Computer vision facilitates global clean-up


We are more aware than ever of the importance of halting climate change and cleaning up our planet; Environmental issues now feature prominently at global summits, boardrooms and classroom sessions. What can computer vision do in the fight against pollution? The image above shows just one example where a project called DeepTrash is using camera-equipped AUVs to detect plastic in the ocean.

clean oceans

Plastic in the world’s oceans is a major threat to marine life, and engineers around the world have invested in technology to address the problem. The sources of plastic pollution are wide-ranging and varied, including food packaging, discarded fishing gear, illegal dumping and accidental chemical spills from ships.

In 2021, researchers from California State University Monterey Bay, The Ocean Cleanup, and UC San Diego published a paper on using AUVs (autonomous underwater vehicles) to identify the most harmful floating plastics to help prioritize areas for cleaning.

The team used lidar and sonar imaging aboard an underwater robot to identify noxious objects in the epipelagic zone (upper open ocean). They used around 3000 internet images and deep convolutional neural networks to train what they named the computer vision model DeepPlasticand reported a 93% accurate identification.

AUVs have also been deployed to assist in the event of oil spills from tankers such as B. in the Deepwater Horizon disaster of 2010. Onboard cameras and sonar tools can be used to map plumes of oil droplets beneath the water’s surface, which don’t always move in predictable ways. Additional sensors can identify particle size or the petrochemical type involved, helping to identify the cause or location of the spill if it is unknown.

Captured on camera: smashing garbage bugs

LitterCam is a UK company’s simple idea to push for a reduction in littering from vehicles. The solution consists of surveillance cameras and an AI algorithm that detects garbage deposited from car windows. The platform reads the vehicle’s number plate and automatically issues a fine in the mail. It was tested in Maidstone, UK in July 2021 and hailed as a cost-effective and efficient solution to the city’s waste problem.

All did not go smoothly and the study was extended beyond its original six week schedule to allow for the retesting and software retraining necessitated by the high levels of non-detection and resulting false positives. However, the theory is good and in the long run the solution should be able to reduce litter and make our streets cleaner.

space junk

Unfortunately, it’s not just the earth and the oceans that are filling up with garbage and pollutants – space close to the earth is also becoming more and more of a garbage can. Space missions and satellite deployments have left a trail of hardware orbiting the earth for decades that will need to be eliminated sooner rather than later—currently there are even more redundant satellites in orbit as working! Several projects have been undertaken to explore ways to dispose of the bulky remains of spacecraft, satellites and other debris from our space ventures. There’s even an established acronym for this work – ADR (Active Debris Removal).

Computer vision plays an important role in this cosmic cleansing. The European Space Agency (ESA) will start ClearSpace-1 in 2025. This will send out a “space claw” based on visual navigation (VBN) technology to grab garbage up to the size of a standard washing machine and send it back to Earth, causing it to burn up on entry into Earth’s atmosphere.

Other innovations include technologies for the British company’s space operations LMO, which develops and tests machine learning algorithms designed to distinguish between satellites and space debris using infrared thermal and optical cameras. Subsidiary of Oxford Instruments AndorManufacturers of a scientific detector camera also want to help astronomers identify objects that pose a risk for ground-based astronomy applications.

Auto focus zoom cameras are an essential part of image processing systems used to detect and identify pollutants. Harrier cameras provide solutions for any type of surveillance, UAV or AUV system.

Written by Natalie Ryan, Marketing Specialist, Active silicon


Comments are closed.