0
Article Tier 2 Sign in to save

Image descattering with synthetic polarization imaging and untrained network

2021 3 citations

AI summary Read the abstract

This study used a synthetic polarizing camera combined with an untrained neural network to remove scattering effects and improve image quality in underwater imaging. The approach addresses the challenge of light scattering that degrades resolution and contrast in underwater optical systems.

Water scattering is a significant limiting factor for underwater imaging quality. It changes the transportation direction of the original light path, causes the attenuation of light intensity, and so on. In this work, we use a synthetic polarizing camera to capture the images with different polarization states and reduce the impact of water scattering in one step with the underwater light propagation model and the Stokes vector. In addition, an untrained deep network is designed to complete the image descattering processing. Compared with the methods based on deep learning or physical model prior, it is more efficient. This technology is suitable for use in portable underwater imaging optical systems for real-time imaging and detecting particulate matter such as microplastics and microbial particles. It also broadens the application of underwater polarization imaging.

More Papers Like This

Article Tier 2

Digital holography with polarization multiplexing for underwater imaging and descattering

AI summary Read the abstract

Researchers developed a digital holographic microscopy method with polarization multiplexing to improve underwater imaging and reduce the degrading effects of light scattering. The technique allows clearer visualization of particles and structures in turbid underwater environments.

Article Tier 2

Computational polarized holography for automatic monitoring of microplastics in scattering aquatic environments

AI summary Read the abstract

Researchers developed an integrated imaging system based on computational polarized holography for automatic monitoring of microplastics in aquatic environments. The system enables accurate 3D tracking of dynamic microplastic particles, and a hybrid de-scattering algorithm substantially improves image quality even in turbid water conditions. An unsupervised clustering method was also developed to identify and classify different microplastics based on their multimodal features without manual annotation.

Article Tier 2

Classification of Microplastic Particles in Water using Polarized Light Scattering and Machine Learning Methods

AI summary Read the abstract

Researchers developed a reflection-based, in-situ classification method for microplastic particles in water using polarized light scattering combined with machine learning, successfully identifying colorless particles in the 50-300 micrometer range. The approach circumvents transmission-based interference problems and offers a pathway toward continuous, large-scale microplastic monitoring in aquatic environments.

Article Tier 2

HCTSpeckle and Lightweight YUV Transformerwith ViT Encoder-Sandwich Decoder NetworkFor Underwater Microplastic High ResolutionImage Segmentation

AI summary Read the abstract

Scientists have developed a smart imaging system that can spot and sort microplastic pollution in murky underwater photos with impressive accuracy, about 97%. This matters because microplastics are turning up everywhere in our oceans and food chain, and better detection tools like this could help researchers track pollution more reliably, which is a key step toward understanding and reducing the health risks these tiny plastic particles may pose to people.

Article Tier 2

Snapshot Polarization-Sensitive Holography for Detecting Microplastics in Turbid Water

AI summary Read the abstract

Researchers developed a new imaging technique combining holography and polarimetry to detect microplastic particles in turbid water, a setting where traditional detection methods struggle. The approach uses differences in how light polarizes when passing through plastic versus natural particles to distinguish microplastics even in murky conditions. The study demonstrates a promising tool for faster, more practical monitoring of microplastic pollution in real-world water environments.

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.

Email me about

Share this paper