藉由機率資料結合濾波器整合車道線和車輛資訊來偵測並追蹤車輛及車道線

Tracking and Detection of Lane and Vehicle Integrating Lane and Vehicle Information Using Probabilistic Data Association Filter

洪思穎(Ssu-Ying Hung)

指導教授 ： 傅立成

共同指導教授 ： 蕭培墉 ； 黃世勳

國立臺灣大學/電機資訊學院/資訊工程學研究所/碩士(2009年)

https://doi.org/10.6342/NTU.2009.00640

摘要

我們提出一個強大的系統來偵測多車道及多車輛，現階段的研究大部份是單讀針對車道線偵測或是車輛偵測，因此他們的系統中通常只能偵測車道線或車輛。然而，車道線和車輛之間是有相依性的。當我們行駛在公路上時，車子通常會遵循著車道線的方向前進。所以我們相信可以利用彼此之間的關係來加強偵測及追蹤車道線和車輛的準確性和穩定度。機率資料結合濾波器(Probabilistic Data Association Filter)追蹤演算法會將之前追蹤的結果累積起來，並用來估算下一個時間點目標可能的位置。對於每次追蹤時偵測到的訊號，會估算出一個可能性作為那個訊號的權重。訊號指的是由影像中截取出來的特徵。因此我們方法主要的核心就是將車道線與車輛之間的關聯性整合到每個訊號的權重。
作車道線偵測時，目前正在追蹤的車輛可以提供方向及位置的資訊。車輛的位置可用來降低車道線特徵的雜訊。追蹤的車道線也可以提供方法性和理想的範圍給偵測及追蹤車輛時使用。實驗結果可以發現，我們提出的系統可以有效並穩定的追蹤多車道線及多車輛。

關鍵字

汽車辨識 ； 車道線辨識

並列摘要

We propose a robust system for multi-vehicle and multi-lane detection with integrating lane and vehicle information. Most research work only can detect the lanes or vehicles separately. However, the dependency between lane information and vehicle information are able to support each other achieving more reliable results. In probabilistic data association filter (PDAF) track model, cumulate history of target is keep in the data association probability and the weight of each detected features are estimated to be the likelihood; therefore we use probabilistic data association filter to integrate information of lane and vehicle. The core of our method is to combine the lanes and vehicles by improve the data association probability with observational relation.
For lane detection and tracking, tracked vehicles provide the orientation and position information. The tracked lane also gives the direction and boundary to the vehicle detection and tracking. According to the lane information, we can know where is impossible to appear the moving vehicles. Experimental results show that our approach can detect multi-vehicle and multi-lane more reliably

並列關鍵字

vehicle detection ； lane detection

參考文獻

[3] Y. Wang, E. K. Teoh, and D. Shen, "Lane detection and tracking using B-Snake," Image and Vision Computing, vol. 22, pp. 269-280, 2004.

[4] S.-S. Huang, C.-J. Chen, P.-Y. Hsiao, and L.-C. Fu, "On-board vision system for lane recognition and front-vehicle detection to enhance driver's awareness," in IEEE Conference on Robotics and Automation, pp. 2456-2461, 2004.

[5] M. Bertozzi and A. Broggi, "GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection," IEEE Transactions on Image Processing, vol. 7, pp. 62-81, 1998.

[6] K.-Y. Chiu and S.-F. Lin, "Lane detection using color-based segmentation," in IEEE Proceedings on Intelligent Vehicles Symposium, pp. 706-711, 2005.

[10] Z. Kim, "Robust Lane Detection and Tracking in Challenging Scenarios," IEEE Intelligent Transportation Systems, vol. 9, pp. 16-26, 2008.