CMOS image sensor
Dotaz
Zobrazit nápovědu
Reliable tools for artefact rejection and signal classification are a must for cosmic ray detection experiments based on CMOS technology. In this paper, we analyse the fitness of several feature-based statistical classifiers for the classification of particle candidate hits in four categories: spots, tracks, worms and artefacts. We use Zernike moments of the image function as feature carriers and propose a preprocessing and denoising scheme to make the feature extraction more efficient. As opposed to convolution neural network classifiers, the feature-based classifiers allow for establishing a connection between features and geometrical properties of candidate hits. Apart from basic classifiers we also consider their ensemble extensions and find these extensions generally better performing than basic versions, with an average recognition accuracy of 88%.
- Klíčová slova
- CMOS sensors, Zernike moments, computer vision, feature-based classification, machine learning,
- MeSH
- artefakty * MeSH
- neuronové sítě * MeSH
- Publikační typ
- časopisecké články MeSH
Gamification is known to enhance users' participation in education and research projects that follow the citizen science paradigm. The Cosmic Ray Extremely Distributed Observatory (CREDO) experiment is designed for the large-scale study of various radiation forms that continuously reach the Earth from space, collectively known as cosmic rays. The CREDO Detector app relies on a network of involved users and is now working worldwide across phones and other CMOS sensor-equipped devices. To broaden the user base and activate current users, CREDO extensively uses the gamification solutions like the periodical Particle Hunters Competition. However, the adverse effect of gamification is that the number of artefacts, i.e., signals unrelated to cosmic ray detection or openly related to cheating, substantially increases. To tag the artefacts appearing in the CREDO database we propose the method based on machine learning. The approach involves training the Convolutional Neural Network (CNN) to recognise the morphological difference between signals and artefacts. As a result we obtain the CNN-based trigger which is able to mimic the signal vs. artefact assignments of human annotators as closely as possible. To enhance the method, the input image signal is adaptively thresholded and then transformed using Daubechies wavelets. In this exploratory study, we use wavelet transforms to amplify distinctive image features. As a result, we obtain a very good recognition ratio of almost 99% for both signal and artefacts. The proposed solution allows eliminating the manual supervision of the competition process.
- Klíčová slova
- CREDO, citizen science, convolutional neural networks, deep learning, gamification, global sensor network, image classification, image sensors,
- MeSH
- artefakty MeSH
- lidé MeSH
- neuronové sítě * MeSH
- počítačové zpracování obrazu * MeSH
- strojové učení MeSH
- vlnková analýza MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
Optical camera communications (OCC) research field has grown recently, aided by ubiquitous digital cameras; however, atmospheric conditions can restrict their feasibility in outdoor scenarios. In this work, we studied an experimental OCC system under environmental phenomena emulated in a laboratory chamber. We found that the heat-induced turbulence does not affect our system significantly, while the attenuation caused by fog does decrease the signal quality. For this reason, a novel strategy is proposed, using the camera's built-in amplifier to overcome the optical power loss and to decrease the quantization noise induced by the analog-digital converter of the camera. The signal quality has been evaluated using the Pearson's correlation coefficient with respect to a reference template signal, along with the signal-to-noise ratio that has been empirically evaluated. The amplification mechanism introduced allows our system to receive the OCC signal under heavy fog by gradually increasing the camera gain up to 16 dB, for meteorological visibility values down to 10 m, with a correlation coefficient of 0.9 with respect to clear conditions.
