A Novel Detection Refinement Technique for Accurate Identification of Nephrops norvegicus Burrows in Underwater Imagery.

With the evolution of the convolutional neural network (CNN), object detection in the underwater environment has gained a lot of attention. However, due to the complex nature of the underwater environment, generic CNN-based object detectors still face challenges in underwater object detection. These challenges include image blurring, texture distortion, color shift, and scale variation, which result in low precision and recall rates. To tackle this challenge, we propose a detection refinement algorithm based on spatial-temporal analysis to improve the performance of generic detectors by suppressing the false positives and recovering the missed detections in underwater videos. In the proposed work, we use state-of-the-art deep neural networks such as Inception, ResNet50, and ResNet101 to automatically classify and detect the Norway lobster Nephrops norvegicus burrows from underwater videos. Nephrops is one of the most important commercial species in Northeast Atlantic waters, and it lives in burrow systems that it builds itself on muddy bottoms. To evaluate the performance of proposed framework, we collected the data from the Gulf of Cadiz. From experiment results, we demonstrate that the proposed framework effectively suppresses false positives and recovers missed detections obtained from generic detectors. The mean average precision (mAP) gained a 10% increase with the proposed refinement technique.

Efficient broadband light absorption in thin-film a-Si solar cell based on double sided hybrid bi-metallic nanogratings.

Thin film solar cells (TFSCs) suffer from poor light absorption due to their small thickness, which limits most of their practical applications. Surface plasmons generated by plasmonic nanoparticles offer an opportunity for a low-cost and scalable method to optically engineer TFSCs. Here, a systematic simulation study is conducted to improve the absorption efficiency of amorphous silicon (a-Si) by incorporating double sided plasmonic bi-metallic (Al-Cu) nanogratings. The upper pair of the gratings together with an antireflection coating are responsible for minimizing the reflection losses and enhancing the absorption of low wavelength visible light spectrum in the active layer. The bottom pairs are accountable for increasing the absorption of long wavelength photons in the active layer. In this way, a-Si, which is a poor absorber in the long wavelength region, is now able to absorb broadband light from 670-1060 nm with an average simulated absorption rate of more than 70%, and improved simulated photocurrent density of 22.30 mA cm-2, respectively. Moreover, simulation results show that the proposed structure reveals many other excellent properties such as small incident angle insensitivity, tunability, and remarkable structural parameters tolerance. Such a design concept is quite versatile and can be extended to other TFSCs.

Correction: Efficient broadband light absorption in thin-film a-Si solar cell based on double sided hybrid bi-metallic nanogratings.

[This corrects the article DOI: 10.1039/C9RA10232A.].