Thermal-Infrared Remote Target Detection System for Maritime Rescue based on Data Augmentation with 3D Synthetic Data
This addresses the problem of dataset scarcity and unclear boundaries in thermal-infrared detection for maritime rescue, though it is incremental as it builds on existing domain adaptation and segmentation techniques.
The paper tackles thermal-infrared target detection for maritime rescue by using a domain adaptation algorithm to bridge the gap between synthetic and real data, resulting in a segmentation model that outperforms state-of-the-art methods and shows large improvements over training on real data alone.
This paper proposes a thermal-infrared (TIR) remote target detection system for maritime rescue using deep learning and data augmentation. We established a self-collected TIR dataset consisting of multiple scenes imitating human rescue situations using a TIR camera (FLIR). Additionally, to address dataset scarcity and improve model robustness, a synthetic dataset from a 3D game (ARMA3) to augment the data is further collected. However, a significant domain gap exists between synthetic TIR and real TIR images. Hence, a proper domain adaptation algorithm is essential to overcome the gap. Therefore, we suggest a domain adaptation algorithm in a target-background separated manner from 3D game-to-real, based on a generative model, to address this issue. Furthermore, a segmentation network with fixed-weight kernels at the head is proposed to improve the signal-to-noise ratio (SNR) and provide weak attention, as remote TIR targets inherently suffer from unclear boundaries. Experiment results reveal that the network trained on augmented data consisting of translated synthetic and real TIR data outperforms that trained on only real TIR data by a large margin. Furthermore, the proposed segmentation model surpasses the performance of state-of-the-art segmentation methods.