LMD-TShip^⋆: Vision Based Large-Scale Maritime Ship Tracking Benchmark for Autonomous Navigation Applications

Abstract

Accurate ship tracking is very important for the security of maritime activities, especially the raising requirements of autonomous navigation applications, e.g., autonomous surface vehicles (ASVs). Unlike deep-learning-based object-tracking methods are prevailing in autonomous driving because of good environmental robustness and high tracking accuracy, few deep-tracking models can be found for maritime ships. The main reason for that is the lack of qualified ship datasets, especially datasets with shipbased perspectives. Therefore, a large-scale, high-definition dataset for ship tracking, LMD-TShip (Large Maritime Dataset), is provided in this paper. In this dataset, five types of ships are included, from cargo ships, fishing ships, passenger ships, and speed boats to unmanned ships. Specifically, LMD-TShip consists of 40,240 frames in 191 videos, each of which is carefully and manually annotated with bounding boxes in YOLO format. Moreover, 13 attributes are used to label videos, e.g., scale variation (SV), occlusion (OCC), basically covering tracking challenges of maritime ship tracking. Next, a detailed analysis is carried out to demonstrate the characteristics of LMD-TShip. Finally, experiments with five baseline short-term tracking models on the dataset are performed, e.g., ECO, SiamRPN++, and the experimental results demonstrate its good evaluation ability, which will provide effective means for training and testing tracking models related to maritime ships.

Maritime video ship detection and tracking based on improved YOLOX and DeepSORT

“…This study mainly uses the LMD-TShip (large maritime dataset) dataset, 31 a high-definition video dataset for ship tracking containing 191 videos with 40,240 frames and five ship categories. However, the original dataset focuses mostly on scale change and occlusion.…”

“…On the LMD-TShip 31 video dataset, our method improves the metric AP50 by 3.41% compared to YOLOX and significantly alleviates some camera shaking and object occlusion issues. On the public dataset COCO2017, 32 iYOLOX improves the average precision (AP) by 3% and improves the metric APs for small objects by 4.2% compared to the original YOLOX.…”

Coastal Ship Tracking with Memory-Guided Perceptual Network

“…It extracts the contextual information of ship features at multiple scales and improves the receptive field through a hierarchical global-and-local dilation convolution, which can improve tracking accuracy and robustness. • Without bells and whistles, our method outperforms the state-of-the-art methods on a large maritime dataset LMD-TShip [33] and achieves a tracking EAO of up to 0.665 and Robustness of up to 0.067.…”

“…Similar to FCOS [29], our regression goals are d l , d t , d b , d r , and they represent the distance from the center point to the border. The overall loss function is: Our dataset LMD-TShip [33] is a large scale, full category, high resolution for ship tracking. It contains 40,240 frames in 191 videos for five categories of ships, including cargo ships, fishing ships, passenger ships, speedboats, and unmanned ships.…”

“…To verify the effectiveness of each component of our MGPN, we perform an ablation study on LMD-TShip [33]. We adopt SiamBAN [25] (represented by B) as our baseline, which is an anchor-free tracking framework.…”