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.

     

Structural health monitoring of railway tracks using IoT-based multi-robot system

Neural Computing and Applications - A multi-robot-based fault detection system for railway tracks is proposed to eliminate manual human visual inspection. A hardware prototype is designed to...     

Location allocation modeling for healthcare facility planning in Malaysia

Malaysia has seen tremendous growth in the standard of living and household per capita income. The demand for a more systematic and efficient planning has become increasingly more important, one of the keys to achieving a high standard in healthcare. In this paper, a Maximal Covering Location Problem (MCLP) is used to study the healthcare facilities of one of the districts in Malaysia. We address the limited capacity of the facilities and the problem is formulated as Capacitated MCLP (CMCLP). We propose a new solution approach based on genetic algorithm to examine the percentage of coverage of the existing facilities within the allowable distance specified/targeted by Malaysian government. The algorithm was shown to generate good results when compared to results obtained using CPLEX version 12.2 on a medium size problem consisting of 179 nodes network. The algorithm was extended to solve larger network consisting of 809 nodes where CPLEX failed to produce non-trivial solutions. We show that the proposed solution approach produces significant results in determining good locations for the facility such that the population coverage is maximized.     

Implementation of genetic algorithm in an embedded microcontroller-based polarization control system

Implementation of genetic algorithm in a PIC32MX microcontroller-based polarization control system is proposed and demonstrated. The controller measures the signal intensity that is used to estimate the genetic value. This process is controlled by the genetic algorithm rather than referring to the Look-Up-Table as implemented in existing solutions. To reach optimum performance, the code is optimized by using the best genetic parameters so that the fastest execution time can be achieved. An ability of genetic algorithm to work efficiently in polarization control system possesses many advantages including easy code construction, low memory consumption and fast control speed. Genetic algorithm is intelligent enough to be used for endless polarization stabilization and in the worst case, able to stabilize the polarization changes in 300 μs. In the best case the response time can reach 17 μs.     

Feature Selection and Extraction Methods for Power Systems Transient Stability Assessment Employing Computational Intelligence Techniques

One of the important aspects in achieving better performance for transient stability assessment (TSA) of power systems employing computational intelligence (CI) techniques is by incorporating feature reduction techniques. For small power system the number of features may be small but when larger systems are considered the number of features increased as the size of the systems increases. Apart from employing faster CI techniques to achieve faster and accurate TSA of power system, feature reduction techniques are needed in reducing the input features while preserving the needed information so as to make faster training of the CI technique. This paper presents feature reductions techniques used, namely correlation analysis and principle component analysis, in reducing number of input features presented to two CI techniques for TSA, namely probabilistic neural network (PNN) and least squares support vector machines (LS-SVM). The proposed feature reduction techniques are implemented and tested on the IEEE 39-bus test system and 87-bus Malaysia’s power system. Numerical results are presented to demonstrate the performance of the feature reduction techniques and its effects on the accuracies and time taken for training the two CI techniques.     

Deep features-based speech emotion recognition for smart affective services

Emotion recognition from speech signals is an interesting research with several applications like smart healthcare, autonomous voice response systems, assessing situational seriousness by caller affective state analysis in emergency centers, and other smart affective services. In this paper, we present a study of speech emotion recognition based on the features extracted from spectrograms using a deep convolutional neural network (CNN) with rectangular kernels. Typically, CNNs have square shaped kernels and pooling operators at various layers, which are suited for 2D image data. However, in case of spectrograms, the information is encoded in a slightly different manner. Time is represented along the x-axis and y-axis shows frequency of the speech signal, whereas, the amplitude is indicated by the intensity value in the spectrogram at a particular position. To analyze speech through spectrograms, we propose rectangular kernels of varying shapes and sizes, along with max pooling in rectangular neighborhoods, to extract discriminative features. The proposed scheme effectively learns discriminative features from speech spectrograms and performs better than many state-of-the-art techniques when evaluated its performance on Emo-DB and Korean speech dataset.

     

An effective back‐off selection technique for reliable beacon reception in VANETs

In safety‐critical scenarios, reliable reception of beacons transmitted by a subject vehicle is critical to avoid vehicle collision. According to the employed contention window sizes in IEEE 802.11p, beacons are transmitted with a small contention window size. As a result, multiple vehicles contend for the shared channel access by selecting the same back‐off slot. This is a perfect recipe for synchronous collisions wherein reliable beacon delivery cannot be guaranteed for any vehicle. We consider the problem of selecting the back‐off slots from the current contention window to provide reliable delivery of beacons transmitted by a subject vehicle to its neighbors. Given a safety scenario, we propose a Pseudo‐Random Number Generator (PRNG)‐inspired back‐off selection (PBS) technique. The proposed technique works on the hypothesis that synchronous collisions of beacons transmitted by a subject vehicle can be reduced if all its neighbors select different back‐off slots (ie, not the back‐off slot selected by the subject vehicle). The discrete‐event simulations demonstrate that PBS can increase the overall message reception from a subject vehicle, in comparison with the uniform random probability back‐off selection in IEEE 802.11p.     

The development of spectral indices for early detection of Ganoderma disease in oil palm seedlings

Field spectroscopy is a rapid and non-destructive analytical technique that may be used for assessing plant stress and disease. The objective of this study was to develop spectral indices for detection of Ganoderma disease in oil palm seedlings. The reflectance spectra of oil palm seedlings from three levels of Ganoderma disease severity were acquired using a spectroradiometer. Denoizing and data transformation using first derivative analysis was conducted on the original reflectance spectra. Then, comparative statistical analysis was used to select significant wavelength from transformed data. Wavelength pairs of spectral indices were selected using optimum index factor. The spectral indices were produced using the wavelength ratios and a modified simple ratio method. The relationship analysis between spectral indices and total leaf chlorophyll (TLC) was conducted using regression technique. The results suggested that six spectral indices are suitable for the early detection of Ganoderma disease in oil palm seedlings. Final results after regression with TLC showed that Ratio 3 is the best spectral index for the early detection of Ganoderma infection in oil palm seedlings. For future works, this can be used for the development of robust spectral indices for Ganoderma disease detection in young and mature oil palm using airborne hyperspectral imaging.     

Speeding up dynamic time warping distance for sparse time series data

Dynamic time warping (DTW) distance has been effectively used in mining time series data in a multitude of domains. However, in its original formulation DTW is extremely inefficient in comparing long sparse time series, containing mostly zeros and some unevenly spaced nonzero observations. Original DTW distance does not take advantage of this sparsity, leading to redundant calculations and a prohibitively large computational cost for long time series. We derive a new time warping similarity measure (AWarp) for sparse time series that works on the run-length encoded representation of sparse time series. The complexity of AWarp is quadratic on the number of observations as opposed to the range of time of the time series. Therefore, AWarp can be several orders of magnitude faster than DTW on sparse time series. AWarp is exact for binary-valued time series and a close approximation of the original DTW distance for any-valued series. We discuss useful variants of AWarp: bounded (both upper and lower), constrained, and multidimensional. We show applications of AWarp to three data mining tasks including clustering, classification, and outlier detection, which are otherwise not feasible using classic DTW, while producing equivalent results. Potential areas of application include bot detection, human activity classification, search trend analysis, seismic analysis, and unusual review pattern mining.     

Study of Half-Metallic Ferromagnetism in Be0.75Ti0.25Y (Y = S,Se, and Te) Using Ab Initio Calculations: Potential Candidate for Spintronic Devices

The structural, elastic, electronic, and magnetic properties of Be_0.75Ti_0.25Y (Y = S, Se, and Te) have been investigated to understand their potential applications in spintonic devices. Crystals of BeS, BeSe, and BeTe, individually doped with Ti with a dopant concentration of x = 0.25, have been evaluated by using full-potential linearized augmented plane-wave plus local orbital method within the framework of density functional theory. We employed the Wu–Cohen generalized gradient approximation for optimizing the crystal structure and evaluating elastic properties. In order improve bandgap values and optical parameters, the modified Becke and Johnson (mBJ) potential has been employed. The theoretical investigation of band structure and density of states confirms the half-metallic ferromagnetic nature of these compounds. The elastic constants are calculated by the charpin method which shows that the compounds under consideration are brittle and anisotropic. Moreover, it is noted that tetrahedral crystal field splits the 3d state of Ti into triple degenerate t_2g and double degenerate e_g states. The exchange splitting energies Δ _x (d) and Δ _x (pd) and exchange constants (N ₀ α) and (N ₀ β) are predicted from triple degenerate t_2g states, and negative values of N ₀ β justify that the nature of effective potential is more attractive in spin down case rather than that in the spin up case. We also find the crystal field splitting (ΔE _crystal = E _t2g?E _eg) energy and reduction of the local magnetic moment of Ti from its free space charge value and creation of small local magnetic moments on the non-magnetic Be, S, Se, and Te sites by p–d hybridization.