In the past decade, underwater spectral imaging (USI) has shown great potential in underwater exploration for its high spectral and spatial resolution. This proposal presents a stare-type USI system combined with the liquid crystal tunable filter (LCTF) spectral splitting device. Considering the working features of LCTF and the theoretical model of USI, the core structure containing “imaging lens-LCTF-imaging sensor” is designed and developed. The system is compact, and the optical geometry is constructed minimally. The spectral calibration test analysis proved that the spectral response range of the system covers a full band of 400 nm to 700 nm with the highest spectral resolution between 6.7 nm and 18.5 nm. The experiments show that the system can quickly collect high-quality spectral image data by switching between different spectral bands arbitrarily. The designed prototype provides a feasible and reliable spectral imaging solution for in situ underwater targets observation with high spectrum collecting efficiency.

Vital transportation of hazardous and noxious substances (HNSs) by sea occasionally suffers spill incidents causing perilous mutilations to off-shore and on-shore ecology. Consequently, it is essential to monitor the spilled HNSs rapidly and mitigate the damages in time. Focusing on on-site and early processing, this paper explores the potential of deep learning and single-spectrum ultraviolet imaging (UV) for detecting HNSs spills. Images of three floating HNSs, including benzene, xylene, and palm oil, captured in different natural and artificial aquatic sites were collected. The image dataset involved UV (at 365 nm) and RGB images for training and comparative analysis of the detection system. The You Only Look Once (YOLOv3) deep learning model is modified to balance the higher accuracy and swift detection. With the MobileNetv2 backbone architecture and generalized intersection over union (GIoU) loss function, the model achieved mean IoU values of 86.57% for UV and 82.43% for RGB images. The model yielded a mean average precision (mAP) of 86.89% and 72.40% for UV and RGB images, respectively. The average speed of 57 frames per second (fps) and average detection time of 0.0119 s per image validated the swift performance of the proposed model. The modified deep learning model combined with UV imaging is considered computationally cost-effective resulting in precise detection accuracy and significantly faster detection speed.

No abstract

No abstract

No abstract