Use of unmanned aircraft systems (UAS) and multispectral imagery for quantifying agricultural areas damaged by wild pigs

Fischer, Justin W.; Greiner, Kelsey; Lutman, Mark W.; Webber, Bryson L.; VerCauteren, Kurt C.

doi:10.1016/j.cropro.2019.104865

Cited by 12 publications

(19 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Validations of classified imagery, or ground truthing, further improve confidence in drones as a detection method for feral horse damage, as they revealed 69.5% and 70.1% accuracies of classified imagery for April 2019 and December 2020, respectively. Comparatively, similar validations for the semi‐automated classification of wild pig damage in agricultural fields using RGB imagery led to estimates of 74%–94% accuracy (Fischer et al, 2019). The higher accuracies in the study involving wild pigs were likely due to the homogenous agricultural landscape where damage stands out better; pigs knocked down large regions of corn, leaving flat and discoloured areas.…”

Section: Discussionmentioning

confidence: 94%

“…The use of drones for the assessment of animal pest impacts on an environment is relatively new, with most past studies focussing on agricultural damage from feral animals rather than their impacts to protected areas (e.g. national parks; Fischer et al, 2019, Pla et al, 2019). Drones have, however, been well‐used for the assessment of the extent and damage of plant pest species in protected areas, and found to be an effective way to assess damage and change over time (Hill et al, 2017; Müllerová et al, 2017; Perroy et al, 2017).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Drones are an effective tool to assess the impact of feral horses in an alpine riparian environment

et al. 2023

View full text Add to dashboard Cite

Protected areas can be impacted by the presence and proliferation of feral species. Effective management of feral species requires reliable tools to monitor their population size and ecological impacts. Here, we used drone‐based image analysis to assess evidence of feral horses and horse‐specific ecological impacts on alpine riparian habitat. Valleys with low (0), medium (1–16) and high (>16) horse abundances were chosen for drone imagery analysis based on independent aerial counts of horses. Data collection trips were carried out pre‐ and post‐2019/2020 wildfires, which unexpectedly burnt valleys with low horse presence. Drone‐based RGB orthomosaic imagery was sufficient to identify seven indicators of horse presence and determine the severity of feral horse impacts. Despite the impact of fire, drone‐derived classifications were able to accurately detect a gradient of horse impacts, showing a significant difference in indicators from low presence valleys compared with medium and high presence valleys, which did not differ significantly from each other. The significance of differences between valleys reveals that regions routinely inhabited by feral horses will display significant environmental impacts. Our results clearly indicated significant differences between valleys with low horse presence compared with either medium or high horse presence regions (0.01 for differences between both low and medium and low and high horse presence). This was evident both before and after the 2019/2020 fires, suggesting that wildfires did not significantly impact horse populations or distribution in the sampled region. Overall, it was evident that feral horses have a clear and definable impact on alpine riparian vegetation, and drone surveying can be used to routinely monitor potential spread and the outcome of management actions.

show abstract

Section: Discussionmentioning

confidence: 94%

Section: Discussionmentioning

confidence: 99%

Drones are an effective tool to assess the impact of feral horses in an alpine riparian environment

et al. 2023

View full text Add to dashboard Cite

show abstract

“…This article provides an integrated drone solution to capture multi-spectral images with geotagging, which has important reference value in terrain and scene perception. Fischer et al (2019) combined multi-spectral and drone technology and used feature extraction algorithms to detect cornfield areas damaged by wild boar. This yields a new monitoring technology that effectively acquires terrain information and assesses the damage of crops based on its description.…”

Section: Multi-spectral Imaging Technologymentioning

confidence: 99%

Recognition and Localization Methods for Vision-Based Fruit Picking Robots: A Review

et al. 2020

View full text Add to dashboard Cite

The utilization of machine vision and its associated algorithms improves the efficiency, functionality, intelligence, and remote interactivity of harvesting robots in complex agricultural environments. Machine vision and its associated emerging technology promise huge potential in advanced agricultural applications. However, machine vision and its precise positioning still have many technical difficulties, making it difficult for most harvesting robots to achieve true commercial applications. This article reports the application and research progress of harvesting robots and vision technology in fruit picking. The potential applications of vision and quantitative methods of localization, target recognition, 3D reconstruction, and fault tolerance of complex agricultural environment are focused, and fault-tolerant technology designed for utilization with machine vision and robotic systems are also explored. The two main methods used in fruit recognition and localization are reviewed, including digital image processing technology and deep learning-based algorithms. The future challenges brought about by recognition and localization success rates are identified: target recognition in the presence of illumination changes and occlusion environments; target tracking in dynamic interference-laden environments, 3D target reconstruction, and fault tolerance of the vision system for agricultural robots. In the end, several open research problems specific to recognition and localization applications for fruit harvesting robots are mentioned, and the latest development and future development trends of machine vision are described.

show abstract

“…Recent research has focused on drones and object detection technology to monitor timing and extent of wild pig damage at a field scale (Michez et al 2016, Kuzelka and Surovy 2018, Rutten et al 2018, Samiappan et al 2018, Fischer et al 2019). Approaches to train and fully automate classification of wild pig damage include crop height models (Michez et al 2016, Kuzelka and Surovy 2018), vegetation indices calculated from multispectral drone imagery (Houborg and McCabe 2016, Fischer et al 2019), and textural feature extractions (Samiappan et al 2018, Fischer et al 2019). Studies concluded that drone approaches were a useful tool to efficiently estimate wild pig damaged areas in crops, yet when it came to determining yield losses, an approximate estimate based on regional yield averages was used (Rutten et al 2018).…”

mentioning

confidence: 99%

“…Samiappan et al 2018, Fischer et al 2019, Foster 2021). However, Rutten et al (2018) found a higher average loss (17.2%) toT A B L E 4a Total loss of income due to wild pig damage.…”

mentioning

confidence: 99%

Using drones to detect and quantify wild pig damage and yield loss in corn fields throughout plant growth stages

Friesenhahn

Massey

DeYoung

et al. 2023

Wildlife Society Bulletin

Self Cite

View full text Add to dashboard Cite

Presently, there are an estimated 6.9 million wild pigs (Sus scrofa) in the U.S., which cause over US$1 billion in damage to agriculture, environmental impacts, and control costs. However, estimates of damage have varied widely, creating a need for standardized monitoring and a method to accurately estimate the economic costs of direct wild pig damage to agriculture. The goal of our study was to integrate remotely sensed imagery from drones and crop harvest data to quantify wild pig damage in corn fields. We used drones with natural color (red, green, blue) cameras to monitor corn fields at different growth stages in an agricultural matrix in Delta County, Texas, USA, during 2019-2020. We flew 36 drone missions and classified wild pig damage in 18 orthomosaics by a combination of manually digitizing and deep-learning algorithms. We compared estimates of damage from drone imagery to those derived from ground-based transect surveys, to verify pig damage. Finally, we compared damaged areas of fields to maps of collected real-time yields at harvest to estimate yield loss. All classified drone orthomosaics of pig damage had >80% overall accuracy for all growth stages. Ground transect surveys,

show abstract

Use of unmanned aircraft systems (UAS) and multispectral imagery for quantifying agricultural areas damaged by wild pigs

Abstract: Use of unmanned aircraft systems (UAS) and multispectral imagery for quantifying agricultural areas damaged by wild pigs" (2019).

Cited by 12 publications

References 42 publications

Drones are an effective tool to assess the impact of feral horses in an alpine riparian environment

Drones are an effective tool to assess the impact of feral horses in an alpine riparian environment

Recognition and Localization Methods for Vision-Based Fruit Picking Robots: A Review

Using drones to detect and quantify wild pig damage and yield loss in corn fields throughout plant growth stages

Contact Info

Product

Resources

About