An official website of the United States government
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
Long-term Monitoring of Bird Flocks in the Wild
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
- Award ID(s):
- 1956050
- PAR ID:
- 10545646
- Publisher / Repository:
- International Joint Conferences on Artificial Intelligence Organization
- Date Published:
- ISBN:
- 978-1-956792-03-4
- Page Range / eLocation ID:
- 6344 to 6352
- Format(s):
- Medium: X
- Location:
- Macau, SAR China
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
It is a common practice to think of a video as a sequence of images (frames), and re-use deep neural network models that are trained only on images for similar analytics tasks on videos. In this paper, we show that this “leap of faith” that deep learning models that work well on images will also work well on videos is actually flawed.We show that even when a video camera is viewing a scene that is not changing in any humanperceptible way, and we control for external factors like video compression and environment (lighting), the accuracy of video analytics application fluctuates noticeably. These fluctuations occur because successive frames produced by the video camera may look similar visually, but are perceived quite differently by the video analytics applications.We observed that the root cause for these fluctuations is the dynamic camera parameter changes that a video camera automatically makes in order to capture and produce a visually pleasing video. The camera inadvertently acts as an “unintentional adversary” because these slight changes in the image pixel values in consecutive frames, as we show, have a noticeably adverse impact on the accuracy of insights from video analytics tasks that re-use image-trained deep learning models. To address this inadvertent adversarial effect from the camera, we explore the use of transfer learning techniques to improve learning in video analytics tasks through the transfer of knowledge from learning on image analytics tasks. Our experiments with a number of different cameras, and a variety of different video analytics tasks, show that the inadvertent adversarial effect from the camera can be noticeably offset by quickly re-training the deep learning models using transfer learning. In particular, we show that our newly trained Yolov5 model reduces fluctuation in object detection across frames, which leads to better tracking of objects (∼40% fewer mistakes in tracking). Our paper also provides new directions and techniques to mitigate the camera’s adversarial effect on deep learning models used for video analytics applications.more » « less
-
There is an urgent need to develop global observation networks to quantify biodiversity trends for evaluating achievements of targets of Kunming-Montreal Global Biodiversity Framework. Camera traps are a commonly used tool, with the potential to enhance global observation networks for monitoring wildlife population trends and has the capacity to constitute global observation networks by applying a unified sampling protocol. The Snapshot protocol is simple and easy for camera trapping which is applied in North America and Europe. However, there is no regional camera-trap network with the Snapshot protocol in Asia. We present the first dataset from a collaborative camera-trap survey using the Snapshot protocol in Japan conducted in 2023. We collected data at 90 locations across nine arrays for a total of 6162 trap-nights of survey effort. The total number of sequences with mammals and birds was 7967, including 20 mammal species and 23 avian species. Apart from humans, wild boar, sika deer and rodents were the most commonly observed taxa on the camera traps, covering 57.9% of all the animal individuals. We provide the dataset with a standard format of Wildlife Insights, but also with Camtrap DP 1.0 format. Our dataset can be used for a part of the global dataset for comparing relative abundances of wildlife and for a baseline of wildlife population trends in Japan. It can also used for training machine-learning models for automatic species identifications.more » « less
-
As camera traps have grown in popularity, their utilization has expanded to numerous fields, including wildlife research, conservation, and ecological studies. The information gathered using this equipment gives researchers a precise and comprehensive understanding about the activities of animals in their natural environments. For this type of data to be useful, camera trap images must be labeled so that the species in the images can be classified and counted. This has typically been done by teams of researchers and volunteers, and it can be said that the process is at best time-consuming. With recent developments in deep learning, the process of automatically detecting and identifying wildlife using Convolutional Neural Networks (CNN) can significantly reduce the workload of research teams and free up resources so that researchers can focus on the aspects of conservation.more » « less
-
As camera traps have grown in popularity, their utilization has expanded to numerous fields, including wildlife research, conservation, and ecological studies. The information gathered using this equipment gives researchers a precise and comprehensive understanding about the activities of animals in their natural environments. For this type of data to be useful, camera trap images must be labeled so that the species in the images can be classified and counted. This has typically been done by teams of researchers and volunteers, and it can be said that the process is at best time-consuming. With recent developments in deep learning, the process of automatically detecting and identifying wildlife using Convolutional Neural Networks (CNN) can significantly reduce the workload of research teams and free up resources so that researchers can focus on the aspects of conservation.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.24963/ijcai.2023/704
