Abstract
Glaucoma is a silent disease that shows symptoms when severe, leading to partial vision loss or irreversible blindness. Early screening permits treating patients in time. For glaucoma screening, retinal images are very important since they enable the observation of initial glaucoma lesions, which typically begins with the cupping formation in the optic disc (OD). In clinical settings, practical indicators such as Cup-to-Disc Ratio (CDR) are frequently used to evaluate the presence and stage of glaucoma. The ratio between the cup and the optic disc can be measured using the vertical or horizontal diameter, or the area of the two. Mass screening programs are limited by the high costs of specialised teams and equipment. Current deep learning (DL) methods can assist the glaucoma mass screening, lower the cost and allow it to be extended to larger populations. With DL methods in the OD and optic cup (OC) segmentation, is possible to evaluate the presence of glaucoma in the patient more quickly based on cupping formation in the OD, using CDR. In this work, is assessed the contribution of Multi-Class and Single-Class segmentation methods for glaucoma screening using the 3 types of CDR. U-Net architecture is trained using transfer learning models (Inception V3 and Inception ResNet V2) to segment the OD and OC and then evaluate glaucoma prediction based on different types of CDRs indicators. The models were trained and evaluated on main public known databases (REFUGE, RIM-ONE r3 and DRISHTI-GS). The segmentation of both OD and OC reach Dice over 0.8 and IoU above 0.7. The CDRs were computed to glaucoma assessment where was reach sensitivity above 0.8, specificity of 0.7, F1-Score around 0.7 and AUC above 0.85. Finally, conclusions of segmentation methods showing adequate performance to be used in practical glaucoma screening.

Abstract
Insect pests are the main cause of loss of productivity and quality in crops worldwide. Insect monitoring becomes necessary for the early detection of pests and thus avoiding the excessive use of pesticides. Automatic detection of insects attracted by traps is a form of monitoring. Modern data-driven methods present great results for object detection when representative datasets are available, but public datasets for insect detection are few and small. Pest24 public dataset is extensive, but noisy resulting in a poor detection rate. In this work, we aim to improve insect detection in the Pest24 dataset. We propose the creation of three sub-datasets selecting the highest represented classes, the highest colour discrepancy, and the one with the highest relative scale, respectively. Several Faster R-CNN and YOLOv5 architectures are explored, and the best results are achieved with the YOLOv5 with an mAP of 95.5%.

Abstract

Abstract
Globally, insect pests are the primary reason for reduced crop yield and quality. Although pesticides are commonly used to control and eliminate these pests, they can have adverse effects on the environment, human health, and natural resources. As an alternative, integrated pest management has been devised to enhance insect pest control, decrease the excessive use of pesticides, and enhance the output and quality of crops. With the improvements in artificial intelligence technologies, several applications have emerged in the agricultural context, including automatic detection, monitoring, and identification of insects. The purpose of this article is to outline the leading techniques for the automated detection of insects, highlighting the most successful approaches and methodologies while also drawing attention to the remaining challenges and gaps in this area. The aim is to furnish the reader with an overview of the major developments in this field. This study analysed 92 studies published between 2016 and 2022 on the automatic detection of insects in traps using deep learning techniques. The search was conducted on six electronic databases, and 36 articles met the inclusion criteria. The inclusion criteria were studies that applied deep learning techniques for insect classification, counting, and detection, written in English. The selection process involved analysing the title, keywords, and abstract of each study, resulting in the exclusion of 33 articles. The remaining 36 articles included 12 for the classification task and 24 for the detection task. Two main approaches-standard and adaptable-for insect detection were identified, with various architectures and detectors. The accuracy of the classification was found to be most influenced by dataset size, while detection was significantly affected by the number of classes and dataset size. The study also highlights two challenges and recommendations, namely, dataset characteristics (such as unbalanced classes and incomplete annotation) and methodologies (such as the limitations of algorithms for small objects and the lack of information about small insects). To overcome these challenges, further research is recommended to improve insect pest management practices. This research should focus on addressing the limitations and challenges identified in this article to ensure more effective insect pest management.

Abstract

Abstract
Public lighting is crucial for maintaining the safety and well-being of communities. Current inspection methods involve examining the luminaires during the day, but this approach has drawbacks, including energy consumption, delay in detecting issues, and high costs and time investment. Utilising deep learning based automatic detection is an advanced method that can be used for identifying and locating issues in this field. This study aims to use deep learning to automatically detect burnt-out street lights, using Seville (Spain) as a case study. The study uses high-resolution night time imagery from the JL1-3B satellite to create a dataset called NLight, which is then divided into three subsets: NL1, NL2, and NT. The NL1 and NL2 datasets are used to train and evaluate YOLOv5 and YOLOv7 segmentation models for instance segmentation of streets. And then, distance outliers were detected to find the lights off. Finally, the NT dataset is used to evaluate the effectiveness of the proposed methodology. The study finds that YOLOv5 achieved a mask mAP of 57.7%, and the proposed methodology had a precision of 30.8% and a recall of 28.3%. The main goal of this work is accomplished, but there is still space for future work to improve the methodology.