Unmanned Aerial Vehicles (UAVs) and artificial intelligence revolutionizing wildlife monitoring and conservation

Surveying threatened and invasive species to obtain accurate population estimates is an important but challenging task that requires a considerable investment in time and resources. Estimates using existing ground-based monitoring techniques, such as camera traps and surveys performed on foot, are known to be resource intensive, potentially inaccurate and imprecise, and difficult to validate. Recent developments in unmanned aerial vehicles (UAV), artificial intelligence and miniaturized thermal imaging systems represent a new opportunity for wildlife experts to inexpensively survey relatively large areas. The system presented in this paper includes thermal image acquisition as well as a video processing pipeline to perform object detection, classification and tracking of wildlife in forest or open areas. The system is tested on thermal video data from ground based and test flight footage, and is found to be able to detect all the target wildlife located in the surveyed area. The system is flexible in that the user can readily define the types of objects to classify and the object characteristics that should be considered during classification.

Carmel River Lagoon Enhancement Project: Water Quality and Aquatic Wildlife Monitoring, 2006-7

This is a report to the California Department of Parks and Recreation. It describes water quality and aquatic invertebrate monitoring after the construction of the Carmel River Lagoon Enhancement Project. Included are data that have been collected for two years and preliminary assessment of the enhanced ecosystem. This report marks the completion of 3-years of monitoring water quality and aquatic habitat. The report adopts the same format and certain background text from previous years’ reporting by the same research group (e.g. Larson et al., 2005). (Document contains 100 pages)

Carmel River Lagoon Enhancement Project: Water Quality and Aquatic Wildlife Monitoring, 2005-6

In summer and fall 2004, the California Department of Parks and Recreation (DPR) initiated the Carmel River Lagoon Enhancement Project. The project involved excavation of a dry remnant Arm of the lagoon and adjacent disused farmland to form a significant new lagoon volume. The intention was to provide habitat, in particular, for two Federally threatened species: the California Red-Legged Frog, and the Steelhead Trout (South Central-Coastal California Evolutionary Significant Unit). DPR contracted with the Foundation of California State University Monterey Bay (Central Coast Watershed Studies Team, Watershed Institute) to monitor water quality and aquatic invertebrates in association with the enhancement, and to attempt to monitor steelhead using novel video techniques. The monitoring objective was to assess whether the enhancement was successful in providing habitat with good water quality, adequate invertebrate food for steelhead, and ultimately the presence of steelhead. (Document contains 102 pages)

Improving the efficiency of wildlife monitoring by estimating detectability: a case study of foxes (Vulpes vulpes) on the Eyre Peninsula, South Australia

Demonstrating the existence of trends in monitoring data is of increasing practical importance to conservation managers wishing to preserve threatened species or reduce the impact of pest species. However, the ability to do so can be compromised if the species in question has low detectability and the true occupancy level or abundance of the species is thus obscured. Zero-inflated models that explicitly model detectability improve the ability to make sound ecological inference in such situations. In this paper we apply an occupancy model including detectability to data from the initial stages of a fox-monitoring program on the Eyre Peninsula, South Australia. We find that detectability is extremely low (< 18%) and varies according to season and the presence or absence of roadside vegetation. We show that simple methods of using monitoring data to inform management, such as plotting the raw data or performing logistic regression, fail to accurately diagnose either the status of the fox population or its trajectory over time. We use the results of the detectability model to consider how future monitoring could be redesigned to achieve efficiency gains. A wide range of monitoring programs could benefit from similar analyses, as part of an active adaptive approach to improving monitoring and management.

Using wildlife activity and antibiotic resistance analysis to model bacterial water quality in coastal ponds

Models that help predict fecal coliform bacteria (FCB) levels in environmental waters can be important tools for resource managers. In this study, we used animal activity along with antibiotic resistance analysis (ARA), land cover, and other variables to build models that predict bacteria levels in coastal ponds that discharge into an estuary. Photographic wildlife monitoring was used to estimate terrestrial and aquatic wildlife activity prior to sampling. Increased duck activity was an important predictor of increased FCB in coastal ponds. Terrestrial animals like deer and raccoon, although abundant, were not significant in our model. Various land cover types, rainfall, tide, solar irradiation, air temperature, and season parameters, in combination with duck activity, were significant predictors of increased FCB. It appears that tidal ponds allow for settling of bacteria under most conditions. We propose that these models can be used to test different development styles and wildlife management techniques to reduce bacterial loading into downstream shellfish harvesting and contact recreation areas.

Advances in camera trap data management tools: Towards collaborative development and integration with GIS

Camera traps have become a widely used technique for conducting biological inventories, generating a large number of database records of great interest. The main aim of this paper is to describe a new free and open source software (FOSS), developed to facilitate the management of camera-trapped data which originated from a protected Mediterranean area (SE Spain). In the last decade, some other useful alternatives have been proposed, but ours focuses especially on a collaborative undertaking and on the importance of spatial information underpinning common camera trap studies. This FOSS application, namely, “Camera Trap Manager” (CTM), has been designed to expedite the processing of pictures on the .NET platform. CTM has a very intuitive user interface, automatic extraction of some image metadata (date, time, moon phase, location, temperature, atmospheric pressure, among others), analytical (Geographical Information Systems, statistics, charts, among others), and reporting capabilities (ESRI Shapefiles, Microsoft Excel Spreadsheets, PDF reports, among others). Using this application, we have achieved a very simple management, fast analysis, and a significant reduction of costs. While we were able to classify an average of 55 pictures per hour manually, CTM has made it possible to process over 1000 photographs per hour, consequently retrieving a greater amount of data.

Sewage disposal and wildlife health in Antarctica

Sewage and its microbiology, treatment and disposal are important to the topic of Antarctic wildlife health because disposal of untreated sewage effluent into the Antarctic marine environment is both allowed and commonplace. Human sewage contains enteric bacteria as normal flora, and has the potential to contain parasites, bacteria and viruses which may prove pathogenic to Antarctic wildlife. Treatment can reduce levels of micro-organisms in sewage effluent, but is not a requirement of the Environmental Protocol to the Antarctic Treaty (the Madrid Protocol). In contrast, the deliberate release of non-native organisms for any other reason is prohibited. Hence, disposal of sewage effluent to the marine environment is the only activity routinely undertaken in Antarctica knowing that it will likely result in the release of large numbers of potentially non-native species. When the Madrid Protocol was negotiated, the decision to allow release of untreated sewage effluent was considered the only pragmatic option, as a prohibition would have been costly, and may not have been achievable by many Antarctic operators. In addition, at that time the potential for transmission of pathogens to wildlife from sewage was not emphasised as a significant potential risk. Since then, the transmission of disease-causing agents between species is more widely recognised and it is now timely to consider the risks of continued discharge of sewage effluent in Antarctica and whether there are practical alternatives.

Aerial image analysis using spiking neural networks with application to power line corridor monitoring

Trees, shrubs and other vegetation are of continued importance to the environment and our daily life. They provide shade around our roads and houses, offer a habitat for birds and wildlife, and absorb air pollutants. However, vegetation touching power lines is a risk to public safety and the environment, and one of the main causes of power supply problems. Vegetation management, which includes tree trimming and vegetation control, is a significant cost component of the maintenance of electrical infrastructure. For example, Ergon Energy, the Australia’s largest geographic footprint energy distributor, currently spends over $80 million a year inspecting and managing vegetation that encroach on power line assets. Currently, most vegetation management programs for distribution systems are calendar-based ground patrol. However, calendar-based inspection by linesman is labour-intensive, time consuming and expensive. It also results in some zones being trimmed more frequently than needed and others not cut often enough. Moreover, it’s seldom practicable to measure all the plants around power line corridors by field methods. Remote sensing data captured from airborne sensors has great potential in assisting vegetation management in power line corridors. This thesis presented a comprehensive study on using spiking neural networks in a specific image analysis application: power line corridor monitoring. Theoretically, the thesis focuses on a biologically inspired spiking cortical model: pulse coupled neural network (PCNN). The original PCNN model was simplified in order to better analyze the pulse dynamics and control the performance. Some new and effective algorithms were developed based on the proposed spiking cortical model for object detection, image segmentation and invariant feature extraction. The developed algorithms were evaluated in a number of experiments using real image data collected from our flight trails. The experimental results demonstrated the effectiveness and advantages of spiking neural networks in image processing tasks. Operationally, the knowledge gained from this research project offers a good reference to our industry partner (i.e. Ergon Energy) and other energy utilities who wants to improve their vegetation management activities. The novel approaches described in this thesis showed the potential of using the cutting edge sensor technologies and intelligent computing techniques in improve power line corridor monitoring. The lessons learnt from this project are also expected to increase the confidence of energy companies to move from traditional vegetation management strategy to a more automated, accurate and cost-effective solution using aerial remote sensing techniques.

Gold nanospikes based microsensor as a highly accurate mercury emission monitoring system

Anthropogenic elemental mercury (Hg0) emission is a serious worldwide environmental problem due to the extreme toxicity of the heavy metal to humans, plants and wildlife. Development of an accurate and cheap microsensor based online monitoring system which can be integrated as part of Hg0 removal and control processes in industry is still a major challenge. Here, we demonstrate that forming Au nanospike structures directly onto the electrodes of a quartz crystal microbalance (QCM) using a novel electrochemical route results in a self-regenerating, highly robust, stable, sensitive and selective Hg0 vapor sensor. The data from a 127 day continuous test performed in the presence of volatile organic compounds and high humidity levels, showed that the sensor with an electrodeposted sensitive layer had 260% higher response magnitude, 3.4 times lower detection limit (,22 mg/m3 or ,2.46 ppbv) and higher accuracy (98% Vs 35%) over a Au control based QCM (unmodified) when exposed to a Hg0 vapor concentration of 10.55 mg/m3 at 1016C. Statistical analysis of the long term data showed that the nano-engineered Hg0 sorption sites on the developed Au nanospikes sensitive layer play a critical role in the enhanced sensitivity and selectivity of the developed sensor towards Hg0 vapor.

Automating marine mammal detection in aerial images captured during wildlife surveys: A deep learning approach

Aerial surveys conducted using manned or unmanned aircraft with customized camera payloads can generate a large number of images. Manual review of these images to extract data is prohibitive in terms of time and financial resources, thus providing strong incentive to automate this process using computer vision systems. There are potential applications for these automated systems in areas such as surveillance and monitoring, precision agriculture, law enforcement, asset inspection, and wildlife assessment. In this paper, we present an efficient machine learning system for automating the detection of marine species in aerial imagery. The effectiveness of our approach can be credited to the combination of a well-suited region proposal method and the use of Deep Convolutional Neural Networks (DCNNs). In comparison to previous algorithms designed for the same purpose, we have been able to dramatically improve recall to more than 80% and improve precision to 27% by using DCNNs as the core approach.

Monitoring wild pig populations: a review of methods

Wild pigs (Sus scrofa) are widespread across many landscapes throughout the world and are considered to be an invasive pest to agriculture and the environment, or conversely a native or desired game species and resource for hunting. Wild pig population monitoring is often required for a variety of management or research objectives, and many methods and analyses for monitoring abundance are available. Here, we describe monitoring methods that have proven or potential applications to wild pig management. We describe the advantages and disadvantages of methods so that potential users can efficiently consider and identify the option(s) best suited to their combination of objectives, circumstances, and resources. This paper offers guidance to wildlife managers, researchers, and stakeholders considering population monitoring of wild pigs and will help ensure that they can fulfill their monitoring objectives while optimizing their use of resources.

Autonomous UAVs wildlife detection using thermal imaging, predictive navigation and computer vision

There is an increased interest on the use of Unmanned Aerial Vehicles (UAVs) for wildlife and feral animal monitoring around the world. This paper describes a novel system which uses a predictive dynamic application that places the UAV ahead of a user, with a low cost thermal camera, a small onboard computer that identifies heat signatures of a target animal from a predetermined altitude and transmits that target’s GPS coordinates. A map is generated and various data sets and graphs are displayed using a GUI designed for easy use. The paper describes the hardware and software architecture and the probabilistic model for downward facing camera for the detection of an animal. Behavioral dynamics of target movement for the design of a Kalman filter and Markov model based prediction algorithm are used to place the UAV ahead of the user. Geometrical concepts and Haversine formula are applied to the maximum likelihood case in order to make a prediction regarding a future state of the user, thus delivering a new way point for autonomous navigation. Results show that the system is capable of autonomously locating animals from a predetermined height and generate a map showing the location of the animals ahead of the user.

Vegetation structure and floristic composition of a tropical dry deciduous forest in Bhadra Wildlife Sanctuary, Karnataka, India

A permanent 2 ha (200 m x 100 m) plot was established for long-term monitoring of plant diversity and dynamics in a tropical dry deciduous forest of Bhadra Wildlife Sanctuary, Karnataka, southern India. Enumeration of all woody plants >= 1 cm DBH (diameter at breast height) yielded a total of 1766 individuals that belonged to 46 species, 37 genera and 24 families. Combretaceae was the most abundant family in the forest with a family importance value of 68.3. Plant density varied from 20 - 90 individuals with an average 35 individuals/quadrat (20 m x 20 m). Randia dumetorum, with 466 individuals (representing 26.7 % of the total density 2 ha(-1)) with species importance value of 36.25, was the dominant species in the plot. The total basal area of the plot was 18.09 m(2) ha(-1) with a mean of 0.72 m(2) quadrat(-1). The highest basal area of the plot was contributed by Combretaceae (12.93 m(2) 2 ha(-1)) at family level and Terminalia tomentosa (5.58 m(2) 2 ha(-1)) at species level. The lowest diameter class (1-10 cm) had the highest density (1054 individuals 2 ha(-1)), but basal area was highest in the 80 - 90 cm diameter class (5.03m(2) 2 ha(-1)). Most of the species exhibited random or aggregated distribution over the plot. This study provides a baseline information on the dry forests of Bhadra Wildlife Sanctuary.

Use of aerial survey and aerophotogrammetry methods in monitoring manatee populations

We evaluated the use of strip-transect survey methods for manatees through a series of replicate aerial surveys in the Banana River, Brevard County, Florida, during summer 1993 and summer 1994. Transect methods sample a representative portion of the total study area, thus allowing for statistical extrapolation to the total area. Other advantages of transect methods are less flight time and less cost than total coverage, ease of navigation, and reduced likelihood of double-counting. Our objectives were: (1) to identify visibility biases associated with the transect survey method and to adjust the counts accordingly; (2) to derive a population estimate with known variance for the Banana River during summer; and (3) to evaluate the potential value of this survey method for monitoring trends in manatee population size over time. (51 page document)

Channel Islands marine protected areas first 5 years of monitoring: 2003-2008 [Report produced by the California Department of Fish and Game in collaboration with the Partnership for Interdisciplinary Studies of Coastal Oceans (PISCO), Channel Islands National Marine Sanctuary, and Channel Islands National Park]

The Channel Islands—sometimes called the Galapagos of North America—are known for their great beauty, rich biodiversity, cultural heritage, and recreational opportunities. In 1980, in recognition of the islands’ importance, the United States Congress established a national park encompassing 5 of California’s Channel Islands (Santa Barbara, Anacapa, Santa Cruz, Santa Rosa, and San Miguel Islands) and waters within 1 nautical mile of the islands. In the same year, Congress declared a national marine sanctuary around each of these islands, including waters up to 6 nautical miles offshore. Approximately 60,000 people visit the Channel Islands each year for aquatic recreation such as fishing, sailing, kayaking, wildlife watching, surfing, and diving. Another 30,000 people visit the islands for hiking, camping, and sightseeing. Dozens of commercial fishing boats based in Santa Barbara, Ventura, Oxnard, and other ports go to the Channel Islands to catch squid, spiny lobster, sea urchin, rockfish, crab, sheephead, flatfish, and sea cucumber, among other species. In the past few decades, advances in fishing technology and the rising number of fishermen, in conjunction with changing ocean conditions and diseases, have contributed to declines in some marine fishes and invertebrates at the Channel Islands. In 1998, citizens from Santa Barbara and Ventura proposed establishment of no-take marine reserves at the Channel Islands, beginning a 4-year process of public meetings, discussions, and scientific analyses. In 2003, the California Fish and Game Commission designated a network of marine protected areas (MPAs) in state waters around the northern Channel Islands. In 2006 and 2007, the National Oceanic and Atmospheric Administration (NOAA) extended the MPAs into the national marine sanctuary’s deeper, federal waters. To determine if the MPAs are protecting marine species and habitats, scientists are monitoring ecological changes. They are studying changes in habitats; abundance and size of species of interest; the ocean food web and ecosystem; and movement of fish and invertebrates from MPAs to surrounding waters. Additionally, scientists are monitoring human activities such as commercial and recreational fisheries, and compliance with MPA regulations. This booklet describes some results from the first 5 years of monitoring the Channel Islands MPAs. Although 5 years is not long enough to determine if the MPAs will accomplish all of their goals, this booklet offers a glimpse of the changes that are beginning to take place and illustrates the types of information that will eventually be used to assess the MPAs’ effectiveness. (PDF contains 24 pages.)