Susan N. Ellis-Felege

Wildlife@Home: Combining Crowd Sourcing and Volunteer Computing to Analyze Avian Nesting Video

New camera technology is allowing avian ecologists to perform detailed studies of avian behavior, nesting strategies and predation in areas where it was previously impossible to gather data. Unfortunately, studies have shown mechanical triggers and a variety of sensors to be inadequate in capturing footage of small predators (e.g., snakes, rodents) or events in dense vegetation. Because of this, continuous camera recording is currently the most robust solution for avian monitoring, especially in ground nesting species. However, continuous video footage results in a data deluge, as monitoring enough nests to make biologically significant inferences results in massive amounts of data which is unclassifiable by humans alone. In the summer of 2012, Dr. Ellis-Felege gathered video footage from 63 sharp-tailed grouse (Tympanuchus phasianellus) nests, as well as preliminary interior least tern (Sternula antillarum) and piping plover (Charadrius melodus) nests, resulting in over 20,000 hours of video footage. In order to effectively analyze this video, a project combining both crowd sourcing and volunteer computing was developed, where volunteers can stream nesting video and report their observations, as well as have their computers download video for analysis by computer vision techniques. This provides a robust way to analyze the video, as user observations are validated by multiple views as well as the results of the computer vision techniques. This work provides initial results analyzing the effectiveness of the crowd sourced observations and computer vision techniques.

Cameras Identify White-tailed Deer Depredating Northern Bobwhite Nests

Abstract Odocoileus virginianus (White-tailed Deer) were videotaped depredating two Colinus virginianus (Northern Bobwhite) nests during a nest-predator study in south Georgia in 2002 and 2003. Deer ate eggs from the nests, leading to the failure of one of the two nests.

A Comparison of Background Subtraction Algorithms for Detecting Avian Nesting Events in Uncontrolled Outdoor Video

This paper examines the use of three different background subtraction algorithms -- Mixture of Gaussians (MOG), Visual Background Extractor (ViBe), and Pixel-Based Adaptive Segmentation (PBAS) -- to detect events of interest within uncontrolled outdoor avian nesting video for the Wildlife@Home project. Many computer vision techniques are unsuccessful in this domain due to low frame-rates and resolution of battery powered surveillance cameras in combination with the cryptic coloration (camouflage) of the animals. Modifications to ViBe and PBAS are presented which provide more robust results in this challenging video, and address issues caused by the cryptic coloration of the species being monitored by the project. These algorithms were run on over 250 hours of video and compared to human observations generated by Wildlife@Homes project scientists and volunteer citizen scientists. All three algorithms provide accurate detection of events however we see much fewer false postives from the modified versions of the ViBe and PBAS algorithms. This is especially true for Interior Least Tern (Sternula antillarum) and Piping Plover (Charadrius melodus) video, which do not suffer from as much moving vegetation as the Sharp-Tailed Grouse (Tympanuchus phasianellus) footage. These results provide initial justification for utilizing Wildlife@Homes 2,000+ volunteered computers to analyze the projects 85,000 hours of avian nesting video, so that this information can be integrated into the Wildlife@Home user interface. Further, the videos and human observations used to test these algorithms have been made available as part of Wildlife@Homes first data release, to encourage future study by computer vision researchers.

Developing a citizen science web portal for manual and automated ecological image detection

Image recognition is challenging in the field of wildlife ecology as samples of a specific species can be rare, making manual detection cumbersome. With over 2,060,000 images taken from motion-sensor trail cameras and unmanned aerial vehicle flights, a touch enabled web interface has been developed to allow citizen scientists and ecologists to categorize positive samples. To minimize categorization errors, the same images are shown to multiple separate users. The observations of each user are then compared using two novel validation strategies: percentage of overlapping area and maximum corner distance. Two novel methods for the extraction of final images from validated results are presented and compared as well: average corner points and area intersection. These methods were evaluated using a set of 142 images with a total of 811 observations of objects generated by citizen scientists that were manually inspected for ground truth. Results show that for this research a maximum corner distance of 10 pixels and the use of area intersection provided the best extracted imagery for future use as training and testing data by computer vision methods.

Toward Using Citizen Scientists to Drive Automated Ecological Object Detection in Aerial Imagery

Automated object detection within imagery is challenging in the field of wildlife biology. Uncontrolled conditions, along with the relative size of target species to the more abundant background makes manual detection tedious and error-prone. In order to address these concerns, the Wildlife@Home project has been developed with a web portal to allow citizen scientists to inspect and catalog these images, which in turn provides training data for computer vision algorithms to automate the detection process. This work focuses on a project with over 65,000 Unmanned Aerial System (UAS) images from flights in the Hudson Bay area of Canada gathered in the years 2015 and 2016. This data set comprises over 3TB of raw imagery and also contains a further 2 million images from related ecological projects. Given the data scale, the person-hours that would be needed to manually inspect the data is extremely high. This work examines the efficacy of using citizen science data as inputs to convolutional neural networks (CNNs) used for object detection. Three CNNs were trained with expert observations, citizen scientist observations, and matched observations made by pairing citizen scientist observations of the same object and taking the intersection of the two observations. The expert, matched, and unmatched CNNs overestimated the number of lesser snow geese in the testing images by 88%, 150%, and 250%, respectively, which is less than current work using similar techniques on all visible (RGB) UAS imagery. These results show that the accuracy of the input data is more important than the quantity of the input data, as the unmatched citizen scientists observations are shown to be highly variable, but substantial in number, while the matched observations are much closer to the expert observations, though less in number. To increase the accuracy of the CNNs, it is proposed to use a feedback loop to ensure the CNN gets continually trained using extracted observations that it did poorly on during the testing phase.

Pedagogy and practice in STEM field experiences: intersections of student and mentor identity and impacts upon student outcomes

ABSTRACT Practicums, internships and field experiences are essential components in many fields. These varied experiences embed both students and their mentors in immersive experiences. Such immersive experiences are essential for STEM students preparing for future jobs, yet little is known about how these research-intensive and immersive experiences impact the practice of teaching in the natural sciences. In order to evaluate the impact, opportunities and challenges associated with such experiences, our team collected and analysed end-of-semester reflections from five students and their faculty mentor. Thematic analysis related to inferences and implications about the impacts of the experience showed a need to formalize and further develop an understanding of both students’ self-identity and the cultural attitudes of the students and the mentor.

Evaluating behavioral responses of nesting lesser snow geese to unmanned aircraft surveys

Abstract Unmanned aircraft systems (UAS) are relatively new technologies gaining popularity among wildlife biologists. As with any new tool in wildlife science, operating protocols must be developed through rigorous protocol testing. Few studies have been conducted that quantify the impacts UAS may have on unhabituated individuals in the wild using standard aerial survey protocols. We evaluated impacts of unmanned surveys by measuring UAS‐induced behavioral responses during the nesting phase of lesser snow geese (Anser caerulescens caerulescens) in Wapusk National Park, Manitoba, Canada. We conducted surveys with a fixed‐wing Trimble UX5 and monitored behavioral changes via discreet surveillance cameras at 25 nests. Days with UAS surveys resulted in decreased resting and increased nest maintenance, low scanning, high scanning, head‐cocking and off‐nest behaviors when compared to days without UAS surveys. In the group of birds flown over, head‐cocking for overhead vigilance was rarely seen prior to launch or after landing (mean estimates 0.03% and 0.02%, respectively) but increased to 0.56% of the time when the aircraft was flying overhead suggesting that birds were able to detect the aircraft during flight. Neither UAS survey altitude nor launch distance alone in this study was strong predictors of nesting behaviors, although our flight altitudes (≥75 m above ground level) were much higher than previously published behavioral studies. Synthesis and applications: The diversity of UAS models makes generalizations on behavioral impacts difficult, and we caution that researchers should design UAS studies with knowledge that some minimal disturbance is likely to occur. We recommend flight designs take potential behavioral impacts into account by increasing survey altitude where data quality requirements permit. Such flight designs should consider a priori knowledge of focal species’ behavioral characteristics. Research is needed to determine whether any such disturbance is a result of visual or auditory stimuli.

Difference in exposure of water birds to covered and uncovered float muskrat sets

Muskrats Ondatra zibethicus are a popular furbearer species across much of North America. Float sets have gained popularity due to the ease of use and effectiveness of capturing muskrats. Little to no research has been conducted on muskrat float sets, especially on the impacts the float sets have on non-target animals. In North Dakota, USA, regulations allowed trappers to use float sets during the spring season, but float sets were required to have a covering made of wire mesh, wood or plastic and no opening larger than 20.32 cm (8 inches) in an effort to minimize the incidental take of non-target species. We aimed to determine if there was any non-target capture injury or mortality risk on float muskrat sets. We conducted a study to compare rates of incidental take in covered (2.54×2.54 cm and 15.24×15.24 cm wire mesh) and uncovered float sets. We trapped muskrats in fall (1191 trap nights) and spring (3054 trap nights) from 2012–2014 at four study areas in North Dakota. Over four trapping periods (two fall and two spring seasons), 490 muskrats and seven non-target species were captured. Non-target species included three black-crowned night heron Nycticorax nycticorax, two blue-winged teal Anas discors and two painted turtles Chrysemys picta. All avian non-target species were captured on uncovered floats. Camera trap data showed that ducks were 10.1 times less likely to be on floats than other types of water birds (e.g. herons). Covers did not negatively influence muskrat captures, but smaller mesh sizes appeared to deter birds from climbing on top of floats. All but one avian non-target capture occurred after 1 May (closing of North Dakotas spring muskrat trapping season) each year, suggesting that season dates may be an important factor to consider in attempts to reduce incidental take of protected bird species.