Coastal constructions (CCs) operate in harsh environmental conditions under many external forces. Therefore, the coastal construction damaged detectors based on the evaluation of cracks’ progression play a crucial role in ensuring the safety of people and facilities. The proposed method analyzes and monitors the sequence of consecutive images collected by a camera system mounted at locations where cracks occur in the critical structure. A deep convolutional neural network (DCNN) is applied to identify and analyze crack evolution over time. By using parameters such as crack width, boundary, and progression, the proposed system assesses the crack progression of the constructions over time, thereby improving the level of safety and guaranteeing stable operation of the CCs in working conditions.