Automated Identification of River Hydromorphological Features Using UAV High Resolution Aerial Imagery

Casado, Mónica Rivas; Ballesteros, Rocío; Kriechbaumer, Thomas; Veal, Amanda Veal

doi:10.3390/s151127969

Cited by 108 publications

(97 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Future work might consider the use of drone-mounted optical systems operating beyond the visible range of the spectrum, particularly in the near-infrared and shortwave infrared regions of spectrum where water bodies are spectrally distinct [25]. Efforts could also be made in the future for automatic detection of water bodies using drone imagery (such as Casado et al [48]); the calibration/training of such models, however, is relatively time-consuming and therefore manual interpretation and delineation of water bodies, as demonstrated to be successful in this study, represents a more operationally valid option for malaria managers.…”

Section: Resultsmentioning

confidence: 99%

Using low-cost drones to map malaria vector habitats

et al. 2017

View full text Add to dashboard Cite

BackgroundThere is a growing awareness that if we are to achieve the ambitious goal of malaria elimination, we must compliment indoor-based vector control interventions (such as bednets and indoor spraying) with outdoor-based interventions such as larval source management (LSM). The effectiveness of LSM is limited by our capacity to identify and map mosquito aquatic habitats. This study provides a proof of concept for the use of a low-cost (< $1000) drone (DJI Phantom) for mapping water bodies in seven sites across Zanzibar including natural water bodies, irrigated and non-irrigated rice paddies, peri-urban and urban locations.ResultsWith flying times of less than 30 min for each site, high-resolution (7 cm) georeferenced images were successfully generated for each of the seven sites, covering areas up to 30 ha. Water bodies were readily identifiable in the imagery, as well as ancillary information for planning LSM activities (access routes to water bodies by road and foot) and public health management (e.g. identification of drinking water sources, mapping individual households and the nature of their construction).ConclusionThe drone-based surveys carried out in this study provide a low-cost and flexible solution to mapping water bodies for operational dissemination of LSM initiatives in mosquito vector-borne disease elimination campaigns. Generated orthomosaics can also be used to provide vital information for other public health planning activities.Electronic supplementary materialThe online version of this article (doi:10.1186/s13071-017-1973-3) contains supplementary material, which is available to authorized users.

show abstract

Section: Resultsmentioning

confidence: 99%

Using low-cost drones to map malaria vector habitats

et al. 2017

View full text Add to dashboard Cite

show abstract

“…UAS-technology is also especially favourable for monitoring purposes with short and/or user-defined repetition intervals. Our automated classification approach for water versus vegetation and at the growth-form level is highly applicable in lake and river management [53] and aquatic plant control, such as in evaluation of rehabilitation measures [54]. Valta-Hulkkonen et al [55] also found that a lake's degree of colonisation by helophytes and nymphaeids detected by remote sensing was positively correlated with the nutrient content in the water.…”

Section: Discussionmentioning

confidence: 99%

Comparison of Manual Mapping and Automated Object-Based Image Analysis of Non-Submerged Aquatic Vegetation from Very-High-Resolution UAS Images

2016

View full text Add to dashboard Cite

Aquatic vegetation has important ecological and regulatory functions and should be monitored in order to detect ecosystem changes. Field data collection is often costly and time-consuming; remote sensing with unmanned aircraft systems (UASs) provides aerial images with sub-decimetre resolution and offers a potential data source for vegetation mapping. In a manual mapping approach, UAS true-colour images with 5-cm-resolution pixels allowed for the identification of non-submerged aquatic vegetation at the species level. However, manual mapping is labour-intensive, and while automated classification methods are available, they have rarely been evaluated for aquatic vegetation, particularly at the scale of individual vegetation stands. We evaluated classification accuracy and time-efficiency for mapping non-submerged aquatic vegetation at three levels of detail at five test sites (100 m × 100 m) differing in vegetation complexity. We used object-based image analysis and tested two classification methods (threshold classification and Random Forest) using eCognition ® . The automated classification results were compared to results from manual mapping. Using threshold classification, overall accuracy at the five test sites ranged from 93% to 99% for the water-versus-vegetation level and from 62% to 90% for the growth-form level. Using Random Forest classification, overall accuracy ranged from 56% to 94% for the growth-form level and from 52% to 75% for the dominant-taxon level. Overall classification accuracy decreased with increasing vegetation complexity. In test sites with more complex vegetation, automated classification was more time-efficient than manual mapping. This study demonstrated that automated classification of non-submerged aquatic vegetation from true-colour UAS images was feasible, indicating good potential for operative mapping of aquatic vegetation. When choosing the preferred mapping method (manual versus automated) the desired level of thematic detail and the required accuracy for the mapping task needs to be considered.

show abstract

“…Machine learning tools are almost ubiquitously applied to rapidly classify images, from fine [34] to broad scales [35]. These methods are also being used in fisheries, where researchers are combining sonar sensing methods and machine learning tools (e.g., [36]).…”

Section: Image Classificationmentioning

confidence: 99%

Development of Active Numerating Side-scan for a High-Density Overwintering Location for Endemic Shortnose Sturgeon (Acipenser brevirostrum) in the Saint John River, New Brunswick

et al. 2020

View full text Add to dashboard Cite

In 1979, the Shortnose Sturgeon (Acipenser brevirostrum) population of the Saint John River, New Brunswick, was estimated at 18,000 ± 5400 individuals. More recently, an estimate of 4836 ± 69 individuals in 2005, and between 3852 and 5222 individuals in 2009 and 2011, was made based on a single Shortnose Sturgeon winter aggregation in the Kennebecasis Bay of the Saint John River, a location thought to contain a large proportion of the population. These data, in combination with the Saint John River serving as the sole spawning location for Shortnose Sturgeon in Canada prompted a species designation of "Special Concern" in 2015 under Canada's Species at Risk Act (SARA). A three-decade span of scientific observations amplified by the traditional knowledge and concerns of local indigenous groups have pointed to a declining population. However, the endemic Shortnose Sturgeon population of the Saint John River has not been comprehensively assessed in recent years. To help update the population estimate, we tested a rapid, low-cost side-scan sonar mapping method coupled with supervised image classification to enumerate individual Sturgeon in a previously undescribed critical winter location in the Saint John River. We then conducted an underwater video camera survey of the area, in which we did not identify any fish species other than Shortnose Sturgeon. These data were then synchronized with four years of continuous acoustic tracking of 18 Shortnose Sturgeon to produce a population estimate in each of the five identified winter habitats and the Saint John River as a whole. Using a side-scan sonar, we identified > 12,000 Shortnose Sturgeon in a single key winter location and estimated the full river population as > 20,000 individuals >~40 cm fork length. We conclude that the combined sonar/image processing method presented herein provides an effective and rapid assessment of large fish such as Sturgeon when occurring in winter aggregation. Our results also indicate that the Shortnose Sturgeon population of the Saint John River could be similar to the last survey estimate conducted in the late 1970s, but more comprehensive and regular surveys are needed to more accurately assess the state of the population.

show abstract

Automated Identification of River Hydromorphological Features Using UAV High Resolution Aerial Imagery

Cited by 108 publications

References 30 publications

Using low-cost drones to map malaria vector habitats

Using low-cost drones to map malaria vector habitats

Comparison of Manual Mapping and Automated Object-Based Image Analysis of Non-Submerged Aquatic Vegetation from Very-High-Resolution UAS Images

Development of Active Numerating Side-scan for a High-Density Overwintering Location for Endemic Shortnose Sturgeon (Acipenser brevirostrum) in the Saint John River, New Brunswick

Contact Info

Product

Resources

About