以影像辨識為基礎之停車場車位管理之研究

A Study of Parking Space Management based on Image Recognition Technigues

李天翔(Tian-Siang Li)

指導教授 ： 包蒼龍

大同大學/電機資訊學院/資訊工程學系所/碩士(2010年)

摘要

隨著經濟快速成長，自用車輛急速增加，在百貨公司或量販店的停車場，這些地方可能有數百個到數千個停車位，雖然目前停車場皆設有空位數量的顯示，但是對可停放位置並無精確定位，導致駕駛仍需浪費許多時間找尋車位，本研究希望藉由從現有的監視攝影設備上所獲取到的影像進行停車位判斷，讓一進入停車場的車主能夠馬上取得車位的資訊，縮短尋找車位的時間。
本研究是以影像辨識為基礎，可以即時偵測車輛進出停車位，所用的方法簡單不需大量的計算與儲存空間。我們先進行停車格座標定位，經影像處理技術(影像相減、二值化)及車位辨識等步驟，就能快速分辨出停車空位，再結合引導燈號，讓進入車場的車輛直接至有空位的地方，如此可免除車主自己尋找車位，同時停車管理系統也記錄該車的停放位置，當車主回來取車時，可以藉由系統查詢立即知道車輛的停放區域，避免因忘記停車位置而盲目尋找。

關鍵字

影像二值化 ； 背景相減

並列摘要

Due to recent economic developments, the number of cars is rapidly expanding. So, shopping malls, department stores, movie theaters and other public places all have a need to provide large number of parking spaces. Currently, in most parking lots a person can discover, on a display at the lot entrance, how many spaces are available in the lot. However, these displays do not show where the spaces are. Therefore, customers often need to spend a lot of time in finding the parking space during busy hours.
In this thesis, we propose an architecture and methods to expand the capabilities of the existing displays panel to be able to show the location of the empty spaces. Our research is based on the proper use of image processing techniques. This algorithm is simple and does not require a lot of computational power to accelerate the processing. We use a geometric type display panel and light to show the empty lots to let the driver quickly identify the available parking space.

並列關鍵字

image binarization ； background subtraction

參考文獻

[8]黃志泰，「基於無線射頻與電腦視覺技術的停車位導引系統」，運輸計畫季刊，第39卷，第1期，41-72頁，99年3月。

[1]Wang, X. G. and Hanson, A. R., “Parking Lot Analysis and Visualization from Aerial Images,” Proceedings of Fourth IEEE Workshop Applications of Computer Vision, IEEE Computer Society Press, pp. 36-41, 1998.

[2]Masaki, I., “Machine-Vision Systems for Intelligent Transportation Systems,” Proceedings of IEEE Conference on Intelligent Transportation System, Vol. 13, No.6, pp. 24-31, 1998.

[3]True, N., “Vacant Parking Space Detection in Static Images,” http://www.cs.ucsd.edu/classes/wi07/ cse190-a/reports /ntrue.pdf, 2008.

[9]Chang, S. L., L. S. Chen, Y. C. Chung and S. W. Chen, “Automatic license plate recognition,” IEEE Transactions on Intelligent Transportation Systems, pp.42-53, 2005.