Using drone imagery analysis in rare plant demographic studies

Rominger, Kody R.; DeNittis, Alyson; Meyer, Susan E.

doi:10.1016/j.jnc.2021.126020

Cited by 16 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Important platforms for use in field studies are consumergrade fixed-wing and rotor-based drones (take-off weight totals less than 30 kg; Anderson and Gaston, 2013;Krishnasamy et al, 2019;Rominger et al, 2021). They are typically also equipped with GPS so that the captured images can be georeferenced.…”

Section: Structure From Motion (Sfm) Photogrammetrymentioning

confidence: 99%

Remote Sensing of Floral Resources for Pollinators – New Horizons From Satellites to Drones

2022

View full text Add to dashboard Cite

Insect pollinators are affected by the spatio-temporal distribution of floral resources, which are dynamic across time and space, and also influenced heavily by anthropogenic activities. There is a need for spatial data describing the time-varying spatial distribution of flowers, which can be used within behavioral and ecological studies. However, this information is challenging to obtain. Traditional field techniques for mapping flowers are often laborious and limited to relatively small areas, making it difficult to assess how floral resources are perceived by pollinators to guide their behaviors. Conversely, remote sensing of plant traits is a relatively mature technique now, and such technologies have delivered valuable data for identifying and measuring non-floral dynamics in plant systems, particularly leaves, stems and woody biomass in a wide range of ecosystems from local to global scales. However, monitoring the spatial and temporal dynamics of plant floral resources has been notably scarce in remote sensing studies. Recently, lightweight drone technology has been adopted by the ecological community, offering a capability for flexible deployment in the field, and delivery of centimetric resolution data, providing a clear opportunity for capturing fine-grained information on floral resources at key times of the flowering season. In this review, we answer three key questions of relevance to pollination science – can remote sensing deliver information on (a) how isolated are floral resources? (b) What resources are available within a flower patch? And (c) how do floral patches change over time? We explain how such information has potential to deepen ecological understanding of the distribution of floral resources that feed pollinators and the parameters that determine their navigational and foraging choices based on the sensory information they extract at different spatial scales. We provide examples of how such data can be used to generate new insights into pollinator behaviors in distinct landscape types and their resilience to environmental change.

show abstract

Section: Structure From Motion (Sfm) Photogrammetrymentioning

confidence: 99%

Remote Sensing of Floral Resources for Pollinators – New Horizons From Satellites to Drones

2022

View full text Add to dashboard Cite

show abstract

“…Our protocol for acquiring and processing drone imagery for analysis is described in detail in our earlier papers [3,9]. For the present work, drone flights were made using DJI Phantom 4 Pro V2 drones (SZ DJI Technology Co. Ltd. Shenzhen, China), which were equipped with a stock 20 MP camera (f/2.8-f/11, 84 • FOV).…”

Section: Drone Flights and Imagery Processingmentioning

confidence: 99%

“…To mitigate this problem, we used only census (40 m AGL) imagery from areas that also had validation (15 m AGL) imagery. The visual difference in image quality from 40 to 15 m AGL is quite dramatic (Figure 3), and the majority of poppies can be reliably confirmed in the 15 m AGL imagery [9]. Training images were obtained from across all poppy populations for which drone imagery was available.…”

Section: Training Imagery Selectionmentioning

confidence: 99%

“…We began our efforts to use drone imagery analysis to census this species in 2018 and have completed census for three of the eight formally recognized populations [4] based on visual analysis of the resulting imagery [3,9]. Relatively inexpensive and easy-to-use drones equipped with high resolution cameras are capable of low-altitude flights over relatively large areas in short time frames.…”

Section: Introductionmentioning

confidence: 99%

“…This species is a good candidate for a remote sensing approach because it grows in sparsely vegetated habitat (Figure 1), and because of its unique blue-green color and mounding growth form (Figure 2b). We began our efforts to use drone imagery analysis to census this species in 2018 and have completed census for three of the eight formally recognized populations [4] based on visual analysis of the resulting imagery [3,9]. Relatively inexpensive and easy-to-use drones equipped with high resolution cameras are capable of low-altitude flights over relatively large areas in short time frames.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Drones, Deep Learning, and Endangered Plants: A Method for Population-Level Census Using Image Analysis

Rominger

Meyer

2021

Drones

Self Cite

View full text Add to dashboard Cite

A census of endangered plant populations is critical to determining their size, spatial distribution, and geographical extent. Traditional, on-the-ground methods for collecting census data are labor-intensive, time-consuming, and expensive. Use of drone imagery coupled with application of rapidly advancing deep learning technology could greatly reduce the effort and cost of collecting and analyzing population-level data across relatively large areas. We used a customization of the YOLOv5 object detection model to identify and count individual dwarf bear poppy (Arctomecon humilis) plants in drone imagery obtained at 40 m altitude. We compared human-based and model-based detection at 40 m on n = 11 test plots for two areas that differed in image quality. The model out-performed human visual poppy detection for precision and recall, and was 1100× faster at inference/evaluation on the test plots. Model inference precision was 0.83, and recall was 0.74, while human evaluation resulted in precision of 0.67, and recall of 0.71. Both model and human performance were better in the area with higher-quality imagery, suggesting that image quality is a primary factor limiting model performance. Evaluation of drone-based census imagery from the 255 ha Webb Hill population with our customized YOLOv5 model was completed in <3 h and provided a reasonable estimate of population size (7414 poppies) with minimal investment of on-the-ground resources.

show abstract

Using real-time kinetic GPS (RTK-GPS) to improve the assessment of population dynamics and optimize population viability studies of threatened species

Far,

Capó,

Cursach

2024

Biodivers Conserv

View full text Add to dashboard Cite

The conservation of threatened plant species needs precise monitoring studies to assess population trends and improve management strategies. Here, we investigated the viability of employing high-accuracy RTK-GPS technology for demographic evaluation of Euphorbia fontqueriana, a critically endangered species of the western Mediterranean Basin. Our study aimed to evaluate the utility of RTK-GPS technology, compare its applicability with traditional methods, and determine its impact on decision-making in conservation. We used permanent plots and comprehensive field surveys to monitor population dynamics, and transitions between plant stages and vital rates were recorded and analysed. Results revealed a positive population trend for E. fontqueriana, contrasting with previous studies. Vegetative stage was the most representative of the population, and high survival rates were observed for vegetative and reproductive individuals. Elasticity analysis showed higher value for vegetative stage. The study underscores the importance of employing high-accuracy plant monitoring methods for effective conservation assessments and emphasizes the potential of RTK-GPS technology in enhancing conservation efforts for threatened plant species.

show abstract

Using drone imagery analysis in rare plant demographic studies

Cited by 16 publications

References 20 publications

Remote Sensing of Floral Resources for Pollinators – New Horizons From Satellites to Drones

Remote Sensing of Floral Resources for Pollinators – New Horizons From Satellites to Drones

Drones, Deep Learning, and Endangered Plants: A Method for Population-Level Census Using Image Analysis

Using real-time kinetic GPS (RTK-GPS) to improve the assessment of population dynamics and optimize population viability studies of threatened species

Contact Info

Product

Resources

About