Public littering and discarded trash are, despite the effort being put to limit it, still a serious ecological, aesthetic, and social problem. The problematic waste is usually localised and picked up by designated personnel, which is a tiresome, time-consuming task. This paper proposes a low-cost solution enabling the localisation of trash and litter objects in low altitude imagery collected by an unmanned aerial vehicle (UAV) during an autonomous patrol mission. The objects of interest are detected in the acquired images and put on the global map using a set of onboard sensors commonly found in typical UAV autopilots. The core object detection algorithm is based on deep, convolutional neural networks. Since the task is domain-specific, a dedicated dataset of images containing objects of interest was collected and annotated. The dataset is made publicly available, and its description is contained in the paper. The dataset was used to test a range of embedded devices enabling the deployment of deep neural networks for inference onboard the UAV. The results of measurements in terms of detection accuracy and processing speed are enclosed, and recommendations for the neural network model and hardware platform are given based on the obtained values. The complete system can be put together using inexpensive, off-the-shelf components, and perform autonomous localisation of discarded trash, relieving human personnel of this burdensome task, and enabling automated pickup planning.

Recent advances in deep learning-based image processing have enabled significant improvements in multiple computer vision fields, with crowd counting being no exception. Crowd counting is still attracting research interest due to its potential usefulness for traffic and pedestrian stream monitoring and analysis. This study considered a specific case of crowd counting, namely, counting based on low-altitude aerial images collected by an unmanned aerial vehicle. We evaluated a range of neural network architectures to find ones appropriate for on-board image processing using edge computing devices while minimising the loss in performance. Through experiments on a range of neural network architectures, we also showed that the input image resolution significantly impacts the prediction quality and should be considered an important factor before going for a more complex neural network model to improve accuracy. Moreover, by extending a state-of-the-art benchmark with more in-depth testing, we showed that larger models might be prone to overfitting because of the relative scarcity of training data.

Introduction: Birt-Hogg-Dubé syndrome is a rare genodermatosis inherited as an autosomal dominant trait. Birt-Hogg-Dubé syndrome was first described in 1977 by three dermatologists, Arthur Birt, Georgina Hogg and William J. Dubé. It is characterised by the development of multiple small white bumps primarily occurring on the face and chest. Birt-Hogg-Dubé syndrome is associate with an increased risk or pneumothorax, pulmonary cysts, and renal tumours. The disorder is caused by mutations in the FLCN gene, which encodes folliculin. Cas report: A 50-year-old man presented with multiple yellowish--white papules located on cheeks and forehead. Earlier the patient was hospitalized because of pneumothorax. Diagnostic imaging revealed pulmonary cysts and fibrosis, most likely secondary to previous pneumothorax. Abdominal ultrasound showed no tumours. The diagnosis of Birt-Hogg-Dubé syndrome was established on the basis of clinical evaluation and confirmed by genetic testing. Conclusions: The treatment of fibrofolliculomas in the course of Birt--Hogg-Dubé syndrome usually involves ablative laser therapy. The prognosis is good, although it depends on the patient's general health, especially the severity of respiratory failure and the presence of renal malignancy. Patients with Birt-Hogg-Dubé syndrome require regular follow-up for pulmonary changes and renal tumors.

No abstract

No abstract