segmentation Method for Complex Background." GCC Conference & Exhibition, pp. 1-5, 2009.

[7] Horng-Horng Lin, Jen-Hui Chuang, and Tyng-Luh Liu, "Regularized Background Adaptation: a Novel Learning Rate Control Scheme for Gaussian Mixture Modeling." IEEE Transactions on Image Processing, Vol. 20, No. 3 pp. 822-836, 2011.

[8] Zhong Ji, Yuting Su, Rongrong Qian, and Jintao Ma, "Surveillance Video Summarization Based on Moving Object Detection and Trajectory Extraction." 2nd International Conference on Signal Processing Systems (ICSPS), Vol. 2, pp. 250-253, 2010.

[9] Pakorn KaewTraKulPong, and Richard Bowden, "An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection." Video-Based Surveillance Systems, pp. 135-144, 2002.