Learning based approaches for depth perception are limited by the availability of clean training data. This has led to the utilization of view synthesis as an indirect objective for learning depth estimation using efficient data acquisition procedures. Nonetheless, most research focuses on pinhole based monocular vision, with scarce works presenting results for omnidirectional input. In this work, we explore spherical view synthesis for learning monocular 360 o depth in a self-supervised manner and demonstrate its feasibility. Under a purely geometrically derived formulation we present results for horizontal and vertical baselines, as well as for the trinocular case. Further, we show how to better exploit the expressiveness of traditional CNNs when applied to the equirectangular domain in an efficient manner. Finally, given the availability of ground truth depth data, our work is uniquely positioned to compare view synthesis against direct supervision in a consistent and fair manner. The results indicate that alternative research directions might be better suited to enable higher quality depth perception. Our data, models and code are publicly available at https
The analysis of multimodal data collected by innovative imaging sensors, Internet of Things devices, and user interactions can provide smart and automatic distant monitoring of Parkinson's and Alzheimer's patients and reveal valuable insights for early detection and/or prevention of events related to their health. This article describes a novel system that involves data capturing and multimodal fusion to extract relevant features, analyze data, and provide useful recommendations. The system gathers signals from diverse sources in health monitoring environments, understands the user behavior and context, and triggers proper actions for improving the patient's quality of life. The system offers a multimodal, multi-patient, versatile approach not present in current developments. It also offers comparable or improved results for detection of abnormal behavior in daily motion. The system was implemented and tested during 10 weeks in real environments involving 18 patients.
Indoor/outdoor localization topic has gained a significant research interest due to the wide range of potential applications. Commonly, the Fingerprinting methods for spatial characterization of the environments monitored are employed in deterministic/statistical estimation. However, there are Fingerprint parameters that are generally neglected and can seriously affect the performance yielding to low accurate location. Nowadays, machine and deep learning (DL) methods are employed in this topic due to its ability to approximate complex non-linear models being capable of mitigating the undesirable effects of wireless propagation. In this paper, a complete overview of most influential aspects in Fingerprinting and indoor tracking methods is presented. Furthermore, a novel multi-modal complete tracking system, called SWiBluX, based on statistic and DL techniques is presented. The system relies on relevant feature extraction from available data sources to estimate user's/target indoor position using a multi-phase statistical Fingerprint and DL disruptive approach. In addition, a Gaussian outlier filter is applied to the position estimation model output to further reduce the error in the estimation. The set of experiments performed shows that Fingerprint positioning accuracy estimation can be improved up to 45% resulting in a final estimation error that outperforms related literature.
SUMMARY:The Alborán Sea is a hydrographically complex and variable area in which wind-driven coastal upwelling occurs. Its most abundant small pelagic resource is the sardine (Sardina pilchardus), which is subject to major interannual oscillations. Postflexion stages of sardine larvae were sampled in their main nursery grounds in the north Alborán Sea, and sardine juveniles were sampled periodically throughout the recruitment season. Daily growth analysis was used to identify periods favourable for larval survival and to assess the evolution of daily increment widths during the first months of life. The results showed that juveniles born later in the spawning season grew relatively faster than those born earlier. Two main growth phases were observed in juveniles: an initial one in which daily increment widths increased progressively, and a second one in which widths fluctuated, showing a decreasing trend. The beginning of the second phase was almost synchronous among different sub-cohorts, suggesting that it was triggered by environmental factors. The estimated mean daily growth rates during the larval phase were higher in surviving juveniles than in postflexion larvae born in the same month, supporting the "bigger is better" hypothesis in relation to larval survival. The influence of the environmental regime on growth was explored, and the evolution of a growth-related index, derived from otolith increment width variability, was compared with a single environmental descriptor, a "wind index" based on wind stress and direction. This analysis suggested that larval survival and larval and juvenile growth rates showed a positive correlation with NW component winds, associated with upwelling events on the continental shelf and calm sea weather conditions in the inshore nursery grounds. Conversely, Levantine and southern wind periods, which interrupt the upwelling and create rough seas in the inshore bays, lead to a decrease in growth rates in juveniles and low larval survival.Keywords: Sardina pilchardus, daily growth, wind stress, recruitment, Alborán Sea. RESUMEN: CRECIMIENTO DIARIO EN LARVAS EN POSTFLEXION Y JUEVENILES DE SARDINA (SARDINA PILCHARDUS WALB.) DEL MARDE ALBORÁN: INFLUENCIA DEL VIENTO. -El mar de Alborán es una zona hidrográficamente compleja y variable, en la que se producen fenómenos de afloramiento costero inducidos por vientos. Su recurso más abundante entre los pequeños pelágicos es la sardina (Sardina pilchardus), que está sujeto a importantes fluctuaciones interanuales. Se muestrearon estadios larvarios avanzados (larvas en estadio de postflexión del urostilo), en sus principales áreas de reclutamiento del norte del mar de Alborán. Los juveniles de sardina fueron muestreados periódicamente a lo largo de la temporada de reclutamiento. Estudios de crecimiento diario permitieron identificar periodos de alta supervivencia larvaria, así como analizar la evolución de la anchura de los microincrementos durante los primeros meses de vida, revelando que los juveniles nacidos más tarde en la época de pue...
Abstract-Indoor Localization and Tracking have become an attractive research topic because of the wide range of potential applications. These applications are highly demanding in terms of estimation accuracy and rise a challenge due to the complexity of the scenarios modeled. Approaches for these topics are mainly based on either deterministic or probabilistic methods such as Kalman or Particles Filter. These techniques are improved by fusing information from different sources such as wireless or optical sensors. In this paper, a novel MUlti-sensor Fusion using Adaptive Fingerprint (MUFAF) Algorithm is presented and compared with several multi-sensor indoor localization and tracking methods. MUFAF is mainly divided in four phases: first, a Target Position Estimation (TPE) process is performed by every sensor; second, a Target Tracking Process (TTP) stage; third, a Multi-Sensor fusion (MMF) combines the sensor information and finally, an Adaptive Fingerprint Update (AFU) is applied. For TPE, a complete environment characterization in combination with a Kernel Density Estimation (KDE) technique are employed to obtain object position. A Modified Kalman Filter (MKF) is applied to TPE output in order to smooth target routes and avoid outliers effect. Moreover, two fusion methods are described in this work: Track-To-Track Fusion (TTTF) and Kalman Sensor Group Fusion (KSGF). Finally, AFU will endow the algorithm with responsiveness to environment changes by using Kriging interpolation to update the scenario fingerprint. MUFAF is implemented and compared in a testbed showing that it provides a significant improvement in estimation accuracy and long-term adaptivity to condition changes.
The focus of research into 5G networks to date has been largely on the required advances in network architectures, technologies, and infrastructures. Less effort has been put on the applications and services that will make use of and exploit the flexibility of 5G networks built upon the concept of software-defined networking (SDN) and network function virtualization (NFV). Media-based applications are amongst the most demanding services, requiring large bandwidths for high Manuscript
Video survey techniques are now commonly used to estimate animal abundance under the assumption that estimates relate to true abundance, a key property needed to make video a valid survey tool. Using the spiny lobster Palinurus elephas as our model organism, we evaluate the effectiveness of baited underwater video (BUV) for estimating abundance in areas with widely different population density. We test three BUV abundance metrics and compare the results with an independently obtained abundance index from trammel-net surveys (Trammel). Video metrics used to estimate relative abundance include a value for total number of individuals per recording (TotN), the traditional maximum number of fish observed in a single video frame (MaxN), and the recently suggested alternative, the average of the mean MaxN from 5-minute periods throughout the duration of the recording (MeanN). This is the first video study of a wild population to include an estimate for TotN. Comparison of TotN with the other two BUV relative abundance metrics demonstrates that both of the latter lack resolution at high population densities. In spite of this, the three BUV metrics tested, as well as the independent estimate Trammel, distinguished high density areas from low density areas. Thus they could all be used to identify areas of differing population density, but MaxN and MeanN would not be appropriate metrics for studies aimed at documenting increases in abundance, such as those conducted to assess marine protected area effectiveness, as they are prone to sampling saturation. We also demonstrate that time of first arrival (T1) is highly correlated with all of the abundance indices; suggesting T1 may be a potentially useful index of abundance. However, these relationships require further investigation as our data suggests T1 may not adequately represent lobster abundance in areas of high density.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.