Coastal surveillance video helps officials to obtain on-site visual information on maritime traffic situations, which benefits building up the maritime transportation detection infrastructure. The previous ship detection methods focused on detecting distant small ships in maritime videos, with less attention paid to the task of ship detection from coastal surveillance video. To address this challenge, a novel framework is proposed to detect ships from coastal maritime images in three typical traffic situations in three consecutive steps. First the Canny detector is introduced to determine the potential ship edges in each maritime frame. Then, the self-adaptive Gaussian descriptor is employed to accurately rule out noisy edges. Finally, the morphology operator is developed to link the detected separated edges to connected ship contours. The model's performance is tested under three typical maritime traffic situations. The experimental results show that the proposed ship detector achieved satisfactory performance (in terms of precision, accuracy and time cost) compared with other state-of-the-art algorithms. The findings of the study offer the potential of providing real-time visual traffic information to maritime regulators, which is crucial for the development of intelligent maritime transportation.

中文翻译：

---

通过集成 Canny-Gaussian-morphology 框架从海岸监控视频中进行船舶检测

沿海监控视频帮助官员获得海上交通情况的现场视觉信息，有利于建立海上交通检测基础设施。以往的船舶检测方法侧重于在海事视频中检测远处的小型船舶，较少关注海岸监控视频中的船舶检测任务。为了应对这一挑战，提出了一种新颖的框架，可以在三个连续步骤中在三种典型交通情况下从沿海海事图像中检测船舶。首先引入 Canny 检测器以确定每个海事框架中的潜在船舶边缘。然后，采用自适应高斯描述符准确排除噪声边缘。最后，开发了形态学算子，将检测到的分离边缘与连接的船舶轮廓联系起来。该模型的性能在三种典型的海上交通情况下进行了测试。实验结果表明，与其他最先进的算法相比，所提出的船舶检测器在精度、准确性和时间成本方面取得了令人满意的性能。该研究的结果提供了向海事监管机构提供实时可视交通信息的潜力，这对于智能海上交通的发展至关重要。