RESUMEN

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.

RESUMEN

Tremendous advances in advanced driver assistance systems (ADAS) have been possible thanks to the emergence of deep neural networks (DNN) and Big Data (BD) technologies. Huge volumes of data can be managed and consumed as training material to create DNN models which feed functions such as lane keeping systems (LKS), automated emergency braking (AEB), lane change assistance (LCA), etc. In the ADAS/AD domain, these advances are only possible thanks to the creation and publication of large and complex datasets, which can be used by the scientific community to benchmark and leverage research and development activities. In particular, multi-modal datasets have the potential to feed DNN that fuse information from different sensors or input modalities, producing optimised models that exploit modality redundancy, correlation, complementariness and association. Creating such datasets pose a scientific and engineering challenge. The BD dimensions to cover are volume (large datasets), variety (wide range of scenarios and context), veracity (data labels are verified), visualization (data can be interpreted) and value (data is useful). In this paper, we explore the requirements and technical approach to build a multi-sensor, multi-modal dataset for video-based applications in the ADAS/AD domain. The Driver Monitoring Dataset (DMD) was created and partially released to foster research and development on driver monitoring systems (DMS), as it is a particular sub-case which receives less attention than exterior perception. Details on the preparation, construction, post-processing, labelling and publication of the dataset are presented in this paper, along with the announcement of a subsequent release of DMD material publicly available for the community.

Asunto(s)

RESUMEN

The World Health Organization (WHO) recommends countries introduce new anti-TB drugs in the treatment of multidrug-resistant tuberculosis. The aim of the study is to prospectively evaluate the effectiveness of bedaquiline (and/or delamanid)- containing regimens in a large cohort of consecutive TB patients treated globally. This observational, prospective study is based on data collected and provided by Global Tuberculosis Network (GTN) centres and analysed twice a year. All consecutive patients (including children/adolescents) treated with bedaquiline and/or delamanid were enrolled, and managed according to WHO and national guidelines. Overall, 52 centres from 29 countries/regions in all continents reported 883 patients as of January 31st 2021, 24/29 countries/regions providing data on 100% of their consecutive patients (10-80% in the remaining 5 countries). The drug-resistance pattern of the patients was severe (>30% with extensively drug-resistant -TB; median number of resistant drugs 5 (3-7) in the overall cohort and 6 (4-8) among patients with a final outcome). For the patients with a final outcome (477/883, 54.0%) the median (IQR) number of months of anti-TB treatment was 18 (13-23) (in days 553 (385-678)). The proportion of patients achieving sputum smear and culture conversion ranged from 93.4% and 92.8% respectively (whole cohort) to 89.3% and 88.8% respectively (patients with a final outcome), a median (IQR) time to sputum smear and culture conversion of 58 (30-90) days for the whole cohort and 60 (30-100) for patients with a final outcome and, respectively, of 55 (30-90) and 60 (30-90) days for culture conversion. Of 383 patients treated with bedaquiline but not delamanid, 284 (74.2%) achieved treatment success, while 25 (6.5%) died, 11 (2.9%) failed and 63 (16.5%) were lost to follow-up.

Asunto(s)

RESUMEN

Objetivo: Determinar los factores asociados al incremento de la Tuberculosis MDR en Hospital Guillermo Almenara Irigoyen en el año 2011. Material y Métodos: estudio descriptivo, retrospectivo, transversal, observacional. Diseño de Investigación: Diseño de tipo No Experimental. Muestra de Estudio: Cada paciente con TBC MDR atendido en el Consultorio externo de PCT del Servicio de Neumología del Hospital Guillermo Almenara Irigoyen en el 2011. Resultados: Se encontró 99 pacientes TBC MDR con PS de las historias clínicas revisadas el promedio de edad fue de 37.7 años; 63.7 por ciento (63/99) fueron hombres y 36.3 por ciento (36/99) mujeres; procedencia de mayor frecuencia San Juan de Lurigancho, Santa Anita y La Victoria; 49.5 por ciento (49/99) fueron casados; 32.4 por ciento (32/99) fueron solteros; 52.5 por ciento (52/99) estaba trabajando, 37.4 por ciento (37/99) desempleados y 10.1 por ciento (5/99) estudiantes; 52.5 por ciento (52/99) tenían secundaria completa, 29.2 por ciento (29/99) tenían estudios superior; 18.2 por ciento (18/99) tuvieron un tratamiento anterior, 52.5 por ciento (52/99) tuvieron 2 tratamientos anteriores; 12.1 por ciento (12/99) tuvieron DM; 2 por ciento (2/99) tuvieron convulsiones; 16.1 por ciento (16/99) gastritis; 6 por ciento (6/99) tuvieron Hepatitis y Cirrosis; 28.2 por ciento (28/99) tuvieron Insuficiencia Renal Crónica; 4 por ciento (4/99) usaron corticoterapia; 2 por ciento (2/99) tuvieron VIH; 4 por ciento (4/99) consumieron tabaco; 2 por ciento (2/99) Consumo de droga; 14.1 por ciento (14/99) Consumieron alcohol; 2 por ciento (2/99) fueron Trabajador o Estudiante de Salud; 2 por ciento (2/99) vivió en una comunidad de drogadictos; 23.2 por ciento (23/99) tuvieron contacto TBC sensible; 21.2 por ciento (21/99) tuvieron Contacto con paciente TBC MDR; 69.6 por ciento (69/99) tercio superior pulmonar comprometido; 38,3 por ciento (38/99) tuvieron un infiltrado alveolar más una caverna; 36.3 por ciento (36/99) solo infiltrado...

Asunto(s)