SeaDroneSim: Simulation of Aerial Images for Detection of Objects Above Water

TL;DR

A new benchmark suite, SeaD-roneSim, that can be used to create photo-realistic aerial image datasets with ground truth for segmentation masks of any given object is presented, which serves as a baseline for the detection of the BlueROV, a popular, open source, remotely operated underwater vehicle (BlueROV) in this feasibility study.

Abstract

Unmanned Aerial Vehicles (UAVs) are known for their fast and versatile applicability. With UAVs' growth in availability and applications, they are now of vital importance in serving as technological support in search-and-rescue(SAR) operations in marine environments. High-resolution cameras and GPUs can be equipped on the UAVs to provide effective and efficient aid to emergency rescue operations. With modern computer vision algorithms, we can detect objects for aiming such rescue missions. However, these modern computer vision algorithms are dependent on numerous amounts of training data from UAVs, which is time-consuming and labor-intensive for maritime environments. To this end, we present a new benchmark suite, SeaDroneSim, that can be used to create photo-realistic aerial image datasets with the ground truth for segmentation masks of any given object. Utilizing only the synthetic data generated from SeaDroneSim, we obtain 71 mAP on real aerial images for detecting BlueROV as a feasibility study. This result from the new simulation suit also serves as a baseline for the detection of BlueROV.

Figures (7)

• Figure 1: (a) Typical image examples with varying altitudes, angles of view and background water color. (b) Corresponding ground truth masks for the object of interest (BlueROV).
• Figure 2: An overview of our approach: 3D models for the object of interest are used in SeaDroneSim to generate Synthetic datasets. Noted the synthetic dataset would include its ground truth mask for the object of interest. The synthetic dataset generated is then fed into a Neural network to obtain the object detection result. Note: Object Detection images are cropped and enlarged for better visualization.
• Figure 3: (a) BlueROV in water near Horn Point Lab, (b) BlueROV in Blender$^{\text{TM}}$, (c) BlueROV in water in Horn Point Lab, (d) BlueROV in Blender$^{\text{TM}}$.
• Figure 4: Different water colors and turbidity levels.
• Figure 5: Images from different altitudes. (a) Image from an altitude equal to 20 m, (b) image from an altitude equal to 30 m, (c) image from an altitude equal to 40 m, (d)(e)(f) are the corresponding ground truth masks for (a)(b)(c).