With the rapid development of artificial intelligence and big traffic data, the data-driven intelligent maritime transportation has received significant attention in both industry and academia. It is capable of improving traffic efficiency and reducing traffic accidents in maritime applications. However, video cameras often suffer from severe haze weather, leading to degraded visual data and ineffective maritime surveillance. It is thus necessary to restore the visually degraded images and to guarantee maritime transportation efficiency and safety under hazy imaging conditions. In this work, a contrastive learning framework is proposed for haze visibility enhancement in intelligent maritime transportation systems. In particular, the proposed learning method could fully learn both local and global image features, which are beneficial for visual quality improvement. A total of 100 clean images containing water traffic scenes were selected as the synthetic test dataset, and good dehazing results were achieved on both visual and indexing results (e.g., peak signal to noise ratio (PSNR): 23.95 ± 3.48 and structural similarity index (SSIM): 0.924 ± 0.065 for different transmittance and atmospheric light values). In addition, extensive experiments on real-world 100 water hazy images demonstrate the effectiveness of the proposed method (e.g., natural image quality evaluator (NIQE): 4.800 ± 0.634 and perception-based image quality evaluator (PIQE): 46.320 ± 10.253 ). The enhanced images could be effectively exploited for promoting the accuracy and robustness of ship detection. The maritime traffic supervision and management could be accordingly improved in the intelligent transportation system.