處理車載攝影機所得影像以評估來自後方車輛的安全威脅

Assessing the Safety Threats from the Vehicles Behind by Processing the Images Captured from Vehicle On-Board Camera

藍昱淳(Yu-Chun Lan)

指導教授 ： 繆紹綱

中原大學/電機資訊學院/通訊工程碩士學位學程/碩士(2017年)

https://doi.org/10.6840/cycu201700596

摘要

近年來，許多相繼推出的車輛安全輔助系統，大多是針對前方視野的威脅，針對後方的系統非常稀少，但當駕駛人要變換車道時，需要同時注意前後方的威脅，有時會造成捉襟見肘、顧此失彼的情況，造成意外的發生。
有鑑於此，本研究提出利用車載攝影機所得的影像，用來偵測後方車輛威脅，藉此來評估變換車道的可行性，提供意見給駕駛判斷行車狀況，降低駕駛人對於後方威脅的精神負擔，使駕駛人可以更專注於前方的威脅，提升安全性，以達到行車安全的目的。
本研究將所得到的影像先進行前處理，將左右兩旁的車道擷取出來，以消除周遭複雜的背景環境，增加系統運行速度。接著分成白天偵測模式以及夜晚偵測模式進行車輛偵測，若判斷為白天，系統會使用事先收集的車輛樣本訓練成的分類器，利用方向梯度直方圖搭配支持向量機分類器做車輛偵測；若判斷為夜晚，系統則將影像轉換至HSV色彩空間進行車燈偵測，利用車燈來抓取車輛位置。求得車輛在影像中的位置後，進行像素距離與實際距離之間的轉換。得出實際距離後，計算一定時間間隔車輛的距離變化，估測出後方車輛的相對速度。最後進行車輛威脅判斷，將相對速度帶入煞車距離公式與當下實際距離作比較後，提供給駕駛一個變換車道與否的建議。
實驗結果顯示白天與夜晚都能夠成功偵測出車輛。在距離與速度的判斷上，雖會因為曲線方程式的轉換，而造成極小的誤差，這在駕駛人的反應中是可以被克服的。在變換車道的適宜性上，也可以有效地提出正確意見。整體而言，系統能夠提供有效的意見，輔助駕駛在變換車道的決策上，減輕駕駛的負擔，提高行車安全。

關鍵字

車輛偵測 ； 分類器 ； 距離估測 ； 曲線擬合 ； 變換車道

並列摘要

In recent years, many driver assistance systems have been proposed, and most of them put emphasis on the threat assessment in the front instead of the back. However, when a driver makes a lane change decision, the threat from both front and the back must be assessed simultaneously. Sometimes, too many situations need to be watched in too little time, which may make car accidents occur.
In view of this, we proposed a method which used the images captured from a vehicle on-board camera to detect the vehicle threat from the back. With this technique we can assess the suitability of changing lanes and provide advice to help a driver make a lane change decision, thereby reducing the driver's mental burden for the threat from the back. Therefore, the driver can be more focused on the front to achieve the goal of driving safety.
Our system will do image preprocessing to remove complex and irrelevant background and extract the part of right and left lanes in order to expedite further processing. Next, it will classify an image into the category of day or night. If day time is determined, the system will enter the day-time mode, where vehicle samples and non-vehicle samples were collected in advance to train a classifier and the classifier detects vehicles based on the histograms of oriented gradients (HOG) along with the support vector machines (SVM). If night time is determined, the system expresses the image in HSV color space to detect the head light of vehicles and find the location of the vehicle accordingly. Given the vehicle location, the system will transform an image pixel count into actual physical distance. Then the system calculates the distance change in a fixed time interval to estimate the relative speed between the driver’s car and the vehicle behind it. The vehicle threat from the back is assessed based on the current distance between the two vehicles involved, their relative speed and the brake stoppable distance. Finally, according to the level of the threat, we can provide the lane change suggestion for the driver.
Experimental results show that vehicles can be detected successfully both in day and night. Although the curve fitting function for pixel and actual distance transformation will cause a small error in distance estimation, it can be compensated by the driver’s response. In the appropriateness of lane change, the system can provide effective suggestion. Overall, the system performs quite well because it can reduce the driver's mental burden by providing effective suggestion on lane change decision and achieve the goal of driving safety.

並列關鍵字

vehicle detection ； classifier ； distance estimation ； curve fitting ； lane change

參考文獻

[1] 林建男，一個用視訊處理技術判斷來自後方車輛威脅的車道變換安全輔助系統，中原大學通訊碩士學位學程碩士論文，2016。

[4] G. Yan, M. Yu, Y. Yu, and L. Fan, "Real-time Vehicle Detection using Histograms of Oriented Gradients and AdaBoost Classification," Optik - International Journal for Light and Electron Optics, vol. 127, no. 19, pp. 7941-7951, 2016.

[5] S. Sivaraman and M. M. Trivedi, "Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis," IEEE Transactions on Intelligent Transportation Systems, vol. 14, no. 4, pp. 1773-1795, 2013.

[6] Y. Dhome et al., "A Benchmark for Background Subtraction Algorithms in Monocular Vision: a Comparative Study," in 2010 2nd International Conference on Image Processing Theory, Tools and Applications, Paris, France, France, 2010, pp. 66-71.

[9] X. Wen, L. Shao, W. Fang, and Y. Xue, "Efficient Feature Selection and Classification for Vehicle Detection," IEEE Transactions on Circuits and Systems for Video Technology, vol. 25, no. 3, pp. 508-517, 2015.