機器人視覺Robot Vision Group

我們機器人視覺組目前的研究目標放在車輛導航與人機介面上。在車輛導航研究方面我們目前著重於駕駛警示輔助系統的開發，而在這個領域的題目有行人偵測、車道線偵測、車輛偵測，以及駕駛特性的分析。

The research goals of our vision group are vehicle navigation and human-machine interface. Vehicle navigation research focuses on developing a warning and guiding system for driving. The topics of vehicle navigation research include pedestrian detection, lane detection, vehicle detection, and driving characteristics analysis.

Back to home

在智慧型型運輸系統中，進階車輛控制與安全系統(AVCSS)是一個重要的議題：經由一台工業用電腦，應用攝影機或與其他感應技術的結合獲得車輛前方道路場景的資訊，並分析或指出是否存在危險的情況。這種系統提供一個警示的裝置避免駕駛因疲勞或短暫的不注意而發生車禍。經由上述的理由，我們發展出一連串以電腦視覺(computer vision)為基礎的技術，包含了道路線辨識和障礙物偵測(行人或車輛偵測)。

Advanced Vehicle Control and Safety System (AVCSS) is an important topic in Intelligent Transportation Systems (ITS).Applying the cameras or other sensor fusion technique to obtain information from road scene in front of vehicle, and analysis or judge whether the dangerous situation happened or not via a industrial PC. This kind of systems provide a warning mechanism to protect drivers from car accidents caused by fatigue or inattention in a short while. According to this reason, we have developed a series of techniques based on computer vision technique including lane recognition and obstacle detection (such as pedestrian or vehicle detection).

發展此系統的動機是因為許多行人受到車輛碰撞而受傷，在此我們開發行人偵測系統，藉由警示駕駛周遭環境的狀況來避免這類意外發生並減輕嚴重性，這個系統是基於模版的階層式比對，所以能做到迅速且有效率，而且這種技術也被廣泛的應用在智慧型駕駛系統或其他監視系統。

The motivation of system is that many pedestrians were injured due to collisions with vehicles. Here we developed pedestrian detection systems to avoid these accidents and ease off the severity by alerting the drivers to take care the surrounding situation. This system is a hierarchical template-based matching, so it is fast and efficient. And it has been widely applied to intelligence transportation systems or some applications of surveillance.

在不同光影條件下，車輛辨識可以使用粒子濾波器(Particle Filter)達成。我們結合了車輛偵測追蹤及道路線偵測，使我們能獲得更健全與有效的結果，但在結合的過程中仍要確保我們的系統能不需經由手動設定就能適應各種環境。經由相機的校正結果與道路線偵測，我們可以簡單的獲得針對偵測有興趣的區域，使車輛偵測和道路線偵測的結合能減少我們誤判的比例。

Vehicle recognition at various lighting condition is achieved by using the particle filtering. We integrate the vehicle detection and tracking with lane detection which give us more robust and efficiency. Fuse of the cues are also important that make our system works under various condition without manual setup or instruction. Based on the results of camera calibration and lane detection, the region of interest can be generated easily. The integration of the vehicle recognition and lane detection will reduce false vehicle recognition rate.

我們提出「峰值尋找演算法」(Peak-Finding Algorithm)來有效的擷取道路線記號的特徵點，之後藉由將特徵點群組化來偵測道路線。在第一個循環完成後，我們在一個參數化的區域尋找道路線記號，如果一條線的峰值聚集在合理化的門檻值內，則我們稱發現了道路線的邊界；否則，我們將使用邊緣連結的程序來建立道路線的邊界。

We propose the Peak-Finding Algorithm to extract the feature points effectively based on the lane markings characteristics. Then, the lane markings are detected by grouping the feature points. We use local searching in the parameter space for the lane markings after first iteration. If the Peaks over one line aggregate to certain threshold, the lane boundaries are found. Else, we will use edge linking procedure to the Peaks to build lane boundaries.

Back to home

詹益銘 Yi-Ming Chan iming (2005-) iming@sgi.csie.ntu.edu.tw

林斌峰 Bin-Feng Lin infinitea (2008- ) infinitea@sgi.csie.ntu.edu.tw

林預淳 Yu-Chun Lin angelcet (2008- ) angelcet@sgi.csie.ntu.edu.tw

莊理安 Li-An Chuang dogchaos (2009- ) dogchaos@sgi.csie.ntu.edu.tw

莊珞杰 Luo-Chieh Chuang pharspher (2009- ) pharspher@gmail.com

謝衛中 Wei-Chung Hsieh wchsieh (2000-2002) r89051@csie.ntu.edu.tw
陳琮仁 Chun-Ren Chen Bugman (2001-2003) bugman@sgi.csie.ntu.edu.tw
王俊哲 Chun-Che Wang waly (2002-2004) waly@sgi.csie.ntu.edu.tw
蔡濬帆 Jyun-Fan Tsai Tsai (2004-2006) jyunfan@gmail.com
陳任志 Jerry Chen jerry (2004-2006) onlyuser@hotmail.com
黃世勳 Shih-Shinh Huang poww (1999-2007) poww@sgi.csie.ntu.edu.tw
黃贊宇 Chan-Yu Huang chanYu (2005-2007) chanyu@sgi.csie.ntu.edu.tw
袁維均 Wei-Chun Yuan Wei-Chun (2005-2007) b90009@csie.ntu.edu.tw
邱一航 Yi-Hang Chiu yhchiu (2006-2008) yhchiu@sgi.csie.ntu.edu.tw
莊振勛 Cheng-Hsiung Chuang houston (2006-2008) houston@sgi.csie.ntu.edu.tw
洪思穎 Ssu-Ying Hung singing (2007-2009) singing@sgi.csie.ntu.edu.tw
李忞藯 Min-Wei Li hugh (2007-2009) hugh@sgi.csie.ntu.edu.tw

1. Shih-Shinh Huang, Li-Chen Fu, and Pei-Yung Hsiao, “Region-Level Motion-Based Background Modeling and Subtraction Using MRFs,” IEEE Trans. on Image Processing (SCI) Vol. 16, No. 5, pp. 1446-1456, May 2007.
2. Shih-Shinh Huang, Li-Chen Fu, and Pei-Yung Hsiao, “Region-Level Motion-Based Foreground Segmentation under a Bayesian Network,” Submitted to IEEE Trans. on Circuits and Systems for Video Technology (SCI), Feb. 2007..
3. Shih-Shinh Huang, Li-Chen Fu, Pei-Yung Hsiao, “Region-Level Motion-Based Background Modeling and Subtraction Using MRFs,” Lecture Notes in Computer Science, 2006.
4. Yi-Ming Chan, Shih-Shinh Huang, Li-Chen Fu, and Pei-Yung Hsiao, “Vehicle Detection under Various Lighting Conditions by Incorporate Particle Filter,” Journal of Vehicle Engineering, Vol.3, pp.31-44 , May 2006.
5. Jyun-Fan Tsai, Shih-Shinh Huang, Chan-Yu Huang, Li-Chen Fu, and Pei-Yung Hsiao, “On Road Image Acquiring and Anti-Blooming System at Nighttime by Using High Dynamic Image Reconstruction with Motion Compensation,” Journal of Vehicle Engineering, Vol.3, pp.45-58, May 2006.
6. Pei-Yung Hsiao, Hsien-Chein Cheng, Shih-Shinh Huang, and Li-Chen Fu, “A Mixed Signal CMOS Imager with Lane Detector for Use in Smart Vehicles,” Submitted to IEEE Trans. on Vehicular Technology (SCI), Oct. 2006.
7. Shih-Shinh Huang, Li-Chen Fu, Pei-Yung Hsiao, “Silhouette-Based Human Pose Estimation Using Reversible Jump Markov Chain Monte Carlo,” IEE Electronics Letters, 2006
8. Chun-Che Wang, Shih-Shinh Huang, Pei-Yung Hsiao, and Li-Chen Fu, “Computer Vision-Based Lane Detection and Vehicle Recognition for Driver Assistance System at Night,” Journal of Vehicle Engineering, Vol.2, pp.51-64 , May 2005.

1. Hung, Ssu-Ying; Chan, Yi-Ming; Lin, Bin-Feng; Fu, Li-Chen; Hsiao, Pei-Yung; Huang, Shin-Shinh, “Tracking and detection of lane and vehicle integrating lane and vehicle information using PDAF tracking model,” Intelligent Transportation Systems, 2009. ITSC ‘09. 12th International IEEE Conference on , vol., no., pp.1-6, 4-7 Oct. 2009
2. Cheng-Hsiung Chuang, Shih-Shinh Huang, Li-Chen Fu and Pei-Yung Hsaio, “Monocular Multi-Human Detection Using Augmented Histograms of Oriented Gradients”, IEEE International Conference on Pattern Recognition, 2008.
3. Chan-Yu Huang, Shih-Shinh Huang, Yi-Ming Chan, Yi-Hang Chiu, Li-Chen Fu and Pei-Yung Hsaio, “Driver Assistance System Using Integrated Information from Lane Geometry and Vehicle Direction”, IEEE International Conference on Intelligent Transportation Systems, 2007.
4. Yi-Ming Chan, Shih-Shinh Huang, Li-Chen Fu and Pei-Yung Hsiao, “Vehicle Detection under Various Lighting Conditions by Incorporating Particle Filter”, IEEE International Conference on Intelligent Transportation Systems, 2007.
5. Shih-Shinh Huang, Li-Chen Fu, Pei-Yung Hsiao, “A Bayesian Framework for Foreground Segmentation”, IEEE International Conference on Systems, Man, and Cybernetics, 2006.
6. Shih-Shinh Huang, Li-Chen Fu, Pei-Yung Hsiao, “Silhouette-Based Human Pose Estimation Using Reversible Jump Markov Chain Monte Carlo,” IEEE International Conference on Pattern Recognition, 2006.
7. Shih-Shinh Huang, Li-Chen Fu, Pei-Yung Hsiao, “A Framework for Human Pose Estimation by Integrating DD-MCMC and MOEA,” IEEE International Conference on Robotics and Automation, 2006.
8. Shih-Shinh Huang, Li-Chen Fu, Pei-Yung Hsiao, “Region-Level Motion-Based Foreground Detection with Shadow Removal Using MRFs,” Asian Conference on Computer Vision, 2006.
9. Jyun-Fan Tsai, Shih-Shinh Huang, Yi-Ming Chan, Chan-Yu Huang, Li-Chen Fu, and Pei-Yung Hsiao, “Road Detection and Classification in Urban Environments Using Conditional Random Field Models,” IEEE International Conference on Intelligent Transportation System, 2006.
10. Shih-Shinh Huang, Li-Chen Fu, Pei-Yung Hsiao, “A Region-Level Motion-Based Background Subtraction Using MRFs,” EEE International Conference on Robotics and Automation, 2005.
11. Chun-Che Wang, Shih-Shinh Huang, Li-Chen Fu, and Pei-Yung Hsiao, “Driver Assistance System for Lane Detection and Vehicle Recognition with Night Vision,” IEEE International Conference on Intelligent Robots and Systems, 2005.
12. Shih-Shinh Huang, Li-Chen Fu, Pei-Yung Hsiao, “A Region-Based Background Modeling and Subtraction Using Partial Directed Hausdorff Distance,” IEEE International Conference on Robotics and Automation, 2004.
13. Shih-Shinh Huang, Chung-Jen Chen, Pei-Yung Hsiao, and Li-Chen Fu, “On-Board Vision System for Lane Recognition and Front-Vehicle Detection to Enhance Driver’s Awareness,” IEEE International Conference on Robotics and Automation, 2004.
14. W. C. Hsieh, Li-Chen Fu and Shih-Shinh Huang, “Vision Based Obstacle Warning System for On-Road Driving,” IEEE Conference on Intelligent Robots and Systems, 2003.
15. Z. T. Sun, Li-Chen Fu and Shih-Shinh Huang, “On-Road Computer Vision Based Obstacle Detection,” IEEE Conference on Intelligent Robots and Systems, 2002.
16. C. Y. Liu, Li-Chen Fu, Shih-Shinh Huang, “Computer Vision Based Objects Detection and Recognition for Safe Vehicle Driving,” IEEE Conference on Robotics and Automation, 2001.

Back to home