变化光照条件下的交通标志快速鲁棒检测
|
摘要
变化光照条件下交通标志检测算法的准确率往往会显著降低。针对此问题,提出了1种新颖的概率图建立方法,并结合最大稳定极值区域特征进行交通标志检测。该方法包括3个处理步骤:①根据不同光照条件对真实场景交通标志样本图像进行明确分类以构建多类颜色直方图,将交通标志输入图像由原始色彩表达转变为概率图(直方图反投影);②通过在概率图上进行MSER特征提取,获取候选的交通标志区域;③根据候选区域的面积、宽高比等特征快速有效去除非交通标志区域。实验结果表明在弱光照和强光照条件下基于归一化RGB的交通标志检测算法检测准确率分别下降到84.4%和83.0%,基于红蓝图的交通标志检测算法检测准确率分别下降到87.4%和86.3%,提出的算法在变化光照条件下依然可以保持90%以上的检测准确率,对光照变化有较好的鲁棒性。
Aiming at the problem that the accuracy rate of traffic sign detection will become significantly lower in protean illumination scenario,a novel robust method of traffic sign detection is proposed based on the color probability map which is built from multiple color-histogram back-projection and the extraction of MSER(Maximally Stable Extremal Region)in color probability map.The algorithm consists of three steps:1)Sample images of traffic signs are classified into a series of different subsets with different illumination states for each color of interest(red,blue or yellow)and the color probability map is built from the multiple color-histogram built from each subset of sample images;2)Candidate regions of traffic sign are found by using the extraction of MSER in color probability map;3)Non-traffic-sign regions are eliminated efficiently according to the features(region perimeter,area,etc.)of the detected MSER.Experimental results show that under the conditions of low light and strong light the accuracy rate of traffic sign detection algorithm based on normalized RGB drops to 84.4%and 83.0%respectively,while the accuracy rate of traffic sign detection algorithm based on red/blue image drops to 87.4%and 86.3%respectively.The proposed method can still remain more than 90%of the detection accuracy in protean illumination scenario,and is of higher robustness in protean illumination environment.
Aiming at the problem that the accuracy rate of traffic sign detection will become significantly lower in protean illumination scenario,a novel robust method of traffic sign detection is proposed based on the color probability map which is built from multiple color-histogram back-projection and the extraction of MSER(Maximally Stable Extremal Region)in color probability map.The algorithm consists of three steps:1)Sample images of traffic signs are classified into a series of different subsets with different illumination states for each color of interest(red,blue or yellow)and the color probability map is built from the multiple color-histogram built from each subset of sample images;2)Candidate regions of traffic sign are found by using the extraction of MSER in color probability map;3)Non-traffic-sign regions are eliminated efficiently according to the features(region perimeter,area,etc.)of the detected MSER.Experimental results show that under the conditions of low light and strong light the accuracy rate of traffic sign detection algorithm based on normalized RGB drops to 84.4%and 83.0%respectively,while the accuracy rate of traffic sign detection algorithm based on red/blue image drops to 87.4%and 86.3%respectively.The proposed method can still remain more than 90%of the detection accuracy in protean illumination scenario,and is of higher robustness in protean illumination environment.
引文
[1]de la Escalera A,Moreno L E,Salichs M A,et al.Road traffic sign detection and classification[J].Industrial Electronics,IEEE Transactions on,1997,44(6):848-859.
[2]Maldonado-Bascón S,Lafuente-Arroyo S,Gil-Jiménez P,et al.Road-sign detection and recognition based on support vector machines[J].Intelligent Transportation Systems,IEEE Transactions on,2007,8(2):264-278.
[3]de la Escalera A,Armingol J M,Mata M.Traffic sign recognition and analysis for intelligent vehicles[J].Image and vision computing,2003,21(3):247-258.
[4]de la Escalera A,Armingol J M,Pastor J M.Visual sign information extraction and identification by deformable models for intelligent vehicles[J].Intelligent Transportation Systems,IEEE Transactions on,2004,15(2):57-68.
[5]Kehtarnavaz N,Griswold N C,Kang D S.Stop sign recognition based on color/shape processing[J].Machine Vision and Applications,1993,6(4):206-208.
[6]Fang C,Chen S,Fuh C.Road sign detection and tracking[J].Vehicular Technology,IEEE Transactions on,2003,52(5):1329-1341.
[7]武莹,张小宁,何斌.基于图像处理的交通信号灯识别方法[J].交通信息与安全,2011,29(3):51-54.
[8]Matas J,Chum O,Urban M,et al.Robust wide-baseline stereo from maximally stable extremal regions[J].Image and Vision Computing,2004,22(10):761-767.
[9]Greenhalgh J,Mirmehdi M.Real-Time Detection and Recognition of Road Traffic Signs[J].Intelligent Transportation Systems,IEEE Transactions on,2012,13(4):1498-1506.
[10]Stallkamp J,Schlipsing M,Salmen J,et al.The german traffic sign recognition benchmark:A multi-class classification competition[C]∥The international Joint Conference on Neural Networks.San Jose.CA:IEEE,2011.
[11]Gomez-Moreno H,Maldonado-Bascon S,Gil-Jimenez P,et al.Goal evaluation of segmentation algorithms for traffic sign recognition[J].Intelligent Transportation Systems,IEEE Transactions on,2010,11(4):917-930.
[2]Maldonado-Bascón S,Lafuente-Arroyo S,Gil-Jiménez P,et al.Road-sign detection and recognition based on support vector machines[J].Intelligent Transportation Systems,IEEE Transactions on,2007,8(2):264-278.
[3]de la Escalera A,Armingol J M,Mata M.Traffic sign recognition and analysis for intelligent vehicles[J].Image and vision computing,2003,21(3):247-258.
[4]de la Escalera A,Armingol J M,Pastor J M.Visual sign information extraction and identification by deformable models for intelligent vehicles[J].Intelligent Transportation Systems,IEEE Transactions on,2004,15(2):57-68.
[5]Kehtarnavaz N,Griswold N C,Kang D S.Stop sign recognition based on color/shape processing[J].Machine Vision and Applications,1993,6(4):206-208.
[6]Fang C,Chen S,Fuh C.Road sign detection and tracking[J].Vehicular Technology,IEEE Transactions on,2003,52(5):1329-1341.
[7]武莹,张小宁,何斌.基于图像处理的交通信号灯识别方法[J].交通信息与安全,2011,29(3):51-54.
[8]Matas J,Chum O,Urban M,et al.Robust wide-baseline stereo from maximally stable extremal regions[J].Image and Vision Computing,2004,22(10):761-767.
[9]Greenhalgh J,Mirmehdi M.Real-Time Detection and Recognition of Road Traffic Signs[J].Intelligent Transportation Systems,IEEE Transactions on,2012,13(4):1498-1506.
[10]Stallkamp J,Schlipsing M,Salmen J,et al.The german traffic sign recognition benchmark:A multi-class classification competition[C]∥The international Joint Conference on Neural Networks.San Jose.CA:IEEE,2011.
[11]Gomez-Moreno H,Maldonado-Bascon S,Gil-Jimenez P,et al.Goal evaluation of segmentation algorithms for traffic sign recognition[J].Intelligent Transportation Systems,IEEE Transactions on,2010,11(4):917-930.