路面灌封裂缝对路面使用寿命的影响较为突出，为了解决目前灌封裂缝检测技术匮乏的问题，文中提出了一种基于改进 Faster Ｒ-CNN 的路面灌封裂缝检测方法。首 先，建立灌封裂缝图像集，对采集到的图像进行增广处理，构建路面灌封裂缝标注样本数据集，并将图像集按 6∶2∶2 的比例划分为训练集、验证集和测试集; 接着，采用 Fas- ter R-CNN 模型对灌封裂缝进行检测，针对 Faster R-CNN 检测灌封裂缝存在漏检、定位效果不够理想的问题，文中分别将 VGG16、ZFNet 和 Resnet50 网络的特征提取层与 Fas- ter R-CNN 模型进行结合，结果表明，VGG16 和 Faster R-CNN 结合的模型检测精度最高，达到 0. 9031; 然后，通过增加灌封裂缝候选框宽高比的方法继续改进模型，检测精度达到 0. 907 3，且原先被漏检的目标能被检测出来; 最后，对改进 Faster R-CNN 与 YOLOv2 模型的检测精度及定位效果进行对比，结果表明，文中提出的改进 Faster R- CNN 能够明显提高对灌封裂缝的检测准确率和定位精度。

Pavement sealed cracks have significant impact on service life of pavement． A new method for pavement sealed crack detection based on improved faster R-CNN was proposed，aiming at solving the current lack of sealed crack detection technology． Firstly，the marked sample data set of pavement sealed crack was constructed based on the augmented sealed crack image set． Then they were divided into training set，verification set and test set accor- ding to the ratio of 6∶2∶2． Next，faster R-CNN model was employed in sealed cracks detection． Given that the faster R-CNN model has the demerits of miss detection and inaccurate positioning of sealed cracks，it was combined the feature extraction layers of VGG16，ZFNet and ＲesNet 50 networks． The results show that the detection accuracy of the VGG16 and faster R-CNN combination models can reach 0. 9031，which is the highest． Then，further im- provement was made by increasing the aspect ratio of the anchor of the sealed crack． The improved detection accu- racy reaches 0. 9073 and the original miss detection target can also be detected． Finally，detection and positioning accuracy between improved faster R-CNN and YOLOv2 model was compared． The result shows that improved faster R-CNN model can significantly enhance both detection and positioning accuracy．