UnityShip: A Large-Scale Synthetic Dataset for Ship Recognition in Aerial Images

Abstract

As a data-driven approach, deep learning requires a large amount of annotated data for training to obtain a sufficiently accurate and generalized model, especially in the field of computer vision. However, when compared with generic object recognition datasets, aerial image datasets are more challenging to acquire and more expensive to label. Obtaining a large amount of high-quality aerial image data for object recognition and image understanding is an urgent problem. Existing studies show that synthetic data can effectively reduce the amount of training data required. Therefore, in this paper, we propose the first synthetic aerial image dataset for ship recognition, called UnityShip. This dataset contains over 100,000 synthetic images and 194,054 ship instances, including 79 different ship models in ten categories and six different large virtual scenes with different time periods, weather environments, and altitudes. The annotations include environmental information, instance-level horizontal bounding boxes, oriented bounding boxes, and the type and ID of each ship. This provides the basis for object detection, oriented object detection, fine-grained recognition, and scene recognition. To investigate the applications of UnityShip, the synthetic data were validated for model pre-training and data augmentation using three different object detection algorithms and six existing real-world ship detection datasets. Our experimental results show that for small-sized and medium-sized real-world datasets, the synthetic data achieve an improvement in model pre-training and data augmentation, showing the value and potential of synthetic data in aerial image recognition and understanding tasks.

Swin-Conv-Dspp and Global Local Transformer for Remote Sensing Image Semantic Segmentation

“…Chen et al [39] creatively proposed a new algorithm based on Swin transformer and linear spectral mixture theory for high-resolution RS images, and achieved state-of-the-art results in multiple public datasets. Li et al [40] designed a modified transformer to capture global spatial location features across different scales, and demonstrated on object detection in optical remote sensing images (DIOR) [41] and northwestern polytechnical university very high resolution -10 (NWPU VHR-10) [42] high-resolution RS image datasets' excellent segmentation accuracy. Wang et al [43] proposed a Swin transformer-based densely connected feature aggregation module by recovering resolution and generating segmentation maps by designing shared spatial attention and shared channel attention.…”

Smart Detection System of Safety Hazards in Industry 5.0

“…The use of synthetic datasets has seen a big surge in object detection. For instance, Boyong He et al [24] turned to Unity 3D to create a dataset for training algorithms to spot ships in aerial images. This move cut down on the high costs and labor of obtaining and annotating real aerial images.…”

“…Boyong He et al [24] Maritime surveillance Ship recognition in aerial images Kai Wang et al [25] Robot scene understanding Object detection in vending machine Tremblay et al [22] Objects detection for the household environment Rampini and Re Cecconi [26] Facilities management Facility management component object detection Akar et al [27] Industry Dataset for object detection Saleh et al [28] Urban scene understanding Semantic Segmentation Sutjaritvorakul et al [29] Construction site safety management Worker detection Neuhausen et al [30] Worker detection and tracking Lee and Lee [31] Worker fall detection…”

SSP3D5000: a synthetic dataset for ship 3D perception

“…The use of virtual synthesis technology to construct datasets has also been studied by some scholars.He proposed UnityShip, an aerial ship dataset synthesized using Unity, and UnityShip annotated the image with environmental information, 2D bounding boxes, rotatable 2D bounding boxes, and the type and ID of the ship [14].…”