Object detection in aerial images is a growing area of research, with maritime object detection being a particularly important task for reliable surveillance, monitoring, and active rescuing. Notwithstanding astonishing advances of computer visiontechnologies, detecting ships and floating matters in these images are challenging due to factors such as object distance. What makes it worse is pervasive sea surface effects such as sunlight reflection, wind, and waves. Hyperspectral image (HSI) sensors, providing more than 100 channels in wavelengths of visible and near-infrared, can extract intrinsic information of materials from a few pixels of HSIs.The advent of HSI sensors motivates us to leverage HSIs to circumvent false positives due to the sea surface effects.Unfortunately, there are few public HSI datasets due to the high cost and labor involved in collecting them, hindering object detection research based on HSIs. We have collected and annotated a new dataset called ``Multi-Modal Ship and flOating matter Detection in Aerial Images (M$^{2}$SODAI),'', which includes synchronized image pairs of RGB and HSI data, along with bounding box labels for nearly 6,000 instances per category. We also propose a new multi-modal extension of the feature pyramid network called DoubleFPN.Extensive experiments on our benchmark demonstrate that fusion of RGB and HSI data can enhance mAP, especially in the presence of the sea surface effects.

The Remotely sensed satellite or airborne images can aid rapid vessel monitoring over wide areas at high resolutions. In this study, airborne hyperspectral experiments were performed to detect marine vessels mainly including fishing boat and yacht by applying pixel-based mixture techniques and to estimate the size of the vessels through an objective ellipse fitting method. Several hyperspectral mixture algorithms, such as N-FINDR, pixel purity index (PPI), independent component analysis (ICA), and vertex component analysis (VCA), were used for the detection of vessels. The pixel-based probability of detection (POD) and false alarm ratio (FAR) for all 14 vessels were 96.40% and 4.30%, respectively. Compared with the digital mapping camera (DMC) images with resolutions of 0.10 m, the root-mean-square error of the length and width of the vessels were approximately 1.19 m and 0.81 m, respectively.

Hazardous Noxious Substance (HNS) is transported entirely through large vessels, so there is always a potential risk of marine HNS spills. In the event of an HNS accident, it can cause enormous human and property damage, so prompt detection is required. However, there is a limit to human access by ship, we need to use remote sensing data. In this study, ground experiments using hyperspectral cameras were performed to construct a spectral library of HNS. We classified the HNS and non-HNS by applying the hyperspectral mixture algorithm, and presented the HNS detection probability for every pixel by calculating the spectrum-based abundance fraction. The results of this study are expected to be used to estimate the extent of HNS spill in the event of a marine HNS accident.

In this study, the effect of hyperspectral atmospheric correction on accuracy of the ship detection was investigated. We applied two atmospheric correction algorithms on airborne hyperspectral data and then detected ship features from reflectance corrected by each algorithms with an unsupervised target detection method. Both ATREM and FLAASH algorithms produce comparable atmospheric correction results but the algorithm which applied with further correction options optimized for coastal monitoring purpose reveals better detection results for ship detection. Compared to the result from ATREM, the result from FLAASH-corrected reflectance shows a distinct contrast between the ship and surrounding background seawater. Mean values of spectral angles between target and endmember spectra were 0.2388 (ATREM) and 0.2169 (FLAASH). This implies a further optimization of the atmospheric correction can improve the performance of target detection using airborne hyperspectral data, especially for maritime search purpose.