Automated surface defect detection is a challenging problem that has attracted major attention for decades. Traditional methods were designed using a pipeline of carefully designed operations. The resulting methods were complex systems, which were difficult to tune and adapt to different problems or data. A new approach to solving this problem has emerged recently: deep learning. This trend is motivated by two main factors: the increasing digitization of society, which makes it possible to record large datasets of labeled samples; and the availability of a large pool of computational resources. This work evaluates state-of-the-art deep-learning methods in object detection and semantic segmentation in the field of automated surface inspection in metals. Images acquired in the industry are affected by the conditions of the environment, including noise, dust, and vibrations, which is an additional challenge. Moreover, industrial inspection requires accuracy, but also robustness and speed. The selected methods are applied to different datasets of images that include the most common defects in metals and the performance is compared in terms of accuracy and speed. Results show exceptional accuracy at a fraction of the required processing time.

The need for improved quality control in industry makes object detection crucial. This work addresses the challenging problem of subsurface defect detections using a combination of active thermography and deep learning. The novel contribution of this work is to pose the problem as one of object detection rather than semantic segmentation or classification. The images used as input for the deep learning algorithms are three-channel color images obtained using principal component thermography (PCT). The use of these images improves the signal-to-noise ratio (SNR). A framework to label ground truths automatically is also created. The most widely used deep learning detector algorithms were evaluated, and the fifth version of you only look once (YOLO), i.e., YOLOv5, was selected because of its excellent average precision (AP) and its low inference time. The resulting combination of this algorithm and active thermography is effective and accurate in detecting subsurface defects.

Land use classification using aerial imagery can be complex. Characteristics such as ground sampling distance, resolution, number of bands and the information these bands convey are the keys to its accuracy. Random Forest is the most widely used approach but better and more modern alternatives do exist. In this paper, state-of-the-art methods are evaluated, consisting of semantic segmentation networks such as UNet and DeepLabV3+. In addition, two datasets based on aircraft and satellite imagery are generated as a new state of the art to test land use classification. These datasets, called UOPNOA and UOS2, are publicly available. In this work, the performance of these networks and the two datasets generated are evaluated. This paper demonstrates that ground sampling distance is the most important factor in obtaining good semantic segmentation results, but a suitable number of bands can be as important. This proves that both aircraft and satellite imagery can produce good results, although for different reasons. Finally, cost performance for an inference prototype is evaluated, comparing various Microsoft Azure architectures. The evaluation concludes that using a GPU is unnecessarily costly for deployment. A GPU need only be used for training.

Ensure worker safety in the industry is crucial. Despite efforts to improve safety, statistics show a plateau in the reduction of these accidents in recent years. To decrease the number of accidents, compliance with established industrial safety standards and regulations by competent authorities must be ensured, including the use of Personal Protective Equipment (PPE). PPE usage is of paramount importance, as it is essential to prevent accidents from occurring. This work aims to improve worker safety by verifying PPE usage. Technology plays a key role here. A cost-effective solution is proposed to monitor PPE usage in real time. Most existing safety control systems are costly and require considerable maintenance. A low-cost computer vision system is proposed to supervise safety in industrial facilities. This system uses object detection and tracking technology in low-cost embedded devices and can generate alarms in real time if PPE is not used. Unlike other works, temporal information is used to generate the alarms. Safety managers receive this information to take necessary actions. Emphasis has been placed on cost, scalability, and ease of use to facilitate system implementation in industrial plants. The result is an effective system that improves worker safety by verifying established safety measures at a reduced cost. The methodology used improves the Average Precision of PPE detection by 6%. In addition, unlike other studies, the problem of application deployment is addressed, which has an impact on its cost.