ABSTRACT
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 F1 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 F1 score of 0.989. The two panel detection methods are highly effective in the presence of complex backgrounds.
ABSTRACT
OBJECTIVE: Friedreich ataxia (FRDA) is an autosomal recessive neurodegenerative disease caused in almost all cases by homozygosity for a GAA trinucleotide repeat expansion in the frataxin gene. Frataxin is a mitochondrial protein involved in iron homeostasis. FRDA patients have a high prevalence of diabetes, the pathogenesis of which is not known. We aimed to evaluate the relative contribution of insulin resistance and ß-cell failure and the pathogenic mechanisms involved in FRDA diabetes. METHODS: Forty-one FRDA patients, 26 heterozygous carriers of a GAA expansion, and 53 controls underwent oral and intravenous glucose tolerance tests. ß-Cell proportion was quantified in postmortem pancreas sections from 9 unrelated FRDA patients. Using an in vitro disease model, we studied how frataxin deficiency affects ß-cell function and survival. RESULTS: FRDA patients had increased abdominal fat and were insulin resistant. This was not compensated for by increased insulin secretion, resulting in a markedly reduced disposition index, indicative of pancreatic ß-cell failure. Loss of glucose tolerance was driven by ß-cell dysfunction, which correlated with abdominal fatness. In postmortem pancreas sections, pancreatic islets of FRDA patients had a lower ß-cell content. RNA interference-mediated frataxin knockdown impaired glucose-stimulated insulin secretion and induced apoptosis in rat ß cells and human islets. Frataxin deficiency sensitized ß cells to oleate-induced and endoplasmic reticulum stress-induced apoptosis, which could be prevented by the incretins glucagon-like peptide-1 and glucose-dependent insulinotropic polypeptide. INTERPRETATION: Pancreatic ß-cell dysfunction is central to diabetes development in FRDA as a result of mitochondrial dysfunction and higher sensitivity to metabolic and endoplasmic reticulum stress-induced ß-cell death.
