An official website of the United States government
Monitoring and analysis of wildlife are key to conservation planning and conflict management. The widespread use of camera traps coupled with AI-based analysis tools serves as an excellent example of successful and non-invasive use of technology for design, planning, and evaluation of conservation policies. As opposed to the typical use of camera traps that capture still images or short videos, in this project, we propose to analyze longer term videos monitoring a large flock of birds. This project, which is part of the NSF-TIH Indo-US joint R&D partnership, focuses on solving challenges associated with the analysis of long-term videos captured at feeding grounds and nesting sites, among other such locations that host large flocks of migratory birds. We foresee that the objectives of this project would lead to datasets and benchmarking tools as well as novel algorithms that would be instrumental in developing automated video analysis tools that could in turn help understand individual and social behavior of birds. The first of the key outcomes of this research will include the curation of challenging, real-world datasets for benchmarking various image and video analytics algorithms for tasks such as counting, detection, segmentation, and tracking. Our recent efforts towards this outcome is a curated dataset of 812 high-resolution, point-annotated, images (4K - 32MP) of a flock of Demoiselle cranes (Anthropoides virgo) taken from their feeding site at Khichan, Rajasthan, India. The average number of birds in each image is about 207, with a maximum count of 1500. The benchmark experiments show that state-of-the-art vision techniques struggle with tasks such as segmentation, detection, localization, and density estimation for the proposed dataset. Over the execution of this open science research, we will be scaling this dataset for segmentation and tracking in videos, as well as developing novel techniques for video analytics for wildlife monitoring.
more »
« less
BirdCollect: A Comprehensive Benchmark for Analyzing Dense Bird Flock Attributes
Automatic recognition of bird behavior from long-term, un controlled outdoor imagery can contribute to conservation efforts by enabling large-scale monitoring of bird populations. Current techniques in AI-based wildlife monitoring have focused on short-term tracking and monitoring birds individually rather than in species-rich flocks. We present Bird-Collect, a comprehensive benchmark dataset for monitoring dense bird flock attributes. It includes a unique collection of more than 6,000 high-resolution images of Demoiselle Cranes (Anthropoides virgo) feeding and nesting in the vicinity of Khichan region of Rajasthan. Particularly, each image contains an average of 190 individual birds, illustrating the complex dynamics of densely populated bird flocks on a scale that has not previously been studied. In addition, a total of 433 distinct pictures captured at Keoladeo National Park, Bharatpur provide a comprehensive representation of 34 distinct bird species belonging to various taxonomic groups. These images offer details into the diversity and the behaviour of birds in vital natural ecosystem along the migratory flyways. Additionally, we provide a set of 2,500 point-annotated samples which serve as ground truth for benchmarking various computer vision tasks like crowd counting, density estimation, segmentation, and species classification. The benchmark performance for these tasks highlight the need for tailored approaches for specific wildlife applications, which include varied conditions including views, illumination, and resolutions. With around 46.2 GBs in size encompassing data collected from two distinct nesting ground sets, it is the largest birds dataset containing detailed annotations, showcasing a substantial leap in bird research possibilities. We intend to publicly release the dataset to the research community. The database is available at: https://iab-rubric.org/resources/wildlife-dataset/birdcollect
more »
« less
- Award ID(s):
- 1956050
- PAR ID:
- 10545625
- Publisher / Repository:
- PKP Publishing Services Network
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 38
- Issue:
- 20
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 21879 to 21887
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Manipulation experiments are a cornerstone of ecological research, but can be logistically challenging to execute—particularly when they are intended to isolate the ecological role of large, vagile species, like birds. Despite indirect evidence that birds are influential in many ecosystems, large‐scale, multi‐year bird manipulation experiments are rare. When these studies are conducted, they are typically realized with caged or netted exclosures, an approach that can be expensive, risky for wildlife, and difficult to maintain. In cases where caged exclosures are not appropriate, alternate approaches are needed to allow rigorous empirical studies on the ecological role of birds. Here, we present and validate a method for experimentally increasing the abundance and richness of birds at the scale of entire aquatic ecosystems. Unlike bird exclusion, this approach is experimentally tractable, appealing to land managers, and possible to deploy over large spatial scales. We tested the efficacy of our approach for increasing bird abundance and species richness at 16 central California ponds. Based on bird visitation data obtained by summer camera trapping, our approach significantly increased bird species richness and abundance at manipulated ponds compared to control ponds. Attractant treatments mitigated the negative effects of a major drought on bird species richness and generated a near doubling of bird abundance in the presence of attractants. Treatments had no effect on most mammal species, with the exception of ground squirrels, which increased in abundance in the presence of attractants. These results suggest that attractants are effective in increasing bird abundance and richness. We encourage researchers to consider this approach for experimentally isolating the ecological role of birds in aquatic and open terrestrial ecosystems, especially in cases where cost or logistical constraints preclude the use of caged or netted exclosures.more » « less
-
Abstract Local-scale studies have shown that an overabundance of Cervidae species (deer, elk, moose) impacts forest bird communities. Through meta-analysis, we provide a generalized estimate of the overall direction and magnitude of the indirect effects overabundant cervids have on avian species. We conducted 2 distinct meta-analyses that synthesized data on 130 bird species collected from 17 publications. These analyses compared bird species’ population abundance and/or species richness at sites with overabundant cervids to sites with lower cervid abundance or without cervids. We evaluated whether the impacts of overabundant cervids are generally in the same direction (positive, negative) across avian species and locations and if effects vary in magnitude according to avian nesting location and foraging habitat. We found that where cervids were overabundant, there was a significant decrease in mean bird population abundance and species richness. Species that nest in trees, shrubs, and on the ground showed the largest decreases in abundance, as did species whose primary habitat is forest and open woodland and species that are primarily insectivores or omnivores. We did not find significant decreases in abundance for avian species that nest in cavities, whose primary habitat is grassland or scrub, nor for species that mainly eat seeds. Our results indicate that overabundant cervids, likely through their direct effects on vegetation and indirect effects on insects and forest birds, negatively impact individual bird populations and decrease overall avian species richness.more » « less
-
Every night during spring and autumn, the mass movement of migratory birds redistributes bird abundances found on the ground during the day. However, the connection between the magnitude of nocturnal migration and the resulting change in diurnal abundance remains poorly quantified. If departures and landings at the same location are balanced throughout the night, we expect high bird turnover but little change in diurnal abundance (stream‐like migration). Alternatively, migrants may move simultaneously in spatial pulses, with well‐separated areas of departure and landing that cause significant changes in the abundance of birds on the ground during the day (wave‐like migration). Here, we apply a flow model to data from weather surveillance radars (WSR) to quantify the daily fluxes of nocturnally migrating birds landing and departing from the ground, characterizing the movement and stopover of birds in a comprehensive synoptic scale framework. We corroborate our results with independent observations of the diurnal abundances of birds on the ground from eBird. Furthermore, we estimate the abundance turnover, defined as the proportion of birds replaced overnight. We find that seasonal bird migration chiefly resembles a stream where bird populations on the ground are continuously replaced by new individuals. Large areas show similar magnitudes of take‐off and landing, coupled with relatively small distances flown by birds each night, resulting in little change in bird densities on the ground. We further show that WSR‐inferred landing and take‐off fluxes predict changes in eBird‐derived abundance turnover rate and turnover in species composition. We find that the daily turnover rate of birds is 13% on average but can reach up to 50% on peak migration nights. Our results highlight that WSR networks can provide real‐time information on rapidly changing bird distributions on the ground. The flow model applied to WSR data can be a valuable tool for real‐time conservation and public engagement focused on migratory birds' daytime stopovers.more » « less
-
Many bird species commonly aggregate in flocks for reasons ranging from predator defense to navigation. Available evidence suggests that certain types of flocks—the V and echelon formations of large birds—may provide a benefit that reduces the aerodynamic cost of flight, whereas cluster flocks typical of smaller birds may increase flight costs. However, metabolic flight costs have not been directly measured in any of these group flight contexts [Zhang and Lauder,J. Exp. Biol.226, jeb245617 (2023)]. Here, we measured the energetic benefits of flight in small groups of two or three birds and the requirements for realizing those benefits, using metabolic energy expenditure and flight position measurements from European Starlings flying in a wind tunnel. The starlings continuously varied their relative position during flights but adopted a V formation motif on average, with a modal spanwise and streamwise spacing of [0.81, 0.91] wingspans. As measured via CO2production, flight costs for follower birds were significantly reduced compared to their individual solo flight benchmarks. However, followers with more positional variability with respect to leaders did less well, even increasing their costs above solo flight. Thus, we directly demonstrate energetic costs and benefits for group flight followers in an experimental context amenable to further investigation of the underlying aerodynamics, wake interactions, and bird characteristics that produce these metabolic effects.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1609/aaai.v38i20.30189
