Imaging Science MS Thesis Defense - Matthew Helvey

Application of Thermal and Ultraviolet Sensors in Remote Sensing of Upland Ducks

Matthew Helvey
Imaging Science MS Candidate
Chester F. Carlson Center for Imaging Science, RIT

Join Zoom Meeting

Abstract:
Detection, mapping, and monitoring of wildlife populations can provide significant insight into the health and trajectory of the ecosystems they rely on. The Prairie Pothole Region in North America is one such premier breeding location for ducks; responsible for producing more than 50% of the North American ducks. The current duck population survey methods are primarily done using manned flights, while the current industry standard for locating nests in situ is known as the “chain drag method” - both methods are manually intensive and costly. Our objectives for this study therefore were to assess the feasibility of utilizing sUAS based thermal longwave infrared (LWIR) imagery for detecting duck nests and ultraviolet (UV) imagery to classify breeding pairs in the prairie pothole region. Our team deployed a DRS Tamarisk 640 LWIR sensor aboard a DJI Matrice 600 hexa-copter at Ducks Unlimited’s Coteau Ranch in North Dakota to obtain the thermal imagery. At the ranch, 24 nests were imaged at two altitudes (40m and 80m) during the early morning (04h00-06h00), morning (06h00-08h00), and midday (11h00-13h00). Using a three-step detection algorithm, we determined that the variable with the highest impact on detection accuracies was altitude. We were able to achieve detection accuracies of 58% and 69% for the 80m and 40m flights, respectively. We determined that with a further increase in spatial resolution, the use of sUAS based thermal imagery is feasible for detecting nests across the prairie and that flights should occur early in the morning while the hens are on the nest, in order to maximize detection potential. To assess the feasibility of classifying breeding duck pairs using UV imagery, our team took a preliminary step in simulating UAS reflectance imagery by collecting scans of upland ducks with a fixed measurement geometry using an OceanOptics spectroradiometer. We established baseline accuracies of 83%, 83%, and 76% for classifying age, sex, and species, respectively, by using a random forest (RF) classifier with simulated panchromatic (250-850nm) image sets. When using imagery at narrow UV bands with the same RF classifier, we were able to increase classification accuracies for age and species by 7%. Therefore, we demonstrated the potential for the use of sUAS based imagery as an alternate method for surveying breeding duck pairs, as well as the potential improvements in age and species classification that the use of UV imagery might provide.

Intended Audience:
Undergraduates, graduates, and experts. Those with interest in the topic.