Sensor Fusion of a Mobile Device to Control and Acquire Videos or Images of Coffee Branches and for Georeferencing Trees.

Smartphones show potential for controlling and monitoring variables in agriculture. Their processing capacity, instrumentation, connectivity, low cost, and accessibility allow farmers (among other users in rural areas) to operate them easily with applications adjusted to their specific needs. In this investigation, the integration of inertial sensors, a GPS, and a camera are presented for the monitoring of a coffee crop. An Android-based application was developed with two operating modes: (i) Navigation: for georeferencing trees, which can be as close as 0.5 m from each other; and (ii) Acquisition: control of video acquisition, based on the movement of the mobile device over a branch, and measurement of image quality, using clarity indexes to select the most appropriate frames for application in future processes. The integration of inertial sensors in navigation mode, shows a mean relative error of ±0.15 m, and total error ±5.15 m. In acquisition mode, the system correctly identifies the beginning and end of mobile phone movement in 99% of cases, and image quality is determined by means of a sharpness factor which measures blurriness. With the developed system, it will be possible to obtain georeferenced information about coffee trees, such as their production, nutritional state, and presence of plagues or diseases.

Quantitative parametric imaging by ultrasound computed tomography of trees under anisotropic conditions: Numerical case study.

A method for the reconstruction of 2D tomographic images adapted to wood was presented, aiming to perform a nondestructive evaluation of standing trees. The proposed method takes into account the orthotropy property of wood material, performing an iterative process that approximated the curved rays. A slowness function was defined for every cell and a nonlinear regression allowed the mapping of the inner elastic constants. Four numerical configurations were tested representing real cases usually found in standing tree monitoring. These specific configurations allowed this work to focus on the analysis of the effect of anisotropy on image reconstruction. The reconstructed images using the proposed method were compared with a straight-ray reconstruction method (filtered back projection algorithm), highlighting a more detailed identification and quantification of the inner state of the anisotropic structure of the trunk.

Effect of wood anisotropy in ultrasonic wave propagation: A ray-tracing approach.

Ultrasonic nondestructive imaging methods allow analyzing the inner structures of trees, without altering their condition. In this study, we are interested in evaluating the influence of anisotropy condition in the wood on the ultrasonic waves time-of-flight (TOF) estimation, by means of a raytracing approach. This technique is used particularly in the field of exploration seismography to simulate wavefronts in elastic media. Wood sections from two species were tested. Defects in the wood were simulated by drilling holes. Defects were tested in two positions, centric and eccentric, and three different defect diameters were used for each position. First, experiments with healthy wood showed that the orthotropic behavior resulted in curved rays from the transmitter to every receiver, compared to the straight-line paths for the isotropic case, considering that the radial direction presents a higher wave velocity. Defects inside the wood resulted in low velocity propagation areas, that modified the trajectories compared to the healthy case. Centric defects resulted in larger TOF variations than eccentric defects. A combination of centric position and bigger size corresponded to a higher probability of decay detection using a tomographic image. To increase the tomographic image quality, curved rays should be considered when performing the image reconstruction.

Gesture Classification Using LSTM Recurrent Neural Networks.

The classification of human hand gestures has gained widespread recognition as a natural and powerful way to interact intuitively and efficiently with computers. Specifically, this approach has facilitated the development of a number of important applications in the medical training field, specially as a way to objectively evaluate surgical tasks of novices compared to an expert surgeon. In this paper, 3D medical gestures, acquired by an instrumented laparoscopic forceps, were classified using Long Short Term Memory (LSTM) recurrent neural networks (RNN). Recognition results are based on gesture dynamics and a comparison of gesture trajectories between novices to an expert motion are presented. Using LSTM RNN, we were able to achieve a recognition rate of 99.1%.

Gesture segmentation and classification using affine speed and energy.

The characterization and analysis of hand gestures are challenging tasks with an important number of applications in human-computer interaction, machine vision and control, and medical gesture recognition. Specifically, several researchers have tried to develop objective evaluation methods of surgical skills for medical training. As a result, the adequate selection and extraction of similarities and differences between experts and novices have become an important challenge in this area. In particular, some of these works have shown that human movements performed during surgery can be described as a sequence of constant affine-speed trajectories. In this article, we will show that affine speed can be used to segment medical hand movements and present how the mechanical energy computed in the segment is analyzed to compare surgical skills. The position and orientation of the instrument end effectors are determined by six video photographic cameras. In addition, two laparoscopic instruments are capable of measuring simultaneously the forces and torques applied to the tool. Finally, we will report the results of these experiments and present a correlation between the mechanical energy values, dissipated during a procedure, and the surgical skills.

Accuracy of coded excitation methods for measuring the time of flight: Application to ultrasonic characterization of wood samples.

Ultrasound computed tomography (USCT) using the transmission mode is a way to detect and assess the extent of decay in wood structures. The resolution of the ultrasonic image is closely related to the different anatomical features of wood. The complexity of the wave propagation process generates complex signals consisting of several wave packets with different signatures. Wave paths, depth dependencies, wave velocities or attenuations are often difficult to interpret. For this kind of assessment, the focus is generally on signal pre-processing. Several approaches have been used so far including filtering, spectrum analysis and a method involving deconvolution using a characteristic transfer function of the experimental device. However, all these approaches may be too sophisticated and/or unstable. The alternative methods proposed in this work are based on coded excitation, which makes it possible to process both local and general information available such as frequency and time parameters. Coded excitation is based on the filtering of the transmitted signal using a suitable electric input signal. The aim of the present study was to compare two coded-excitation methods, a chirp- and a wavelet-coded excitation method, to determine the time of flight of the ultrasonic wave, and to investigate the feasibility, the robustness and the precision of the measurement of geometrical and acoustical properties in laboratory conditions. To obtain control experimental data, the two methods were compared with the conventional ultrasonic pulse method. Experiments were conducted on a polyurethane resin sample and two samples of different wood species using two 500 kHz-transducers. The relative errors in the measurement of thickness compared with the results of caliper measurements ranged from 0.13% minimum for the wavelet-coded excitation method to 2.3% maximum for the chirp-coded excitation method. For the relative errors in the measurement of ultrasonic wave velocity, the coded excitation methods showed differences ranging from 0.24% minimum for the wavelet-coded excitation method to 2.62% maximum for the chirp-coded excitation method. Methods based on coded excitation algorithms thus enable accurate measurements of thickness and ultrasonic wave velocity in samples of wood species.

Surgical gesture classification using Dynamic Time Warping and affine velocity.

Minimally Invasive Surgery (MIS) has become widespread as an important surgical technique due to its advantages related to pain relief and short recovery time periods. However, this approach implies the acquisition of special surgical skills, which represents a challenge in the objective assessment of surgical gestures. In this way, several studies shown that kinematics and kinetic analysis of hand movement is a valuable assessment tool of basic surgical skills in MIS. In addition, recent researches proved that human motion performed during surgery can be described as a sequence of constant affine velocity movements. In this paper, we present a novel method to classify gestures based on an affine velocity analysis of 3D motion and an implementation of the Dynamic Time Warping algorithm. In particular, affine velocity calculation correlates kinematics and geometrical variables such as curvature, torsion, and euclidean velocity, reducing the dimension of the conventional 3D problem. In this way, using the simplicity of dynamic time warping algorithm allows us to perform an accurate classification, easier to implement and understand. Experimental validation of the algorithm is presented based on the position and orientation data of a laparoscope instrument, determiMinimally Invasive Surgery (MIS) has become widespread as an important surgical technique due to its advantages related to pain relief and short recovery time periods. However, this approach implies the acquisition of special surgical skills, which represents a challenge in the objective assessment of surgical gestures. In this way, several studies shown that kinematics and kinetic analysis of hand movement is a valuable assessment tool of basic surgical skills in MIS. In addition, recent researches proved that human motion performed during surgery can be described as a sequence of constant affine velocity movements. In this paper, we present a novel method to classify gestures based on an affine velocity analysis of 3D motion and an implementation of the Dynamic Time Warping algorithm. In particular, affine velocity calculation correlates kinematics and geometrical variables such as curvature, torsion, and euclidean velocity, reducing the dimension of the conventional 3D problem. In this way, using the simplicity of dynamic time warping algorithm allows us to perform an accurate classification, easier to implement and understand. Experimental validation of the algorithm is presented based on the position and orientation data of a laparoscope instrument, determined by six cameras. Results show the advantages of the proposed method compared to conventional Multidimensional Dynamic Time Warping to classify surgical gestures in MIS.ned by six cameras. Results show the advantages of the proposed method compared to conventional Multidimensional Dynamic Time Warping to classify surgical gestures in MIS.

Automatic gesture analysis using constant affine velocity.

Hand human gesture recognition has been an important research topic widely studied around the world, as this field offers the ability to identify, recognize, and analyze human gestures in order to control devices or to interact with computer interfaces. In particular, in medical training, this approach is an important tool that can be used to obtain an objective evaluation of a procedure performance. In this paper, some obstetrical gestures, acquired by a forceps, were studied with the hypothesis that, as the scribbling and drawing movements, they obey the one-sixth power law, an empirical relationship which connects path curvature, torsion, and euclidean velocity. Our results show that obstetrical gestures have a constant affine velocity, which is different for each type of gesture and based on this idea this quantity is proposed as an appropriate classification feature in the hand human gesture recognition field.

An arc-length warping algorithm for gesture recognition using quaternion representation.

This paper presents a new algorithm, called Dynamic Arc-Length Warping algorithm (DALW) for hand gesture recognition based on the orientation data. In this algorithm, after calculating the quaternion for each orientation measurement, we use DALW algorithm to obtain a similarity measure between different trajectories. We present the benefits of using quaternion alongside the implementation of Dynamic Arc Length Warping to present an optimized tool for gesture recognition.We show the advantages of this approach compared with other techniques. This tool can be used to distinguish similar and different gestures. An experimental validation is carried out to classify a series of simple human gestures.