Pavement distress detection is the key to the development of road maintenance programs. However, traditional methods with long detection period and strong subjectivity are difficult to meet the rapid and large-scale automatic detection and evaluation of pavement technical condition. In this paper, we propose a method based on YOLOv5 combined with the initialized anchor frame selection strategy of intersection and merger ratio metrics, the multidimensional information interaction attention mechanism module ARDs, and the lightweight up-sampling operator CARAFE. An asphalt pavement distress dataset ARDs-5 containing 21,797 pavement images is constructed using a vehicle-mounted CCD camera. The proposed method outperforms the comparison frontier baseline on the self-constructed dataset with a mAP of 75.8%. Finally, ARD-YOLO was applied to evaluate the pavement condition of asphalt highways in Liaoning Province, China, and achieved excellent performance. The experiments show that ARD-YOLO has high practical value for pavement distress detection and evaluation in complex environments.