Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

Our e-services for applications, projects and assessments close on Thursday 30 May at 4:30pm because of system upgrades. We expect to open them again on Friday 31 May at 8am the latest.

TrashCam - UAV´s for marine litter mapping

Reference number
Funding from Vinnova SEK 486 000
Project duration May 2018 - June 2019
Status Completed
Venture Drones
Call Drones of the future - Drones for citizens and community

Purpose and goal

The project aimed to increase the knowledge of marine litter and enable mapping of longer coastal distances regarding litter on beaches along the Baltic Sea. The main goal was to develop a cost-effective measurement method for marine litter with the help of a specially adapted drone.

Expected effects and result

The project has developed a method for measuring marine litter on beaches with drones. However, the subsequent work on manual identification of litter from aerial images proved to have low accuracy and overall it took longer compared to the traditional method of picking litter by hand. In order for the method to be cost-effective, an auto-identification program of litter items is required, which the project has failed to produce in its entirety. The project has shown that flying with fixed wing can quickly scan large areas which is useful in identifying so-called. hot-spots of litter.

Planned approach and implementation

The work started with developing operational parameters for flight with quadrocopter and aerial images. After that, field work was carried out where the results of the manual method of picking litter were compared with the drone method. Orthophotos were developed and a beach was analysed for the number and type of litter that occurred. Accuracy and time spent on the work were compared. In parallel, intensive work was performed to develop an algorithm for auto-identification of litter and machine learning of neural networks in order to identify litter.

External links

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 8 January 2019

Reference number 2018-01751

Page statistics