A Comparison of Deep Neural Networks for Monocular Depth Map Estimation in Natural Environments Flying at Low Altitude.

Currently, the use of Unmanned Aerial Vehicles (UAVs) in natural and complex environments has been increasing, because they are appropriate and affordable solutions to support different tasks such as rescue, forestry, and agriculture by collecting and analyzing high-resolution monocular images. Autonomous navigation at low altitudes is an important area of research, as it would allow monitoring parts of the crop that are occluded by their foliage or by other plants. This task is difficult due to the large number of obstacles that might be encountered in the drone's path. The generation of high-quality depth maps is an alternative for providing real-time obstacle detection and collision avoidance for autonomous UAVs. In this paper, we present a comparative analysis of four supervised learning deep neural networks and a combination of two for monocular depth map estimation considering images captured at low altitudes in simulated natural environments. Our results show that the Boosting Monocular network is the best performing in terms of depth map accuracy because of its capability to process the same image at different scales to avoid loss of fine details.

Knowledge, attitudes and practices of parents towards antibiotic use in rural communities in Peru: a cross-sectional multicentre study.

BACKGROUND: The inappropriate use of antibiotics significantly contributes to the development of antibiotic resistance. There is limited information about the use of antibiotics among parents from rural areas in Peru. This study aimed to describe the knowledge, attitudes and practices towards antibiotics among parents of children < 5 years of age from rural communities in Peru; to explore the association between knowledge and attitudes towards antibiotics and to explore determinants of low knowledge and self-medicating his/her child with antibiotics. METHODS: Cross-sectional study in six rural primary health centres in Peru using a self-administered survey. Crude and adjusted Prevalence Ratios (PR), and 95% Confidence Intervals (95% CI) were calculated to explore determinants of low knowledge and of having self-medicated his/her child with antibiotics. Linear regression was used to explore the association between knowledge and attitudes. RESULTS: A total of 231 parents were included. The largest gap in knowledge was among 183 parents (79%) who did not know that antibiotics cannot cure viral infections. The largest gap in attitudes was among 185 participants (80%) that did not disagree with "If I want my child to receive antibiotics, I would not be satisfied if the doctor refuses to prescribe them". More than half of parents (n = 120, 52%) reported having self-medicated his/her child with antibiotics. A positive correlation was found between knowledge and attitudes (Coefficient 0.53, 95% CI 0.38-0.68) after adjusting for the age and the education of the parent. Parents who were < 20 years old were more likely to have low knowledge about antibiotics (crude PR 2.39, 95% CI 1.32-4.34) compared to those aged > 40 years. Parents who had self-medicated his/her child with antibiotics (n = 120, 52%) were more likely to have purchased antibiotics without prescription (aPR 2.70, 95% CI 1.74-4.19) and to have received antibiotics after the recommendation of a pharmacist (aPR 1.79, 95% CI 1.13-2.82). CONCLUSIONS: Knowledge about antibiotics among parents from rural settings in Peru is limited and highlights the need for educational interventions. Public health policies to limit the acquisition of antibiotics without prescription should be implemented.

Driving Maximal Frequency Content and Natural Slopes Sharpening for Image Amplification with High Scale Factor.

BACKGROUND: In this paper, a method for adaptive Pure Interpolation (PI) in the frequency domain, with gradient auto-regularization, is proposed. METHODS: The input image is transformed into the frequency domain and convolved with the Fourier Transform (FT) of a 2D sampling array (interpolation kernel) of initial size L × M. The Inverse Fourier Transform (IFT) is applied to the output coefficients and the edges are detected and counted. To get a denser kernel, the sampling array is interpolated in the frequency domain and convolved again with the transform coefficients of the original image of low resolution and transformed back into the spatial domain. The process is repeated until a maximum number of edges is reached in the output image, indicating that a locally optimal magnification factor has been attained. Finally, a maximum ascend-descend gradient auto-regularization method is designed and the edges are sharpened. RESULTS: For the gradient management, a new strategy is proposed, referred to as the Natural bi- Directional Gradient Field (NBGF). It uses a natural following of a pair of directional and orthogonal gradient fields. CONCLUSION: The proposed procedure is comparable to novel algorithms reported in the state of the art with good results for high scales of amplification.