Small unmanned aircraft systems (UAS) may be useful for conducting high-precision, low-disturbance waterbird surveys, but limited data exist on their effectiveness. We evaluated the capacity of a small UAS to census a large (>6,000 nests) coastal Common tern (Sterna hirundo) colony of which ground surveys are particularly disruptive and time-consuming. We compared aerial photographic tern counts to ground nest counts in 45 plots (5-m radius) throughout the colony at three intervals over a nine-day period in order to identify sources of variation and establish a coefficient to estimate nest numbers from UAS surveys. We also compared a full colony ground count to full counts from two UAS surveys conducted the following day. Finally, we compared colony disturbance levels over the course of UAS flights to matched control periods. Linear regressions between aerial and ground counts in plots had very strong correlations in all three comparison periods (R² = 0.972–0.989, P < 0.001) and regression coefficients ranged from 0.928–0.977 terns/nest. Full colony aerial counts were 93.6% and 94.0%, respectively, of the ground count. Varying visibility of terns with ground cover, weather conditions and image quality, and changing nest attendance rates throughout incubation were likely sources of variation in aerial detection rates. Optimally timed UAS surveys of Common tern colonies following our method should yield population estimates in the 93–96% range of ground counts. Although the terns were initially disturbed by the UAS flying overhead, they rapidly habituated to it. Overall, we found no evidence of sustained disturbance to the colony by the UAS. We encourage colonial waterbird researchers and managers to consider taking advantage of this burgeoning technology.

Bird surveys conducted using aerial images can be more accurate than those using airborne observers, but can also be more time-consuming if images must be analyzed manually. Recent advances in digital cameras and image-analysis software offer unprecedented potential for computer-automated bird detection and counts in high-resolution aerial images. We review the literature on this subject and provide an overview of the main image-analysis techniques. Birds that contrast sharply with image backgrounds (e.g., bright birds on dark ground) are generally the most amenable to automated detection, in some cases requiring only basic image-analysis software. However, the sophisticated analysis capabilities of modern object-based image analysis software provide ways to detect birds in more challenging situations based on a variety of attributes including color, size, shape, texture, and spatial context. Some techniques developed to detect mammals may also be applicable to birds, although the prevalent use of aerial thermal-infrared images for detecting large mammals is of limited applicability to birds because of the low pixel resolution of thermal cameras and the smaller size of birds. However, the increasingly high resolution of true-color cameras and availability of small unmanned aircraft systems (drones) that can fly at very low altitude now make it feasible to detect even small shorebirds in aerial images. Continued advances in camera and drone technology, in combination with increasingly sophisticated image analysis software, now make it possible for investigators involved in monitoring bird populations to save time and resources by increasing their use of automated bird detection and counts in aerial images. We recommend close collaboration between wildlife-monitoring practitioners and experts in the fields of remote sensing and computer science to help generate relevant, accessible, and readily applicable computer-automated aerial photographic census techniques. Conteo de aves realizados utilizando imágenes aéreas pueden ser mas precisos que los que utilizan observadores desde el aire, pero pueden consumir mas tiempo si las imágenes tienen que ser analizadas manualmente. Avances recientes en cámaras digitales y software de análisis de imágenes ofrecen un potencial sin precedentes para la detección computacional automática de aves y conteos en imágenes aéreas de alta resolución. Revisamos la literatura en este tema y ofrecemos una visión general de las principales técnicas de análisis en imágenes. Las aves que tienen un fuerte contraste con los fondos de las imágenes (e.g., aves brillantes en fondos oscuros) son en general las mas sensibles a las detecciones automáticas, en algunos casos solo requieren un software básico de analizador de imágenes. Sin embargo, las sofisticadas capacidades de los software de análisis modernos en imágenes basadas en objetos, proveen formas de detectar aves en situaciones mas desafiantes basadas en una variedad de atributos incluyendo el color, tamaño, forma, textura y contexto espacial. Algunas técnicas desarrolladas para detectar mamíferos pueden ser aplicables en aves, aunque el uso predominante de imágenes aéreas de infra rojo térmico para detectar grandes mamíferos tienen aplicabilidad limitada para las aves, debido a la baja resolución en los pixeles de las cámaras térmicas y el tamaño pequeño de las aves. Sin embargo, el incremento en la alta resolución de las cámaras de color y la disponibilidad de pequeños sistemas de aeronaves no tripuladas (drones) que pueden volar a bajas elevaciones, ahora hacen que sea posible detectar incluso pequeñas aves playeras en imágenes aéreas. Los continuos avances en la tecnología de la cámara y aeronaves no tripuladas, en combinación con software de análisis de imágenes cada vez más sofisticados, ahora hacen posible ahorrara tiempo y recursos a los investigadores involucrados en el monitoreo de las poblaciones de aves, mediante el aumento del uso de la detección y conteos de aves automatizado en imágenes aéreas. Recomendamos una estrecha colaboración entre los profesionales de monitoreo de fauna silvestre y expertos en el campo de la teledetección y la informática para ayudar a generar técnicas de censo relevantes, accesibles y de fácil aplicación automatizada computacionalmente utilizando fotografías aéreas.

High-resolution drone aerial surveys combined with object-based image analysis are transforming our capacity to monitor and manage aquatic vegetation in an era of invasive species. To better exploit the potential of these technologies, there is a need to develop more efficient and accessible analysis workflows and focus more efforts on the distinct challenge of mapping submerged vegetation. We present a straightforward workflow developed to monitor emergent and submerged invasive water soldier (Stratiotes aloides) in shallow waters of the Trent-Severn Waterway in Ontario, Canada. The main elements of the workflow are: (1) collection of radiometrically calibrated multispectral imagery including a near-infrared band; (2) multistage segmentation of the imagery involving an initial separation of above-water from submerged features; and (3) automated classification of features with a supervised machine-learning classifier. The approach yielded excellent classification accuracy for emergent features (overall accuracy = 92%; kappa = 88%; water soldier producer’s accuracy = 92%; user’s accuracy = 91%) and good accuracy for submerged features (overall accuracy = 84%; kappa = 75%; water soldier producer’s accuracy = 71%; user’s accuracy = 84%). The workflow employs off-the-shelf graphical software tools requiring no programming or coding, and could therefore be used by anyone with basic GIS and image analysis skills for a potentially wide variety of aquatic vegetation monitoring operations.

Chabot, D., C. Dillon, and C. M. Francis. 2018. An approach for using off-the-shelf object-based image analysis software to detect and count birds in large volumes of aerial imagery. Avian Conservation and Ecology 13(1):15. https://doi.org/10.5751/ACE-01205-130115