The main factor affecting road performance is pavement damage. One of the difficulties in maintaining roads is pavement cracking. Credible and reliable inspection of heritage structural health relies heavily on crack detection on road surfaces. To achieve intelligent operation and maintenance, intelligent crack detection is essential to traffic safety. The detection of road pavement cracks using computer vision has gained popularity in recent years. Recent technological breakthroughs in general deep learning algorithms have resulted in improved results in the discipline of crack detection. In this paper, two techniques for object identification and segmentation are proposed. The EfficientNet with residual U-Net technique is suggested for segmentation, while the YOLO v5 algorithm is offered for crack detection. To correctly separate the pavement cracks, a crack segmentation network is used. Road crack identification and segmentation accuracy were enhanced by optimising the model's hyperparameters and increasing the feature extraction structure. The suggested algorithm's performance is compared to state-of-the-art algorithms. The suggested work achieves 99.35% accuracy.