Computer vision–based bat monitoring solution
Development
Nov 17, 2025
Aug 10, 2026
Project Overview
Bats that nest in homes can cause damage over time. This can include wood decay and corrosion, damaged insulation, and a strong odour. There is also an increased risk of disease transmission due to the accumulation of their droppings and urine, which poses a health risk. In collaboration with Sam Watson Ecology, Saiwa is developing an AI model that uses computer vision to process videos and images and identify bats and their nests.
Innovation
The solution developed by Saiwa's team is one of the first commercial solutions for detecting bats and their nests in residential areas, homes, and buildings using computer vision processing of fixed surveillance camera images and videos. The model is to be developed in a way that is cost-effective and easy-to-use for environmental protection agencies, research institutions, and industrial partners.
Partners
- Saiwa Inc: Development of computer vision-based AI model and deployment on Sairone platform
- Sam Watson Ecology: Applied ecology specialist
Solution
Sam Watson Ecology uses its equipment and cameras to collect suitable data, including high-quality images and videos, to train the model, and Saiwa's team uses that to develop a computer vision model that can process the data to identify bats and their nests and provide them in the form of downloadable reports.
The algorithm assumes a fixed camera at night, and has these steps:
- Preprocessing: It denoises frames to remove insects and small moving objects, then enhances contrast to reveal faint details.
- Detection: Background subtraction reduces slow lighting changes, and frame differencing highlights fast, small motions (bat flights).
- Tracking: Detected bats are tracked in 2D with a Kalman filter, overlapping tracks are separated, and individual flight paths are recovered.
- Roost Estimation: Start and end points of tracks are analyzed; If these points cluster in regions away from the frame edges, the area is likely a roost. A Gaussian voting scheme selects the most likely roost locations, which are shown with bounding boxes.
The output is a map on the first frame with roost candidates, plus a video showing bats, their tracks, and a black-and-white motion mask.
Related Projects
Hemaa.ai, in partnership with Tarmeez, delivers an AI-powered solution for date palm plantations that enables early health monitoring, precise tree counting, and targeted weed detection using drone and satellite imagery. Leveraging advanced deep learning models, this platform enhances operational efficiency, reduces costs, and promotes sustainable agriculture through timely alerts and accurate spatial data mapping.
Ordered by
Ducks Unlimited Canada (DUC)Detection and Semantic Segmentation of European Water Chestnut Colonies in Drone Orthophotos
Jan 2026
In 2026, Saiwa continues its collaboration with Ducks Unlimited Canada (DUC) to advance drone-based monitoring of invasive aquatic vegetation. Building on previous phases focused on segmentation accuracy and geospatial localization, this phase introduces enhanced pixel-level semantic segmentation of European Water Chestnut (EWC) to enable detailed mapping of both individual plants and dense colonies across diverse aquatic environments.
Ordered by
Ducks Unlimited CanadaDetection and Surveillance of European Water Chestnut
Oct 2022→Jan 2023
European water chestnut (Trapa natans) is an invasive floating-leaved aquatic plant that is capable of out-competing native species and altering Ontario’s aquatic ecosystems. In addition to ongoing control of known populations in Ontario, this species is designated as a “Prohibited Species” in Ontario under the Invasive Species Act, 2015 to aid in prevention, detection and control of the species. Ducks Unlimited Canada (DUC) performs surveillance and control of this species in eastern Ontario in attempts to eradicate existing populations and prevent the establishment of new ones.
To enhance Ducks Unlimited Canada (DUC)‘s capability for UAV-based surveillance of European Water Chestnut (EWC) through machine learning, we at Saiwa have previously implemented the initial version of the EWC detector software. In the second stage, we are in the process of finalizing the product’s features and upgrading its interfaces.The two primary features to be incorporated in this stage are as follows:
Incremental learning for gradually training the deep network over time. This feature enables us to rectify false positive and false negative detections over time.
Reporting the 3D universal coordinates of EWC locations using drone configuration and temporal GPS data.
Ordered by
Ducks Unlimited Canada (DUC)Detect Water Soldier RGB Drone Monitoring And Tracking
Dec 2024→Dec 2025
In late 2024, Saiwa Co and Ducks Unlimited Canada launched a project to enhance UAV-based detection and surveillance of the invasive aquatic plant Water Soldier (Stratiotes Aloides) using advanced image processing and deep learning. The team addressed challenges from dense and submerged vegetation, environmental noise, and irregular plant shapes by reformulating the task as semantic segmentation. The project delivered a robust model achieving 95.52% pixel accuracy, enabling accurate monitoring of both isolated plants and dense colonies, supporting early intervention, efficient management, and a scalable foundation for future multispectral enhancements.
Ordered by
Ducks Unlimited Canada (DUC)Multispectral Submersion Classification of Water Soldier in Drone Imagery
Jan 2026
In 2026, Saiwa continues its collaboration with Ducks Unlimited Canada (DUC) to further enhance drone-based monitoring of invasive aquatic vegetation. Building on last year’s high-accuracy RGB-based Water Soldier detection pipeline, this new phase focuses specifically on determining whether each detected plant is located above or below the water surface.