Automatic Boat Identification System for VIIRS Low Light Imaging Data

Abstract

Abstract:The ability for satellite sensors to detect lit fishing boats has been known since the 1970s. However, the use of the observations has been limited by the lack of an automatic algorithm for reporting the location and brightness of offshore lighting features arising from boats. An examination of lit fishing boat features in Visible Infrared Imaging Radiometer Suite (VIIRS) day/night band (DNB) data indicates that the features are essentially spikes. We have developed a set of algorithms for automatic detection of spikes and characterization of the sharpness of spike features. A spike detection algorithm generates a list of candidate boat detections. A second algorithm measures the height of the spikes for the discard of ionospheric energetic particle detections and to rate boat detections as either strong or weak. A sharpness index is used to label boat detections that appear blurry due to the scattering of light by clouds. The candidate spikes are then filtered to remove features on land and gas flares. A validation study conducted using analyst selected boat detections found the automatic algorithm detected 99.3% of the reference pixel set. VIIRS boat detection data can provide fishery agencies with up-to-date information of fishing boat activity and changes in this activity in response to new regulations and enforcement regimes. The data can provide indications of illegal fishing activity in restricted areas and incursions across Exclusive Economic Zone (EEZ) boundaries. VIIRS boat detections occur widely offshore from East and Southeast Asia, South America and several other regions.

VIIRS night-time lights

“…Each 16-line sweep across the Earth is termed a scan. A method was developed in 2014 to detect and filter out lightning (Elvidge et al 2015). The procedure involves calculating the relative radiance difference between adjacent lines of DNB data.…”

“…An initial filtering is done using thresholds placed on the DNB radiance and spike height index (SHI) (Elvidge et al 2015). SHI is calculated in two stages.…”

Vessel detection and classification from spaceborne optical images: A literature survey

“…Nonetheless, some publications have shown that in particular fishing ships can be detected by their nightlights from space; e.g. Cho et al (1999) with OLS, and Elvidge et al (2015), Lebona et al (2016) and Straka et al (2015) with VIIRS.…”

An Object Similarity-Based Thresholding Method for Urban Area Mapping from Visible Infrared Imaging Radiometer Suite Day/Night Band (VIIRS DNB) Data

“…Because of the improved performance, VIIRS DNB data have been used in various applications, such as extracting urban areas [23][24][25][26][27], reflecting demographic and socioeconomic conditions [25,[28][29][30][31][32][33], monitoring nocturnal surface air quality [34][35][36], and so on [26,[37][38][39][40][41].…”