Multi-camera BEV video-surveillance system for efficient monitoring of social distancing.

The current sanitary emergency situation caused by COVID-19 has increased the interest in controlling the flow of people in indoor infrastructures, to ensure compliance with the established security measures. Top view camera-based solutions have proven to be an effective and non-invasive approach to accomplish this task. Nevertheless, current solutions suffer from scalability problems: they cover limited range areas to avoid dealing with occlusions and only work with single camera scenarios. To overcome these problems, we present an efficient and scalable people flow monitoring system that relies on three main pillars: an optimized top view human detection neural network based on YOLO-V4, capable of working with data from cameras at different heights; a multi-camera 3D detection projection and fusion procedure, which uses the camera calibration parameters for an accurate real-world positioning; and a tracking algorithm which jointly processes the 3D detections coming from all the cameras, allowing the traceability of individuals across the entire infrastructure. The conducted experiments show that the proposed system generates robust performance indicators and that it is suitable for real-time applications to control sanitary measures in large infrastructures. Furthermore, the proposed projection approach achieves an average positioning error below 0.2 meters, with an improvement of more than 4 times compared to other methods.

Fractal characterization of retinal microvascular network morphology during diabetic retinopathy progression.

OBJECTIVE: The study aimed to characterize morphological changes of the retinal microvascular network during the progression of diabetic retinopathy. METHODS: Publicly available retinal images captured by a digital fundus camera from DIARETDB1 and STARE databases were used. The retinal microvessels were segmented using the automatic method, and vascular network morphology was analyzed by fractal parametrization such as box-counting dimension, lacunarity, and multifractals. RESULTS: The results of the analysis were affected by the ability of the segmentation method to include smaller vessels with more branching generations. In cases where the segmentation was more detailed and included a higher number of vessel branching generations, increased severity of diabetic retinopathy was associated with increased complexity of microvascular network as measured by box-counting and multifractal dimensions, and decreased gappiness of retinal microvascular network as measured by lacunarity parameter. This association was not observed if the segmentation method included only 3-4 vessel branching generations. CONCLUSIONS: Severe stages of diabetic retinopathy could be detected noninvasively by using high resolution fundus photography and automatic microvascular segmentation to the high number of branching generations, followed by fractal analysis parametrization. This approach could improve risk stratification for the development of microvascular complications, cardiovascular disease, and dementia in diabetes.

Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using Deep Convolutional Neural Networks.

Computerized Tomography Angiography (CTA) based follow-up of Abdominal Aortic Aneurysms (AAA) treated with Endovascular Aneurysm Repair (EVAR) is essential to evaluate the progress of the patient and detect complications. In this context, accurate quantification of post-operative thrombus volume is required. However, a proper evaluation is hindered by the lack of automatic, robust and reproducible thrombus segmentation algorithms. We propose a new fully automatic approach based on Deep Convolutional Neural Networks (DCNN) for robust and reproducible thrombus region of interest detection and subsequent fine thrombus segmentation. The DetecNet detection network is adapted to perform region of interest extraction from a complete CTA and a new segmentation network architecture, based on Fully Convolutional Networks and a Holistically-Nested Edge Detection Network, is presented. These networks are trained, validated and tested in 13 post-operative CTA volumes of different patients using a 4-fold cross-validation approach to provide more robustness to the results. Our pipeline achieves a Dice score of more than 82% for post-operative thrombus segmentation and provides a mean relative volume difference between ground truth and automatic segmentation that lays within the experienced human observer variance without the need of human intervention in most common cases.