当前位置: X-MOL 学术Appl. Ocean Res. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Visual ship tracking via a hybrid kernelized correlation filter and anomaly cleansing framework
Applied Ocean Research ( IF 4.3 ) Pub Date : 2021-01-01 , DOI: 10.1016/j.apor.2020.102455
Xinqiang Chen , Xueqian Xu , Yongsheng Yang , Yanguo Huang , Jing Chen , Ying Yan

Abstract Ship tracking from maritime visual sensing data (namely maritime surveillance videos) provides various kinematic maritime traffic information, which significantly benefits remote maritime traffic controlling and management, off-site law enforcement, etc. But, it is difficult to extract distinct ship visual features when the target ship is sheltered by the neighboring ship in the maritime images (or the images are shot in low visibility condition). To address the difficulty, we proposed a hybrid ship tracking framework via the help of kernelized correlation filter (KCF) and anomaly cleaning models (including curve fitting method and Kalman filter). First, we employed the KCF model to obtain raw ship trajectories in consecutive maritime images. Second, our ship tracker is accurately initialized (to be specific, ground truth ship position in the first frame is employed to initialize the ship tracker). Third, the Kalman filter is introduced to suppress the trivial ship position oscillations in the raw ship trajectories. We verified the proposed framework performance on the four typical maritime scenarios. The experimental results indicate that the proposed ship tracker showed more accurate ship tracking results compared to other four popular ship trackers in terms of average root mean square error (RMSE), mean absolute deviation (MAD) and mean square error (MSE). The research findings can help maritime traffic participants obtain visual on-spot maritime kinematic information, and thus further enhance maritime traffic safety.

中文翻译:

通过混合核相关过滤器和异常清理框架进行视觉船舶跟踪

摘要 海上视觉传感数据(即海上监视视频)的船舶跟踪提供了各种动态的海上交通信息,这对远程海上交通控制和管理、异地执法等具有重要意义。但是,难以提取明显的船舶视觉特征。当目标船舶在海上图像中被相邻船舶遮挡时(或图像是在低能见度条件下拍摄的)。为了解决这个困难,我们通过核相关滤波器(KCF)和异常清理模型(包括曲线拟合方法和卡尔曼滤波器)的帮助提出了一种混合船舶跟踪框架。首先,我们采用 KCF 模型来获取连续海上图像中的原始船舶轨迹。其次,我们的船舶跟踪器已准确初始化(具体来说,第一帧中的地面实况船舶位置用于初始化船舶跟踪器)。第三,引入卡尔曼滤波器来抑制原始船舶轨迹中的微不足道的船舶位置振荡。我们在四种典型的海事场景中验证了所提出的框架性能。实验结果表明,与其他四种流行的船舶跟踪器相比,所提出的船舶跟踪器在平均均方根误差 (RMSE)、平均绝对偏差 (MAD) 和均方误差 (MSE) 方面显示出更准确的船舶跟踪结果。研究成果可以帮助海上交通参与者获得视觉现场海上运动信息,从而进一步提高海上交通安全。引入卡尔曼滤波器来抑制原始船舶轨迹中的微不足道的船舶位置振荡。我们在四种典型的海事场景中验证了所提出的框架性能。实验结果表明,与其他四种流行的船舶跟踪器相比,所提出的船舶跟踪器在平均均方根误差 (RMSE)、平均绝对偏差 (MAD) 和均方误差 (MSE) 方面显示出更准确的船舶跟踪结果。研究成果可以帮助海上交通参与者获得视觉现场海上运动信息,从而进一步提高海上交通安全。引入卡尔曼滤波器来抑制原始船舶轨迹中的微不足道的船舶位置振荡。我们在四种典型的海事场景中验证了所提出的框架性能。实验结果表明,与其他四种流行的船舶跟踪器相比,所提出的船舶跟踪器在平均均方根误差 (RMSE)、平均绝对偏差 (MAD) 和均方误差 (MSE) 方面显示出更准确的船舶跟踪结果。研究成果可以帮助海上交通参与者获得视觉现场海上运动信息,从而进一步提高海上交通安全。实验结果表明,与其他四种流行的船舶跟踪器相比,所提出的船舶跟踪器在平均均方根误差 (RMSE)、平均绝对偏差 (MAD) 和均方误差 (MSE) 方面显示出更准确的船舶跟踪结果。研究成果可以帮助海上交通参与者获得视觉现场海上运动信息,从而进一步提高海上交通安全。实验结果表明,与其他四种流行的船舶跟踪器相比,所提出的船舶跟踪器在平均均方根误差 (RMSE)、平均绝对偏差 (MAD) 和均方误差 (MSE) 方面显示出更准确的船舶跟踪结果。研究成果可以帮助海上交通参与者获得视觉现场海上运动信息,从而进一步提高海上交通安全。
更新日期:2021-01-01
down
wechat
bug