Robust and Fair Undersea Target Detection with Automated Underwater Vehicles for Biodiversity Data Collection

Dinakaran, Ranjith and Zhang, Li and Li, Chang-Tsun and Bouridane, Ahmed and Jiang, Richard (2022) Robust and Fair Undersea Target Detection with Automated Underwater Vehicles for Biodiversity Data Collection. Remote Sensing, 14 (15): 3680. ISSN 2072-4292

Text (remotesensing-14-03680-v2)
remotesensing_14_03680_v2.pdf - Published Version
Available under License Creative Commons Attribution.
Download (3MB)

Abstract

Undersea/subsea data collection via automated underwater vehicles (AUVs) plays an important role for marine biodiversity research, while it is often much more challenging than the data collec-tion above ground via satellites or AUVs. To enable the automated undersea/subsea data collec-tion system, the AUVs are expected to be able to automatically track the objects of interest through what they can “see” from their mounted underwater cameras, where videos or images could be drastically blurred and degraded in underwater lighting conditions. To solve this chal-lenge, in this work, we propose a cascaded framework by combining a DCGAN (deep convolu-tional generative adversarial network) with an object detector, i.e., single-shot detector (SSD), named DCGAN+SSD, for the detection of various underwater targets from the mounted camera of an automated underwater vehicle. In our framework, our assumption is that DCGAN can be leveraged to alleviate the impact of underwater conditions and provide the object detector with a better performance for automated AUVs. To optimize the hyperparameters of our models, we ap-plied a particle swarm optimization (PSO)-based strategy to improve the performance of our proposed model. In our experiments, we successfully verified our assumption that the DCGAN+SSD architecture can help improve the object detection toward the undersea conditions and achieve apparently better detection rates over the original SSD detector. Further experiments showed that the PSO-based optimization of our models could further improve the model in object detection toward a more robust and fair performance, making our work a promising solution for tackling the challenges in AUVs.