Master of Science, The Ohio State University, 2024, Computer Science and Engineering

Motion-activated cameras, commonly known as camera traps, play a crucial role in wildlife monitoring, biodiversity conservation, and basic ecological science, capturing a diverse range of species in their natural habitats. However, the sheer volume of images generated requires manual analysis by ecologists, making this a time-consuming and inefficient process. This is particularly frustrating since many of the images do not contain animals because camera traps are triggered by the motion of vegetation due to wind or miss the animal due to the slow camera response. This thesis presents an approach aimed at addressing these challenges through the automation of image classification and the development of smart camera traps that leverage artificial intelligence implementations in edge devices. First, we develop a species classifier pipeline consisting of object detection and a species classifier for a novel camera trap setting. We train a convolutional neural network to identify 45 trained species using 1.2M images, achieving an accuracy of around 89\% at the class level without manual intervention. This research demonstrates the combination of deep learning methodologies and human oversight, showcasing their ability to facilitate automatic or semiautomatic, precise, and efficient surveys of small animals in the wild, particularly in novel settings or for novel species. The suggested pipeline helps achieve 95\% accuracy in image classification, resulting in 11\% of images that require manual review at the class level. This pipeline helps to automatically annotate the image while maintaining accuracy. The camera trap generates a large number of images. The time delay between data capture and image processing leads to the loss of critical information. Real-time labeling while capturing images can help mitigate this issue. Following the traditional classifier, we investigate methods for deploying an AI model in a camera trap. Smart Camera Traps would result in real (open full item for complete abstract)

Committee: Tanya Berger-Wolf (Advisor); Christopher Stewart (Committee Member); Wei-Lun Chao (Committee Member) Subjects: Computer Engineering

MS, University of Cincinnati, 2024, Engineering and Applied Science: Computer Science

Camera traps have become integral tools in wildlife conservation, providing non-intrusive means to monitor and study wildlife in their natural habitats. The utilization of object detection algorithms to automate species identification from Camera Trap images is of huge importance for research and conservation purposes. However, the generalization issue where the trained model is unable to apply its learnings to a never-before-seen dataset is prevalent. This thesis explores the enhancements made to the YOLOv8 object detection algorithm to address the problem of generalization. The study delves into the limitations of the baseline YOLOv8 model, emphasizing its struggles with generalization in real-world environments. To overcome these limitations, enhancements are proposed, including the incorporation of a Global Attention Mechanism (GAM) module, modified multi-scale feature fusion, and Wise Intersection over Union (WIoUv3) as a bounding box regression loss function. A thorough evaluation and ablation experiments reveal the improved model's ability to suppress the background noise, focus on object properties, and exhibit robust generalization in novel environments. The proposed enhancements not only address the challenges inherent in camera trap datasets but also pave the way for broader applicability in real-world conservation scenarios, ultimately aiding in the effective management of wildlife populations and habitats.

Committee: Yizong Cheng Ph.D. (Committee Chair); Jun Bai Ph.D. (Committee Member); FNU NITIN Ph.D. (Committee Member) Subjects: Computer Science

Master of Science, The Ohio State University, 2022, Environment and Natural Resources

Artificial light at night (ALAN) is a growing environmental stressor due to human expansion and increased urbanization. ALAN has shown to have significant impacts on a suite of taxa and on multiple levels of biological organization, but most research has focused on individual to population levels of biological organization. Furthermore, there has been a disproportionate research emphasis on terrestrial vs. aquatic ecosystems. In this study, I investigated the impacts of ALAN on riparian mammal space use and food webs along 12 small streams in Columbus, Ohio, USA. Seasonality and time of day were the strongest drivers of mammal community composition along streams, despite the presence of ALAN. Seasonality, sediment size, and other site-level differences, but not ALAN, were associated with total mammal space use and species richness. No species-specific small mammal captures or species/guild-specific camera-trap encounters were impacted by ALAN. In the context of this study, sediment size is likely a proxy for either stream size or urbanization but also a potentially important structural factor related to small-mammal movement across streams. ALAN presence was related to the proportion of energy derived from aquatic vs. terrestrial primary producer pathways in the genus Peromyscus, the only small mammals with sufficient sample size to estimate diet proportions. At illuminated reaches, Peromyscus nutritional subsidies derived from aquatic primary producer pathways (i.e., originating from stream periphyton) were 1.2% lower at lit compared to unlit reaches. Canopy cover was also associated with the proportion of energy derived from the terrestrial primary producer pathway that is indirectly consumed by Peromyscus (i.e., originating from aquatic detritus). Site – as a random effect in linear-mixed models – explained the greatest amount of variation in the proportion of energy derived from different primary producer pathways. Overall, I did not find e (open full item for complete abstract)

Committee: Mažeika Sullivan (Advisor); Robert Gates (Committee Member); Stanley Gehrt (Committee Member) Subjects: Ecology; Environmental Science; Natural Resource Management; Wildlife Conservation; Wildlife Management