Monitoring marine mammals using unmanned aerial vehicles: quantifying detection certainty

Abstract

Unmanned aerial vehicles (UAVs) are increasingly being recognized as potentially useful for detection of marine mammals in their natural habitats, but an important consideration is the associated uncertainties in animal detection. We present a study based on field trials using UAVs to carry out image‐based monitoring of cetaceans in two fjords in northern Norway. We conducted 12 missions to assess the effects of both environmental‐ and aircraft‐related variables on detection certainty. Images were inspected for animal presence and its associated detection certainty. Images were also assessed for potentially important covariates such as wave turbulence (sea state), luminance, and glare. Aircraft variables such as altitude, pitch, and roll were combined into a single variable—pixel size. We recorded a total of 50 humpback whales, 63 killer whales (KW), and 118 unidentified sightings. We also recorded 57 harbor porpoise sightings. None of the environmental conditions (sea state, glare, and luminance) affected the detection certainty of harbor porpoises. In contrast, increasing sea state and luminance had negative and positive effects, respectively, on the detection certainty of humpback and KW. The detection certainty was not significantly affected by pixel size for both harbor porpoises, and humpback and KW. Our results indicate that at lower altitudes, variations in aircraft position (pitch and roll) do not have a variable effect on detection certainty. Overall, this study shows the importance of measuring variability in both environmental and flight‐related variables, in order to attain unbiased estimates of detectability for UAV‐based marine mammal surveys, particularly in Arctic and sub‐Arctic regions.

Unmanned aerial vehicle for internet of everything: Opportunities and challenges

“…For the areas with weak-connection, we list four typical regions that are construction sites in urban, disaster regions in urban, blind coverage spots in the city, and the transportation road. In these areas, some recent studies use UAVs to offer an extended network coverage and perform some specified applications such Areas with weak-connection Urban construction sites Construction project management [119]- [121] Indoor construction monitoring [122], [123] Disaster regions Disaster surveillance [80], [124], [125] Emergency networks construction [126]- [129] Urban coverage blind spots Enhanced coverage in urban area [29], [80], [130]- [133] Patrolling and surveillance [134]- [139] Transportation systems Intelligent transportation systems [140]- [143] Connection between ground vehicles [144]- [147] Areas without network deployment Farms Survey of UAV in agriculture [63], [148] Imagery analysis of crops [149]- [153] Deserts Disaster monitoring [154]- [156] Geomorphological analysis [61], [155], [157] Military detection [158] Forests Trees and plants monitoring [159]- [162] Forest growing volume prediction [163], [164] Oceans Coastal environment analysis [165]- [168] Ocean environment monitoring [169]- [171] Marine science and observation [18]...…”

“…Furthermore, the flexible deployment of UAVs also enables myriad IoE applications. Through the dedicated configuration and specified control design, UAVs have a variety of applications such as agriculture management [17], marine mammals monitoring [18], and military medical evacuation [19]. However, using UAV in IoE also poses new challenges in the perspectives of dynamic network connection, flexible network topology, precise control and lightweight intelligent algorithms.…”

Automatic whale counting in satellite images with deep learning

“…A global operationalization of our satellite-based model for whale detection and counting could greatly complement traditional methods (13)(14)(15)(16)(17)(18)(19)(20)(21) to assist whale conservation, to guide marine spatial planning (65), or to assess regional (11) and global (33) priorities for marine biodiversity protection against global change (66). In addition, since deep learning is agnostic to the type of image data used, our method could be adapted to identify and quantify other marine species such as seals and sea lions (67), penguins (68), etc.…”

Autonomous Deployment of Underwater Acoustic Monitoring Devices Using an Unmanned Aerial Vehicle: The Flying Hydrophone

“…They are relatively inexpensive compared to other monitoring techniques described above and they can be configured for a variety of uses. The most popular use of UAVs in marine mammal research have mostly been through visual observation of marine species using both fixed-wing and multirotor vehicles [42][43][44]. These vehicles usually have a camera attached to them, which enables observers to analyse images which are either stored in memory or relayed in real-time.…”