CAJ | 학술논문

针对复杂背景下多类型交通信号灯的自动识别问题，提出一种基于亮度分割、K 均值聚类及前景直方图分析相结合的识别方法。首先通过亮度分割、几何特征分析和分类统计方法对信号灯进行自动定位；然后利用 K 均值聚类算法判断信号灯颜色；最终通过分析信号灯前景直方图对信号灯类型及其包含的方向信息进行判断，从而实现信号灯的自动识别。实验结果表明，该方法对不同场景下的不同类型信号灯均具有很高的识别准确率，证明了该方法的高可靠性和广泛适用性。
침대복잡배경하다류형교통신호등적자동식별문제，제출일충기우량도분할、K 균치취류급전경직방도분석상결합적식별방법。수선통과량도분할、궤하특정분석화분류통계방법대신호등진행자동정위；연후이용 K 균치취류산법판단신호등안색；최종통과분석신호등전경직방도대신호등류형급기포함적방향신식진행판단，종이실현신호등적자동식별。실험결과표명，해방법대불동장경하적불동류형신호등균구유흔고적식별준학솔，증명료해방법적고가고성화엄범괄용성。
To solve the auto-recognition problem of multi-type traffic lights in complex background,a novel method based on brightness value division,K-means clustering and histogram analysis of foreground objects was proposed. First-ly,self-localization was realized by brightness value division,geometric features analysis and classification statistics. Along with signal color judgment by K-means clustering algorithm,the type and direction information of traffic lights would be acquired by analyzing the histograms of foreground objects;accordingly auto-detection was realized. Experi-mental results showed that the proposed method had high detection accuracy for multi-type traffic lights in different sce-narios. It was proved that this method was highly reliable and widely applicable.