Daniel Asmar

American University of Beirut | AUB · Department of Mechanical Engineering

The recent success of hybrid methods in monocular odometry has led to many attempts to generalize the performance gains to hybrid monocular SLAM. However, most attempts fall short in several respects, with the most prominent issue being the need for two different map representations (local and global maps), with each requiring different, computatio...

Photometric calibration is essential to many computer vision applications. One of its key benefits is enhancing the performance of Visual SLAM, especially when it depends on a direct method for tracking, such as the standard KLT algorithm. Another advantage could be in retrieving the sensor irradiance values from measured intensities, as a pre-proc...

In this work, an Electrical Capacitance Tomography (ECT) coplanar sensor design is used to detect the presence of oil beneath ice, alongside estimating its depth and thickness. Oil spill response in the arctic region requires a non-intrusive and efficient method to detect and measure oil under ice, and this is where the role of coplanar ECT comes i...

The superimposition of sequential radiographs of the head is commonly used to determine the amount and direction of orthodontic tooth movement. A harmless method includes the timely unlimited superimposition on the relatively stable palatal rugae, but the method is performed manually and, if automated, relies on the best fit of surfaces, not only r...

This paper proposes a new framework for the production and development of immersive and playful technologies in cultural heritage in which different stakeholders such as users and local communities are involved early on in the product development chain. We believe that an early stage of co-creation in the design process produces a clear understandi...

Site inspection is a notably tedious, time-consuming, and error-prone process when carried out manually by construction inspectors. One portion of site inspection is the generation and comparison of as-built drawings to their as-planned counterparts to ensure conformity. Current as-built evaluation systems rely on manually positioning and transport...

In this paper, we propose and validate a Joint-Initiative Supervised Autonomy (JISA) framework for Human-Robot Interaction (HRI). Through JISA, a robot maintains a measure of its self-confidence (SC) while performing a task, and only prompts the human supervisor for help when its SC drops. At the same time, a human supervisor can intervene in the t...

The complete report can be obtained from: https://www.bsee.gov/sites/bsee.gov/files/research-reports//1103aa.pdf. This project developed oil thickness sensors to quantify the thickness of oil floating on water. Two unique sensors were developed to measure oil thickness greater than 3 mm in real time. The first is a hand held unit that can be deploy...

Highlights A deep learning architecture, which relies on multi-modal imagery from the RGB and thermal spectra, is proposed to detect PPM nests via aerial drones. A GPS-based computation method is implemented to geo-tag the position of the detected nests in the drone’s perimeter. A Kalman filter is utilized as a nest tracker to avoid reporting back...

During oil spills, an accurate estimate of the oil-slick thickness at different locations within the affected area is an essential requirement to estimate the spilled amount, assess and enhance the performance of skimmers, and decide on type of remediation techniques to be applied such as in situ burning. This requirement cannot be satisfied usin...

In this paper, we propose and validate a Joint-Initiative Supervised Autonomy (JISA) framework for Human-Robot Interaction (HRI), in which a robot maintains a measure of its self-confidence (SC) while performing a task, and only prompts the human supervisor for help when its SC drops. At the same time, during task execution, a human supervisor can...

Provided herein are systems , methods and apparatuses for a thickness measurement device based on a capacitive array; https://patents.google.com/patent/US10976147B2/en.

Measurement of oil's internal flow resistance, usually known as viscosity, is essential in several domains such as automotive and oil production. Although different types of viscometers are available in the market, several limitations affect their usability in real-time applications; mainly the requirement for calibration. In this paper, we introdu...

Measurement of oil’s viscosity is essential in several domains such as automotive and oil production. Viscometers available in the market have several limitations that affect their usability under real time conditions. We introduce a new method for measuring the oil viscosity under real time conditions based on coplanar capacitive sensors installed...

Link: https://ieee-dataport.org/open-access/dataset-binary-classification-digital-sensor-signals. The dataset is composed of digital signals obtained from a capacitive sensor electrodes that are immersed in water or in oil. Each signal, stored in one row, is composed of 10 consecutive intensity values and a label in the last column. The label is +1...

One of the challenges facing humanoid robots is the design of a more human-like gait. In this paper, we propose a new paradigm for gait design for humanoids that is founded in the field of Kinesiology and is based on energy-exchange between potential and kinetic energies. Additionally, we propose an energy-based controller, which not only maintains...

Have you ever wondered how a song might sound if performed by a different artist? In this work, we propose SCM-GAN, an end-to-end non-parallel song conversion system powered by generative adversarial and transfer learning, which allows users to listen to a selected target singer singing any song. SCM-GAN first separates songs into vocals and instru...

Meaningful 3D maps have a lot to offer to the design of safe and intelligent transportation systems. To do so, street content such as cars, traffic lights and signs need to be segmented in their 3D form, and accurately localized in a map. This paper proposes a first step towards producing 3D rich urban maps in which cars are segmented from a point...

While Direct Visual Odometry (VO) methods have been shown to outperform feature-based ones in terms of accuracy and processing time, their optimization is sensitive to the initialization pose typically seeded from heuristic motion models. In real-life applications, the motion of a hand-held or head-mounted camera is predominantly erratic, thereby v...

In this paper, we study the value of using synthetically produced videos as training data for neural networks used for action categorization. Motivated by the fact that texture and background of a video play little to no significant roles in optical flow, we generated simplified texture-less and background-less videos and utilized the synthetic dat...

In this paper, we study the value of using synthetically produced videos as training data for neural networks used for action categorization. Motivated by the fact that texture and background of a video play little to no significant roles in optical flow, we generated simplified texture-less and background-less videos and utilized the synthetic dat...

Image Captioning (IC) is the process of automatically augmenting an image with semantically-laden descriptive text. While English IC has made remarkable strides forward in the past decade, very little work exists on IC for other languages. One possible solution to this problem is to boostrap off of existing English IC systems for image understandin...

Have you ever wondered how a song might sound if performed by a different artist? In this work, we propose SCM-GAN, an end-to-end non-parallel song conversion system powered by generative adversarial and transfer learning that allows users to listen to a selected target singer singing any song. SCM-GAN first separates songs into vocals and instrume...

In this work, a six degrees-of-freedom (DOF) nonlinear kinematic and dynamic model of a Hybrid Autonomous Underwater Vehicle (H-AUV) is derived for the two modes of locomotion, propelled and gliding modes. A comprehensive linearization algorithm is developed to include both modes of locomotion. Starting with a three-dimensional time-parameterized c...

During an oil spill response, one of the main challenges is the ability to measure, in situ and in real time, the oil slick thickness at different locations throughout the slick. This paper presents an instrument that can respond to this need by employing a capacitive-based sensor designed for oils of different viscosities. There are three main adv...

Capacitive sensors are widely used in different liquid level sensing applications, including multi-phase thickness measurements. The performance of these sensors usually degrades when dealing with highly viscous liquids under dynamic conditions. In such situations, in what is known as fouling, liquid accumulates on the sensor body causing errors in...

This paper presents a novel method for characterizing the distribution of a multiphase gas/liquid mixture under dynamic conditions. The main advantage of the proposed technique is its ability to leverage sensor motion information to correct measurement errors. The proposed method is applied to the measurement of oil thickness within a gas/oil/water...

Monocular Odometry systems can be broadly categorized as being either Direct, Indirect, or a hybrid of both. While Indirect systems process an alternative image representation to compute geometric residuals, Direct methods process the image pixels directly to generate photometric residuals. Both paradigms have distinct but often complementary prope...

Measuring the soil moisture is an essential task in precision agriculture and smart irrigation strategies. However, most of the available measurement instruments are expensive and are not suitable for use by traditional farmers with a low level of education. In addition, several technical limitations affect the performance of the currently used soi...

One of the key features impacting the effectiveness of the currently used oil spill cleaning techniques is knowing, in real-time, the actual thickness of oil films. Aiming to enhance the efficiency of the oil spill response, this paper presents the design, prototyping, and testing of a LED-based spectrometer instrument that measures the thickness o...

Purpose: Driven by the shortage in qualified nurses and the high percentage of aging populations, the past decade has witnessed a significant growth in the use of robots in nursing, especially in countries like Japan. This article is a scoping review of the different tracks in which robots are used in nursing. Whereas assistive robots are used for...

The ability to reliably estimate free space is an essential requirement for efficient and safe robot navigation. This paper presents a novel system, built upon a stochastic framework, which estimates free space quickly from stereo data, using self-supervised learning. The system relies on geometric data in the close range of the robot to train a se...

One of the challenges of teleoperation is the recognition of a user’s intended commands, particularly in the manning of highly dynamic systems such as drones. In this paper, we present a solution to this problem by developing a generalized scheme relying on a Convolutional Neural Network (CNN) that is trained to recognize a user’s intended commands...

Visual Odometry (VO) can be categorized as being either direct or feature based. When the system is calibrated photometrically, and images are captured at high rates, direct methods have shown to outperform feature-based ones in terms of accuracy and processing time; they are also more robust to failure in feature-deprived environments. On the down...

This paper briefly surveys pose tracking methods used for augmented reality applications in cultural heritage. The paper primarily benefits scholars and practitioners in the areas of electronic heritage. Pose tracking techniques are categorized as either being dependent or independent of their surrounding; accordingly, various solution methods in t...

The complete report can be obtained from the Bureau of Safety and Environmental Enforcement (BSEE) at https://www.bsee.gov/sites/bsee.gov/files/research-reports//1078aa.pdf. This technical report presents the design, prototyping, and testing of two low cost floating oil thickness measurement instruments, that provide near real-time measurements for...

In this paper, we propose a novel approach for ground segmentation and free space estimation of outdoor environments. The system is completely self-supervised and relies on two modules: the first module is built around a Fully Convolutional Network (FCN), and is used for ground segmentation after the system is initiated. The second module relies on...

This paper presents a tool for analyzing the motion of two-link nonholonomic swimmers. We refer to these systems as Land-sharks, which are a generalization of the well known Roller Racers. By exploiting the symmetry of the system, we are able to reduce the equations of motion and construct the scaled momentum evolution equation. This unveils a very...

Extensive research in the field of monocular SLAM for the past fifteen years has yielded workable systems that found their way into various applications in robotics and augmented reality. Although filter-based monocular SLAM systems were common at some time, the more efficient keyframe-based solutions are becoming the de facto methodology for build...

An efficient approach for the development of a compact integrated wood charcoal retort was designed. The key fundamental requirements to guarantee efficiency and productivity are initially investigated via CFD simulations to identify the temperature and velocity profiles inside the unit. The final compact design is comprised of a double vessel arra...

This paper presents a new approach to tackle the problem of infinite chattering, observed at bang-singular junctions of the minimum-time trajectories of car-like robots with bounded angular acceleration control. To eliminate chattering from time-optimal control solutions, we propose to relax the ideal nonholonomic constraint of no-skidding. A proof...

In this paper we propose a novel system that uses sensory input from both vision and inertial sensors for an improved perception of the robot current status of equilibrium. We use MonoSLAM vision odometry as a basis for the visual perception and a gyro for angular velocity measurements; and we devise a reweighting method within a Kalman filter fram...

The conservation and valorization of our cultural heritage has become one of the priorities of the international community. Accordingly, many technological applications are being developed with a cultural object as the focal theme of interest. This paper presents a detailed account of the construction of a computerized model of the Roman Theater of...

This paper briefly surveys pose tracking methods used for augmented reality applications in cultural heritage. The paper primarily benefits scholars and practitioners in the areas of electronic heritage. Pose tracking techniques are categorized as either being dependent or independent of their surrounding; accordingly, various solution methods in t...

This research aims to evaluate the performance of low-cost resistive soil moisture sensors under greenhouse conditions. For this purpose, sensors have been assessed by several calibrations and evaluation experiments. Soil moisture percentages were logged daily to obtain curves relating moisture percentages to voltages provided by the sensors. The o...

When humanoid robots are pushed they risk falling and damaging themselves. Preemptive fall avoidance strategies are becoming popular and usually involve measures such as actively actuating the ankles, the hips or even taking steps. Deciding which strategy to take can be determined based on a stability region—known as the decision surface—drawn on a...

Since unmanned aerial vehicles (UAVs) were introduced, their teleoperation was and still is a challenging task. Significant research was conducted in order to facilitate and improve UAVs maneuverability, and yet many accidents are attributed to human error. Remote controls (RCs) are commonly used to control UAVs, but with their constant scale for i...

In recent years, agencies around the world have invested huge amounts of effort toward digitizing many aspects of the world's cultural heritage. Of particular importance is the digitization of outdoor archaeological sites. In the spirit of valorization of this digital information, many groups have developed virtual or augmented reality (AR) compute...

The fundamental shortcoming underlying monocular-based localizationand mapping solutions (SfM, Visual SLAM) is the fact thatthe obtained maps and motion are solved up to an unknown scale.Yet, the literature provides interesting solutions to scale estimationusing cues from focus or defocus of a camera. In this paper, wetake advantage of the scale of...

3D pose of a camera with respect to a 3D representation of thescene. IBL, despite being a trivial problem for small scenes, becomesquite challenging as the size of the scene grows. Aside fromthe computational burden, matching against a very large numberof 3D keypoints spanning a wide variety of viewpoints, illumination,and areas is a very unreliabl...

Extensive research in the field of Visual SLAM for the past fifteen years has yielded workable systems that found their way into various applications, such as robotics and augmented reality. Although filter-based (e.g., Kalman Filter, Particle Filter) Visual SLAM systems were common at some time, non-filter based (i.e., akin to SfM solutions), whic...

In this paper, a three dimensional model for a variable-diameter wheeled mobile base is introduced which is tailored for modeling locomotion on rough terrain. The motion planning of the introduced model is novel, since the forward motion of the robot is governed by a central rolling disk, while its steering is governed by the lateral shifting of th...

This paper proposes a novel technique to extract training data from free space in a scene using a stereo camera. The proposed technique exploits the projection of planes in the v-disparity image paired with Bayesian linear regression to reliably identify training image pixels belonging to free space in a scene. Unlike other methods in the literatur...

p>Image-based localization problem consists of estimating the 6 DoF camera pose by matching the image to a 3D point cloud (or equivalent) representing a 3D environment. The robustness and accuracy of current solutions is not objective and quantifiable. We have completed a comparative analysis of the main state of the art approaches, namely Brute Fo...

This paper proposes a novel technique for segmenting the ground plane and at the same time estimating the occupancy probability of each point in a scene. Using a stereo camera rig, our system first calculates a disparity map and transforms it to a v-disparity map, which is then filtered and processed to generate a corresponding probability field. T...

Abstract: This paper presents a method for generating three-dimensional paths for a vehicle with a bounded maximum curvature in both yaw and pitch rotations. We build upon the two-dimensional time-optimal path generation for constant speed vehicles with bounded steering that produces the socalled Dubins curves. We formulate a similar problem in thr...

In this paper, we solve the motion planning problem for a class of underactuated multibodied planar mechanical systems. These systems interact with the environment via viscous frictional forces. The motion planning problem is solved by specifying the location of friction pads on the robot as well as by specifying the input of the actuated degrees o...

This paper proposes a new intuitive technique for the haptic teleoperation of unmanned aerial vehicles (UAVs). The UAV is controlled using joystick's velocity commands, and the haptic feedback is a repelling force proportional to the UAV's velocity. Our proposed method that entails sensing the UAV velocity and commanding it using velocity based ges...

In this paper we propose a new method to tackle the problem of discontinuous curvature observed in the time-optimal Dubins trajectories of car-like robots. The discontinuous curvature profile renders the paths untraceable by a real robot due to the existence of infinite accelerations at the transition points. To make way for a continuous curvature...