It is important for the ecological management of wildlife populations in the Czech Republic to know the composition of species in individual habitats. This will allow predictions on the reactions of wildlife based on evolving changes that will occur sooner or later in these habitats due to human activity and natural change of our environment. Camera traps are a powerful tool of the 21st century with which we are able to observe wildlife without major interventions in their lives. With the right experimental design, camera traps allow us to find out details about wildlife life such as their distribution and habitat preferences, population structure, and their behavior. In this work, I used camera traps to determine the species composition of two groups; ungulates and carnivores in different habitats. This thesis analyzes the habitat preferences and hepls to find out to what extent the spatial patterns of occurrence on these two groups are in the monitored habitats over the course of a couple years. Data collection took place from June 2015 to May 2017 in the Central Bohemian Region northeast of Prague. Despite the fact that the area is densely populated and agriculturally exploited, I was able to capture four species of ungulates and nine species of carnivores on a total of 73 camera traps in this...

This study examined two different aspects of black bear (Ursus americanus) ecology in Utah. First, we determined the post-denning behaviors of female black bears in order to help management agencies protect bears from human disturbances as well as set spring hunts that minimize the taking of females with dependent young. We looked at the timing of den emergence (X = 25 March), the number of days at the den site post emergence (X = 11 days), and departure (X = 8 April) for female black bears in Utah from 2011—2013. We also analyzed the effects of cohort (lone female, female with cubs, and female with yearlings), region of Utah, year, elevation, and weather on emergence, departure, and total number of days at den. Lastly, we describe behaviors observed at the den site. We found that first emergence was significantly correlated with cohort and spring temperature. Departure date was significantly correlated with geographic region, spring temperature during emergence and departure, and temperature the spring and summer before denning. Total number of days at den was significantly correlated with cohort and last frost date from the year before. Bears spent little of the post-denning period outside of the dens (X = 9.8% of total observation time). When outside of dens, bears were often observed walking, lying down, sitting and standing. We also observed unique behaviors, including gathering nest materials, nursing, and ingesting. Dens were frequently visited by other wildlife as well. Second, we analyzed conflict between humans and black bears in Utah. The Utah Division of Wildlife Resources initiated a black bear sightings and encounters database in 2003. We upgraded this database by gathering available records and organizing them into a new database for analysis using Microsoft Access®. From 2003—2013 there were 943 records, with 499 bear-human encounters, 33 incidents, 10 attacks, 208 property damages, 187 sightings, and 6 vehicle collisions. Utah county had the highest number of events (n = 115). The majority of events took place at campsites (n = 363). Summer was the most common season for events (n = 715). Time of day was frequently not reported, but when it was, most events occurred at night (n = 173). We found no significant increase in the number of events over the last ten years. We also found no significant relationship between the number of events per year and drought data. The highest number of events involved single bears (n = 843), and over half of events had food or garbage available for the bear (n = 475).

La fragmentation des paysages et des habitats induite par les infrastructures linéaires de transport terrestres est une des principales causes de la perte de biodiversité actuelle. Parmi ces infrastructures, la route est un acteur majeur de fragmentation, d’autant plus qu’elle possède des effets propres dus au trafic circulant qui induit des collisions véhicule-faune et une pollution des paysages. Afin de diminuer ces effets négatifs, des mesures de réduction sont mises en place, notamment des passages à faune permettant de faire traverser la faune de part et d’autre des voies. La route crée aussi de nouveaux habitats potentiels pour les espèces de la petite faune dans des paysages anthropisés et fragmentés. Dans ce mémoire sont démontrées (1) la potentialité d’habitat de différents éléments routiers ; (2) la possibilité de prédire les collisions véhicule-faune afin de positionner au mieux les mesures de réduction ; (3) l’importance de la méthodologie dans l’évaluation de l’efficacité des passages à faune ; et (4) la possibilité d’améliorer les passages à faune existants. Ces résultats permettront d’améliorer les stratégies de défragmentation des paysages. / Habitats and landscape fragmentation, caused by linear land transports infrastructures, is one of the major cause for the current loss of biodiversity. Among those infrastructures, road is a major cause of fragmentation, especially as it possess specific traffic-linked effects, which induces wildlife-vehicles collisions and landscape pollution. In order to decrease those negative effects, mitigation measures are taken, among which wildlife crossings, enabling wildlife to cross the road. Road also creates new potential habitats for small wildlife species in anthropogenic and fragmented landscapes. In this essay are shown (1) the potential as habitat of different road-linked elements; (2) the possibility to anticipate wildlife-vehicles collisions in order to improve the position of mitigation measures; (3) the importance of methodology in the evaluation of wildlife crossings effectiveness; and (4) the possibility to improve existing wildlife crossings. Those results will allow improving landscape defragmentation strategies.

Monitoring wildlife is of great interest to ecologists and is arguably even more important in the Arctic, the region in focus for the research network INTERACT, where the effects of climate change are greater than on the rest of the planet. This master thesis studies how artificial intelligence (AI) and computer vision can be used together with camera traps to achieve an effective way to monitor populations. The study uses an image data set, containing both humans and animals. The images were taken by camera traps from ECN Cairngorms, a station in the INTERACT network. The goal of the project is to classify these images into one of three categories: "Empty", "Animal" and "Human". Three different methods are compared, a DenseNet201 classifier, a YOLOv3 object detector, and the pre-trained MegaDetector, developed by Microsoft. No sufficient results were achieved with the classifier, but YOLOv3 performed well on human detection, with an average precision (AP) of 0.8 on both training and validation data. The animal detections for YOLOv3 did not reach an as high AP and this was likely because of the smaller amount of training examples. The best results were achieved by MegaDetector in combination with an added method to determine if the detected animals were dogs, reaching an average precision of 0.85 for animals and 0.99 for humans. This is the method that is recommended for future use, but there is potential to improve all the models and reach even more impressive results.Teknisk-naturvetenskapliga

<p>  </p> <p>Free-roaming dogs on Native American Reservations are called rez dogs on the Pine Ridge Indian Reservation, SD. Understanding the human-rez dog relationship is needed to develop best management practices. As a member of the Oglala Lakota nation and a resident of the Pine Ridge Indian Reservation, I used a combination of western scientific methods and Lakota ways of knowing to research how rez dogs are related to their human caretakers on the Pine Ridge Reservation. First, I determined how they are related to humans spatially. To do this, I installed trail cameras at 73 sites distributed within four zones around six communities on the Pine Ridge Reservation. I analyzed presence-absence and count data to estimate how human habitat covariates influenced rez dog occurrence and abundance. My results show that rez dog occupancy and abundance is related to human habitation and emphasizes the importance of considering human caretakers when developing best management practices. To investigate how human caretakers may perceive rez dogs and current management practices on the Pine Ridge Reservation, I used semi-structured questionnaires. I distributed surveys to 107 residents at grocery stores and convenience stores within five towns. The survey assessed the communities' perceptions of rez dog overpopulation, and topics related to their attitude toward dogs overall and rez dog sterilization programs. I used ordinal regression to determine if community member demographics, the number of people and dogs in the household, and distance to the veterinary clinic influenced these variables. My results show community members support rez dog sterilization programs and that policymakers should focus on free or low-cost sterilization programs for ambiguously owned rez dogs in conjunction with owned dogs. In addition, these results highlight how the economic disparity and lack of culturally appropriate methods of rez-dog population control prevent effective management of rez dogs. This dynamic is one example of how the settler-colonialism structure continues to negatively impact Native American communities and prevent effective, efficient, and ethical ways to manage rez dogs. I describe how the Lakota ways of knowing can be used to develop best management practices for rez dogs that are culturally appropriate. I describe the seven Lakota values, lessons learned from the Lakota dog creation story, and approaches to Lakota research methodologies. This paper introduces an example of a seven-generation, One Health framework that implements Lakota ways of knowing to establish rez dog management and centers community values, beginning generational healing through <em>Shunka </em>(dog) caretaking. In conclusion, this research describes how rez dogs are related to us spatially, by occupying the same area as us, and how we are related within a social context, with dogs being an indicator of our own well-being as humans. </p>

No description available.

A rapid global decline in biodiversity has been observed in the past few decades, especially in large vertebrates and the habitats supporting these animal populations. This widely accepted fact has made it very important to understand how animals respond to modern ecological threats and to understand the ecosystems functions. The motion activated camera (also known as a camera trap) is a common tool for research in this field, being well-suited for non-invasive observation of wildlife. The images captured by camera traps in biological studies need to be classified to extract information, a traditionally manual process that is time intensive. Recent studies have shown that the use of machine learning (ML) can automate this process while maintaining high accuracy. Until recently the use of machine learning has required significant computing power, relying on data being processed after collection or transmitted to the cloud. This need for connectivity introduces potentially unsustainable overheads that can be addressed by placing computational resources on the camera trap and processing data locally, known as edge computing. Including more computational power in edge and IoT devices makes it possible to keep the computation and data storage on the edge, commonly referred to as edge computing. Applying edge computing to the camera traps enables the use of ML in environments with slow or non-existent network accesss since their functionality does not rely on the need for connectivity. This project shows the feasibility of running machine learning algorithms for the purpose of species identification on low-cost hardware with similar power to what is commonly found in edge and IoT devices, achieving real-time performance and maintaining high energy efficiency sufficient for more than 12 hours of runtime on battery power. Accuracy results were mixed, indicating the need for more tailor-made network models for performing this task and the importance of high quality images for classification.

This master’s thesis investigates the application of advanced machine learning models for the identification and classification of Swedish predators using camera trap images. With the growing threats to biodiversity, there is an urgent need for innovative and non-intrusive monitoring techniques. This study focuses on the development and evaluation of object detection models, including YOLOv5, YOLOv8, YOLOv9, and Faster R-CNN, aiming to enhance the surveillance capabilities of Swedish predatory species such as bears, wolves, lynxes, foxes, and wolverines. The research leverages a dataset from the NINA database, applying data preprocessing and augmentation techniques to ensure robust model training. The models were trained and evaluated using various dataset sizes and conditions, including day and night images. Notably, YOLOv8 and YOLOv9 underwent extended training for 300 epochs, leading to significant improvements in performance metrics. The performance of the models was evaluated using metrics such as mean Average Precision (mAP), precision, recall, and F1-score. YOLOv9, with its innovative Programmable Gradient Information (PGI) and GELAN architecture, demonstrated superior accuracy and reliability, achieving an F1-score of 0.98 on the expanded dataset. The research found that training models on images captured during both day and night jointly versus separately resulted in only minor differences in performance. However, models trained exclusively on daytime images showed slightly better performance due to more consistent and favorable lighting conditions. The study also revealed a positive correlation between the size of the training dataset and model performance, with larger datasets yielding better results across all metrics. However, the marginal gains decreased as the dataset size increased, suggesting diminishing returns. Among the species studied, foxes were the least challenging for the models to detect and identify, while wolves presented more significant challenges, likely due to their complex fur patterns and coloration blending with the background.