Today, solar energy is taking an increasing share of the total energy mix. Unfortunately, many operational photovoltaic plants suffer from a plenitude of defects resulting in non-negligible power loss. The latter highly impacts the overall performance of the PV site; therefore, operators need to regularly inspect their solar parks for anomalies in order to prevent severe performance drops. As this operation is naturally labor-intensive and costly, we present in this paper a novel system for improved PV diagnostics using drone-based imagery. Our solution consists of three main steps. The first step locates the solar panels within the image. The second step detects the anomalies within the solar panels. The final step identifies the root cause of the anomaly. In this paper, we mainly focus on the second step comprising the detection of anomalies within solar panels, which is done using a region-based convolutional neural network (CNN). Experiments on six different PV sites with different specifications and a variety of defects demonstrate that our anomaly detector achieves a true positive rate or recall of more than 90% for a false positive rate of around 2% to 3% tested on a dataset containing nearly 9000 solar panels. Compared to the best state-of-the-art methods, the experiments revealed that we achieve a slightly higher true positive rate for a substantially lower false positive rate, while tested on a more realistic dataset.

The installation of solar plants everywhere in the world increases year by year. Automated diagnostic methods are needed to inspect the solar plants and to identify anomalies within these photovoltaic panels. The inspection is usually carried out by unmanned aerial vehicles (UAVs) using thermal imaging sensors. The first step in the whole process is to detect the solar panels in those images. However, standard image processing techniques fail in case of low-contrast images or images with complex backgrounds. Moreover, the shades of power lines or structures similar to solar panels impede the automated detection process. In this research, two self-developed methods are compared for the detection of panels in this context, one based on classical techniques and another one based on deep learning, both with a common post-processing step. The first method is based on edge detection and classification, in contrast to the second method is based on training a region based convolutional neural networks to identify a panel. The first method corrects for the low contrast of the thermal image using several preprocessing techniques. Subsequently, edge detection, segmentation and segment classification are applied. The latter is done using a support vector machine trained with an optimized texture descriptor vector. The second method is based on deep learning trained with images that have been subjected to three different pre-processing operations. The postprocessing use the detected panels to infer the location of panels that were not detected. This step selects contours from detected panels based on the panel area and the angle of rotation. Then new panels are determined by the extrapolation of these contours. The panels in 100 random images taken from eleven UAV flights over three solar plants are labeled and used to evaluate the detection methods. The metrics for the new method based on classical techniques reaches a precision of 0.997, a recall of 0.970 and a $F_1$ score of 0.983. The metrics for the method of deep learning reaches a precision of 0.996, a recall of 0.981 and a $F_1$ score of 0.989. The two panel detection methods are highly effective in the presence of complex backgrounds.

The recent advent of 3D in electron microscopy (EM) has allowed for detection of nanometer resolution structures. This has caused an explosion in dataset size, necessitating the development of automated workflows. Moreover, large 3D EM datasets typically require hours to days to be acquired and accelerated imaging typically results in noisy data. Advanced denoising techniques can alleviate this, but tend to be less accessible to the community due to low-level programming environments, complex parameter tuning or a computational bottleneck. We present DenoisEM: an interactive and GPU accelerated denoising plugin for ImageJ that ensures fast parameter tuning and processing through parallel computing. Experimental results show that DenoisEM is one order of magnitude faster than related software and can accelerate data acquisition by a factor of 4 without significantly affecting data quality. Lastly, we show that image denoising benefits visualization and (semi-)automated segmentation and analysis of ultrastructure in various volume EM datasets.

In this letter, we present an efficient image denoising method combining quadtree-based nonlocal means (NLM) and locally adaptive principal component analysis. It exploits nonlocal multiscale self-similarity better, by creating sub-patches of different sizes using quadtree decomposition on each patch. To achieve spatially uniform denoising, we propose a local noise variance estimator combined with denoiser based on locally adaptive principal component analysis. Experimental results demonstrate that our proposed method achieves very competitive denoising performance compared with state-of-the-art denoising methods, even obtaining better visual perception at high noise levels.

Low-rank tensor completion has been widely used in computer vision and machine learning. This paper develops a novel multimodal core tensor factorization (MCTF) method combined with a tensor low-rankness measure and a better nonconvex relaxation form of this measure (NC-MCTF). The proposed models encode low-rank insights for general tensors provided by Tucker and T-SVD and thus are expected to simultaneously model spectral low-rankness in multiple orientations and accurately restore the data of intrinsic low-rank structure based on few observed entries. Furthermore, we study the MCTF and NC-MCTF regularization minimization problem and design an effective block successive upper-bound minimization (BSUM) algorithm to solve them. Theoretically, we prove that the iterates generated by the proposed models converge to the set of coordinatewise minimizers. This efficient solver can extend MCTF to various tasks such as tensor completion. A series of experiments including hyperspectral image (HSI), video and MRI completion confirm the superior performance of the proposed method.