影像式交通偵測系統用於解決複雜環境及交通狀況之研究

Abstract

在本論文中，我們發展了一個用來解決複雜環境及交通狀況的影像式車輛辨識系統。在文中，我們提出了許多的法則，用來解決發生在複雜環境及塞車情況所發生的問題，這些複雜環境包含了:晴天、雨天、清晨、黃昏、陰天及夜晚。在最近的許多研究中，我們可以發現有很多知名的車輛辨識方法，都採取背景收斂的方式來達成車輛辨識的效果。這些法則均需要不斷的更新背景圖像，否則光線亮度的變化，將很容易影響偵測的品質。車輛偵測在複雜環境下會面臨到很多的困難；例如：亮度的變化、陰影的效應及塞車時的車輛交疊問題。本論文最重要的貢獻在於提出了一個不需要參考及更新背景圖像並且可以運用於複雜環境下的可調整式車輛偵測系統。首先，我們利用直方圖展開法消除了光線及氣候效應。接下來，利用灰階差值法分割出移動物件。最後，利用適當的追蹤以及錯誤補償法則提高追蹤的正確性。除此之外，本系統可以自動偵測出許多有用的交通數據。這些數據包含了：車流量、車速及車型。利用這些數據，可以協助行控中心控制交通流量，並且可以提供駕駛者很好的駕駛參考。最後透由實驗數據的結果顯示本系統展現了穩健、精準及有效率的克服複雜環境及交通狀況。

In this study, a vehicle detection approach for complex environments is presented. This paper proposes methods for solving problems of vehicle detection in traffic jams and complex weather conditions such as sunny days, rainy days, sunrise time, sunset time, cloudy days, or night. In recent researches, there have been many well-known vehicle detectors utilizing background extraction methods to recognize vehicles. In these studies, the background image needs to be updated continuously; otherwise the luminance variation will impact the detection quality. The vehicle detection under various environments will have many difficulties such as illumination vibrations, shadow effects and vehicle overlapping problems appearing in traffic jams. The main contribution of this paper is to propose an adaptive vehicle detection approach in complex environments to detect vehicles directly without extracting and updating a reference background image in complex environments. In the proposed approach, histogram extension deals with the removal of the effects of weather and light impact. Gray-level differential value method is utilized to extract moving objects directly from the images. Finally, tracking and error compensation are applied to refine the target tracking quality. In addition, many useful traffic parameters are evaluated. These useful traffic parameters including traffic flows, velocity and vehicle classifications can help in controlling traffic, and provide drivers good guidance. Experimental results show that the proposed methods are robust, accurate and powerful enough to overcome complex weather conditions and traffic jams.