Accurate shoreline extraction is critical for coastal engineering applications, including erosion monitoring, disaster response, and sustainable management of island ecosystems. However, traditional methods face challenges in large-scale monitoring due to high costs, environmental interference (e.g., cloud cover), and poor performance in complex terrains (e.g., bedrock coastlines). This study developed an optimized DeepLabV3+ model for the extraction of island shorelines, which improved model performance by replacing the backbone network with MobileNetV2, introducing a strip pooling layer into the ASPP module, and adding CBAM modules in both the shallow and deep stages of feature extraction from the backbone network. The model accuracy was verified using a self-built drone dataset of the shoreline of Koh Lan, Thailand, and the results showed: (1) Compared with the control model, the improved DeepLabV3+ model performs excellently in pixel accuracy (PA), recall, F1 score, and intersection over union (IoU), reaching 98.7%, 97.7%, 98.0%, and 96.2%, respectively. Meanwhile, the model has the lowest number of parameters and floating-point operations, at 6.61 M and 6.7 GFLOPS, respectively. (2) In terms of pixel accuracy (PA) and intersection over union (IoU), the CBAM attention mechanism outperforms the SE-Net and CA attention mechanisms. Compared with the original DeepLabV3+ network, PA increased by 3.1%, and IoU increased by 8.2%. (3) The verification results of different types of coastlines indicate that the improved model can effectively distinguish between shadows and water bodies, reducing the occurrence of false negatives and false positives, thereby lowering the risk of misclassification and obtaining better extraction results. This work provides a cost-effective tool for dynamic coastal management, particularly in data-scarce island regions.