Applications,databases and open computer vision research from drone videos and images: a survey

Analyzing videos and images captured by unmanned aerial vehicles or aerial drones is an emerging application attracting significant attention from researchers in various areas of computer vision. Currently, the major challenge is the development of autonomous operations to complete missions and replace human operators. In this paper, based on the type of analyzing videos and images captured by drones in computer vision, we have reviewed these applications by categorizing them into three groups. The first group is related to remote sensing with challenges such as camera calibration, image matching, and aerial triangulation. The second group is related to drone-autonomous navigation, in which computer vision methods are designed to explore challenges such as flight control, visual localization and mapping, and target tracking and obstacle detection. The third group is dedicated to using images and videos captured by drones in various applications, such as surveillance, agriculture and forestry, animal detection, disaster detection, and face recognition. Since most of the computer vision methods related to the three categories have been designed for real-world conditions, providing real conditions based on drones is impossible. We aim to explore papers that provide a database for these purposes. In the first two groups, some survey papers presented are current. However, the surveys have not been aimed at exploring any databases. This paper presents a complete review of databases in the first two groups and works that used the databases to apply their methods. Vision-based intelligent applications and their databases are explored in the third group, and we discuss open problems and avenues for future research.

     

Deploying deep learning approaches to left ventricular non-compaction measurement

The Journal of Supercomputing - Left ventricular non-compaction (LVNC) is a rare cardiomyopathy characterized by abnormal trabeculations in the left ventricle cavity. Although traditional computer...     

An XPS and reduction study of PrCoO3

The perovskite-type oxide PrCoO₃ has been studied by means of X-ray photoelectron spectroscopy (XPS), reduction in H₂ and X-ray diffraction. Two types of oxygen were detected: lattice oxygen (binding energy = 528.4 eV) and adsorbed oxygen (binding energy = 530.9 eV). The increase in relative intensity of the peak corresponding to the latter species after reduction of PrCo0₃ to 3e^– per molecule is assigned to the formation of hydroxyl groups. Temperature-programmed reduction (TPR) results showed two reduction steps: to 1 e^– per molecule (Co^3.1 Co²⁺) at 475 to 635 K, and to 3e^– per molecule (Co²¹ Co⁰) at 725 to 815 K. Reduction in the first and second steps occurs according to the contracting sphere model and the nucleation mechanism, respectively. Reduction of Co³⁺ to Co²⁺ causes minimal structural changes in the perovskite. Reduction to 3e^– per molecule yielded Pr₂O₃ and metallic cobalt. After this reduction and reoxidation at 973 K, the perovskite structure was regained. By XPS and TPR it was shown that PrCo0₃ is more easily reducible than LaCo0₃. It is concluded that the cation in the A position of the structure plays a significant role in the bulk and surface properties of LnCo0₃ (Ln, lanthanide elements) oxides.     

Assessment of the environmental quality of two urbanized lotic systems using multiple indicators

Urbanization impacts ecosystems through loss and fragmentation of habitat, loss of diversity, increase in runoff, and contaminant discharges, and the invasion of exotic species. Potrero de los Funes Village (San Luis, Argentina) is experiencing not only a population increase during summer months due to tourism but also an accelerated growth of its permanent population. In order to evaluate the potential effects of urbanization, the environmental quality of Potrero de los Funes River and Las Chacras Stream was assessed, using physical–chemical and biological indicators. Macroinvertebrates, through the application of the Biotic Index for San Luis Sierras (BISLS), anuran amphibian richness and relative abundance, and riparian vegetation were used as bioindicators. While the Simplified Index of Water Quality (SIWQ) was used to characterize the physical–chemical quality of water at each site. SIWQ and BISLS scores were significantly different between sites (F_7,28 = 9.88, p < .001 and F_7,28 = 24.18, p < .001, respectively). SIWQ was significantly correlated with BISLS (Spearman correlation coefficient = 0.8, p < .001). Four anuran species were registered along Potrero River, with no significant differences in the intensity of vocalizations between sites. No species were detected in Las Chacras Stream. Average total plant species richness, exotic plants richness, and vegetation cover were higher at the most impaired system, Las Chacras Stream. The principal component analysis showed that the first two principal components (PCs) explained 76.3% of the total variance. PC1, with strong loadings of SIWQ, BISLS, and amphibian richness, was principally driven by chemical water quality and biological conditions. PC2 was mainly determined by plant richness. The chemical and biological water quality of Potrero and Las Chacras is somewhat impaired, being the upper Las Chacras Stream the most compromised area. This study provides information that will certainly be used to manage future impacts of urbanization on aquatic resources.     

A 2D algorithm with asymmetric workload for the UPC conjugate gradient method

This paper examines four different strategies, each one with its own data distribution, for implementing the parallel conjugate gradient (CG) method and how they impact communication and overall performance. Firstly, typical 1D and 2D distributions of the matrix involved in CG computations are considered. Then, a new 2D version of the CG method with asymmetric workload, based on leaving some threads idle during part of the computation to reduce communication, is proposed. The four strategies are independent of sparse storage schemes and are implemented using Unified Parallel C (UPC), a Partitioned Global Address Space (PGAS) language. The strategies are evaluated on two different platforms through a set of matrices that exhibit distinct sparse patterns, demonstrating that our asymmetric proposal outperforms the others except for one matrix on one platform.     

Efficient mining of discriminative co-clusters from gene expression data

Discriminative models are used to analyze the differences between two classes and to identify class-specific patterns. Most of the existing discriminative models depend on using the entire feature space to compute the discriminative patterns for each class. Co-clustering has been proposed to capture the patterns that are correlated in a subset of features, but it cannot handle discriminative patterns in labeled datasets. In certain biological applications such as gene expression analysis, it is critical to consider the discriminative patterns that are correlated only in a subset of the feature space. The objective of this paper is twofold: first, it presents an algorithm to efficiently find arbitrarily positioned co-clusters from complex data. Second, it extends this co-clustering algorithm to discover discriminative co-clusters by incorporating the class information into the co-cluster search process. In addition, we also characterize the discriminative co-clusters and propose three novel measures that can be used to evaluate the performance of any discriminative subspace pattern-mining algorithm. We evaluated the proposed algorithms on several synthetic and real gene expression datasets, and our experimental results showed that the proposed algorithms outperformed several existing algorithms available in the literature.     

Chattering-Free Sliding Mode Altitude Control for a Quad-Rotor Aircraft: Real-Time Application

Nowadays, the chattering problem in sliding mode control is one of the most important points to consider in real-time applications. To address this problem, a real-time robust altitude control scheme is proposed for the efficient performance of a Quad-rotor aircraft system using a continuous sliding mode control. The sensing of altitude measurement sensing is performed by a pressure sensor in order to obtain a robust altitude control of the vehicle in hovering mode both indoor and outdoor. The altitude measurement has the advantage of introducing this state information directly in the closed loop control which should be very useful for achieving robust stabilization of the altitude control. Accordingly, we propose a sliding mode control strategy without chattering. The sliding mode control proposed removes the chattering phenomenon by replacing a sign function with a high-slope saturation function. The control algorithm is derived from the Lyapunov stability theorem. Moreover, we have assumed that the actuators are able to respond quickly and accurately and we have not enforced limits on the control signals for a real-time application. Finally, to verify the satisfactory performance of proposed nonlinear control law, several simulations and experimental results of the Chattering-free sliding mode control for the Quad-rotor aircraft in the presence of bounded disturbances are presented.     

Preconditioning the solution of the time-dependent neutron diffusion equation by recycling Krylov subspaces

Spectral preconditioners are based on the fact that the convergence rate of the Krylov subspace methods is improved if the eigenvalues of the smallest magnitude of the system matrix are ‘removed’. In this paper, two preconditioning strategies are studied to solve a set of linear systems associated with the numerical integration of the time-dependent neutron diffusion equation. Both strategies can be implemented using the matrix–vector product as the main operation and succeed at reducing the total number of iterations needed to solve the set of systems.     

Influence of maize kernel hardness on flour hydration and cooking properties

Knowledge of the association between cooking properties and endosperm hardness may help nutritionist and processors to select raw materials for preparing maize based food products, particularly those eaten as cooked dispersions. Seven commercial maize cultivars differing in hardness were selected to evaluate endosperm hardness on the kernels and some characteristics such as composition and hydration and cooking properties on the grits obtained from those maizes. Results show that the differences in endosperm hardness (directly related to grits protein content) can explain the differences in swelling and amylographic consistencies values. Cultivars with the hardest endosperm show the lowest values at high temperature. They also show the lowest amylographic consistencies. On the other hand softer endosperms present the highest swelling power and the highest amylographic consistencies. These differences are attributed to the restriction for starch swelling caused by the protein matrix. Endosperm hardness measurements and swelling power at 95 degrees C, can be useful to select cultivars that are going to be used to prepare maize based foods like atoles, polenta, etc.