Advancing UAV-based EWC surveillance

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. 

Problem

Using the software saved a lot of time. However, it was possible to further optimize the software to reduce false positive and false negative detections to increase efficiency.

Solution

Incremental learning capabilities were added to the software, allowing the artificial intelligence algorithms to improve their detection accuracy over time and minimize false detections. Additionally, the integration of GPS data has enabled the software to report three-dimensional global coordinates of the European water chestnut locations, greatly facilitating the DUC staff’s ability to locate invasive plant species with ease.

Outcome

With the addition of incremental learning, the software has been able to achieve near 100% accuracy in detection, significantly reducing false positives and negatives. Moreover, by utilizing GPS data, the software now reports three-dimensional global coordinates of the European water chestnut locations, enabling DUC staff to locate invasive plant species more accurately than before. These advancements aid DUC in more effectively combating this invasive species and preserving aquatic ecosystems.

Read Also: Corrective Exercise mobile application

Project customer: Duck Unlimited Canada Company
For more information please contact us via: info@saiwa.ai