We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Flow-guided acoustic imaging for tracking underwater floating debris in low-visibility environments
AI summary Read the abstract
Researchers developed a sonar-based system that can track floating trash like plastic bags, bottles, and cans underwater, even in murky, dark water where cameras don't work well. This matters because it could help power robots that automatically clean up ocean debris, tackling plastic pollution before it breaks down into microplastics that end up in seafood and drinking water. While the system worked well for plastic bags, it was less accurate for bottles and cans, showing there's still room for improvement before this technology is ready for widespread ocean cleanup use.
Robust tracking of floating marine debris is a prerequisite for autonomous underwater cleanup systems operating in turbid or poorly illuminated environments. Conventional optical sensors often fail under such conditions, while appearance-based tracking methods suffer from limited generalization due to the large variability in debris shape, material composition, and deformation. To address these challenges, this study proposes an acoustic imaging-based tracking framework that exploits temporal motion cues in 2D forward-looking sonar (FLS) frame sequences through optical-flow estimation, eliminating the need for prior knowledge of object categories or geometric characteristics. A learning-based optical flow model is adapted to the unique characteristics of acoustic imagery, improving motion estimation robustness in the presence of sonar noise, background reverberation, and low contrast. The proposed approach was evaluated using acoustic datasets containing representative floating debris, including plastic bags, plastic bottles, and metal cans, under diverse underwater conditions. Experimental results achieved mean Intersection-over-Union (mIoU) scores of 78.10%, 56.99%, and 59.62% for plastic bags, plastic bottles, and metal cans, respectively. These findings indicate that motion-aware analysis of FLS data provides an effective solution for debris tracking in low-visibility environments.
More Papers Like This
Automated Underwater Plastic Waste Detection and Volume Assessment through Instance Segmentation
AI summary Read the abstract
Researchers built an AI tool that can automatically spot and measure plastic waste in murky underwater video, even when visibility is poor. This matters because tracking ocean plastic pollution is a critical first step toward cleanup efforts, plastic waste breaks down into microplastics that enter the food chain and eventually end up in the seafood we eat. By making it easier to monitor where plastic waste accumulates, this technology could help scientists and cleanup crews target their efforts more effectively.
Automated Underwater Plastic Waste Detection and Volume Assessment through Instance Segmentation
AI summary Read the abstract
Researchers built an AI tool that can automatically spot and measure plastic waste in murky underwater footage, even when visibility is poor. This matters because tracking ocean plastic pollution is a critical first step to cleaning it up, plastic debris breaks down into microplastics that enter the food chain and, ultimately, our own bodies through seafood and water. By making pollution monitoring faster and easier, tools like this could help scientists and cleanup crews target problem areas more efficiently.
Deep learning-based detection of submerged debris and plastics in underwater environments: a systematic review
AI summary Read the abstract
This review pulls together 50 studies on AI systems that use underwater cameras to spot plastic debris in oceans and waterways, finding that certain smart, efficient algorithms can now detect trash with over 90% accuracy—even running on small, low-power devices carried by underwater robots. This matters because better tracking of where plastic waste accumulates and breaks down is a key step toward understanding and eventually reducing the microplastics that end up in seafood, drinking water, and our bodies, though the technology still struggles in murky or dark water.
Improved Transformer-based detection of underwater plastic debris in complex environments
AI summary Read the abstract
Researchers built an improved AI system that can spot plastic trash underwater more accurately, even in murky, cluttered footage where debris is small or hard to see. This matters because better detection tools could help track and clean up ocean plastic before it breaks down into microplastics — the tiny particles increasingly found in seafood, drinking water, and even human blood and organs. While this study focused on detection technology rather than health outcomes directly, improving our ability to find and remove plastic waste is an important step toward reducing microplastic pollution that can ultimately end up in our food chain and bodies.
Cleaning up the world’s oceans with underwater laser imaging
AI summary Read the abstract
Researchers proposed using underwater LiDAR (Light Detection and Ranging) technology to detect and map submerged plastic debris in the oceans, arguing this approach offers higher resolution and greater safety for marine life compared to sonar, and could enable targeted cleanup of the estimated 70% of ocean plastic that lies below the surface.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.