Manh Duong Phung

Anh Thu Nguyen Ngoc, Tam Phong Truong, Thai Anh Nguyen Duong et al.

Sign language recognition technologies can improve communication between deaf individuals and the broader community, but many existing systems face challenges in real-world deployment. This paper presents a deployable smart glove system for sign language recognition that integrates wearable sensing and deep learning. The glove incorporates flex sensors and an inertial measurement unit (IMU) to capture finger articulation and hand motion, while facial cues are obtained through a camera. Sensor data are transmitted via an ESP32-C6 microcontroller and processed using a long short-term memory (LSTM) network to model temporal gesture dynamics. Experimental results show that the proposed model achieves an overall recognition accuracy of approximately 95%. The trained model is further converted to TensorFlow Lite for real-time inference. This demonstrates the feasibility of the system for practical sign language translation applications.

Van Truong Hoang, Manh Duong Phung

This paper introduces a new path planning algorithm for unmanned aerial vehicles (UAVs) based on the teaching-learning-based optimization (TLBO) technique. We first define an objective function that incorporates requirements on the path length and constraints on the movement and safe operation of UAVs to convert the path planning into an optimization problem. The optimization algorithm named Multi-subject TLBO is then proposed to minimize the formulated objective function. The algorithm is developed based on TLBO but enhanced with new operations including mutation, elite selection and multi-subject training to improve the solution quality and speed up the convergence rate. Comparison with state-of-the-art algorithms and experiments with real UAVs have been conducted to evaluate the performance of the proposed algorithm. The results confirm its validity and effectiveness in generating optimal, collision-free and flyable paths for UAVs in complex operating environments.

Alessandro Gallo, Manh Duong Phung

A trained T1 class Convolutional Neural Network (CNN) model will be used to examine its ability to successfully identify motor imagery when fed pre-processed electroencephalography (EEG) data. In theory, and if the model has been trained accurately, it should be able to identify a class and label it accordingly. The CNN model will then be restored and used to try and identify the same class of motor imagery data using much smaller sampled data in an attempt to simulate live data.

Quang Huy Vu, Quan Le, Manh Duong Phung

Water quality monitoring is essential for protecting aquatic ecosystems and detecting environmental pollution. This paper presents the design and experimental validation of a bio-inspired miniature submarine for low-cost water quality monitoring. Inspired by the jet propulsion mechanism of squids, the proposed system employs pump-driven water jets for propulsion and steering, combined with a pump-based buoyancy control mechanism that enables both depth regulation and water sampling. The vehicle integrates low-cost, commercially available components including an ESP32 microcontroller, IMU, pressure sensor, GPS receiver, and LoRa communication module. The complete system can be constructed at a hardware cost of approximately $122.5, making it suitable for educational and environmental monitoring applications. Experimental validation was conducted through pool tests and field trials in a lake. During a 360 degrees rotation test, roll and pitch deviations remained within +/-2 degrees and +/-1.5 degrees, respectively, demonstrating stable attitude control. Steering experiments showed a heading step response with approximately 2 s rise time and 5 s settling time. Depth control experiments achieved a target depth of 2.5 m with steady-state error within +/-0.1 m. Field experiments further demonstrated reliable navigation and successful water sampling operations. The results confirm that the proposed platform provides a compact, stable, and cost-effective solution for small-scale aquatic environmental monitoring.

Thi Thuy Ngan Duong, Duy-Nam Bui, Manh Duong Phung

Path planning is essential for unmanned aerial vehicles (UAVs) as it determines the path that the UAV needs to follow to complete a task. This work addresses this problem by introducing a new algorithm called navigation variable-based multi-objective particle swarm optimization (NMOPSO). It first models path planning as an optimization problem via the definition of a set of objective functions that include optimality and safety requirements for UAV operation. The NMOPSO is then used to minimize those functions through Pareto optimal solutions. The algorithm features a new path representation based on navigation variables to include kinematic constraints and exploit the maneuverable characteristics of the UAV. It also includes an adaptive mutation mechanism to enhance the diversity of the swarm for better solutions. Comparisons with various algorithms have been carried out to benchmark the proposed approach. The results indicate that the NMOPSO performs better than not only other particle swarm optimization variants but also other state-of-the-art multi-objective and metaheuristic optimization algorithms. Experiments have also been conducted with real UAVs to confirm the validity of the approach for practical flights. The source code of the algorithm is available at https://github.com/ngandng/NMOPSO.

Duy Nam Bui, Thuy Ngan Duong, Manh Duong Phung

This paper presents a new swarm intelligence-based approach to deal with the cooperative path planning problem of unmanned aerial vehicles (UAVs), which is essential for the automatic inspection of infrastructure. The approach uses a 3D model of the structure to generate viewpoints for the UAVs. The calculation of the viewpoints considers the constraints related to the UAV formation model, camera parameters, and requirements for data post-processing. The viewpoints are then used as input to formulate the path planning as an extended traveling salesman problem and the definition of a new cost function. Ant colony optimization is finally used to solve the problem to yield optimal inspection paths. Experiments with 3D models of real structures have been conducted to evaluate the performance of the proposed approach. The results show that our system is not only capable of generating feasible inspection paths for UAVs but also reducing the path length by 29.47\% for complex structures when compared with another heuristic approach. The source code of the algorithm can be found at https://github.com/duynamrcv/aco_3d_ipp.

Manh Duong Phung, Quang Phuc Ha

This paper presents a new algorithm named spherical vector-based particle swarm optimization (SPSO) to deal with the problem of path planning for unmanned aerial vehicles (UAVs) in complicated environments subjected to multiple threats. A cost function is first formulated to convert the path planning into an optimization problem that incorporates requirements and constraints for the feasible and safe operation of the UAV. SPSO is then used to find the optimal path that minimizes the cost function by efficiently searching the configuration space of the UAV via the correspondence between the particle position and the speed, turn angle and climb/dive angle of the UAV. To evaluate the performance of SPSO, eight benchmarking scenarios have been generated from real digital elevation model maps. The results show that the proposed SPSO outperforms not only other particle swarm optimization (PSO) variants including the classic PSO, phase angle-encoded PSO and quantum-behave PSO but also other state-of-the-art metaheuristic optimization algorithms including the genetic algorithm (GA), artificial bee colony (ABC), and differential evolution (DE) in most scenarios. In addition, experiments have been conducted to demonstrate the validity of the generated paths for real UAV operations. Source code of the algorithm can be found at https://github.com/duongpm/SPSO.

Cong Hoang Quach, Chi Thanh Vo, Dong LT. Tran et al.

Accurate localization of unmanned aerial vehicles (UAVs) is essential for applications such as structural health monitoring, especially in environments where Global Positioning System (GPS) signals are denied or unreliable, like indoor spaces, tunnels, urban canyons, or areas beneath large structures. To address this challenge, we propose Cross-Fusion, a novel method for real-time UAV localization that integrates data from a 3D Light Detection and Ranging (LiDAR) and a monocular camera. A key contribution is its cross-session fusion strategy, which integrates visual and geometric information collected from multiple agents during routine baseline surveys to improve localization consistency and map completeness. The system employs LiDAR-based odometry for motion tracking and image-based feature matching via a single red-green-blue (RGB) camera to correct drift and improve accuracy. Unlike visual-inertial systems, Cross-Fusion maintains a simple sensor setup and avoids the complexity of stereo or global shutter configurations. Experimental results demonstrate that Cross-Fusion achieves localization accuracy comparable to GPS-based methods and performs reliably in challenging feature-sparse environments.

Minh Dang Tu, Kieu Trang Le, Manh Duong Phung

This work presents a neural network model capable of recognizing small and tiny objects in thermal images collected by unmanned aerial vehicles. Our model consists of three parts, the backbone, the neck, and the prediction head. The backbone is developed based on the structure of YOLOv5 combined with the use of a transformer encoder at the end. The neck includes a BI-FPN block combined with the use of a sliding window and a transformer to increase the information fed into the prediction head. The prediction head carries out the detection by evaluating feature maps with the Sigmoid function. The use of transformers with attention and sliding windows increases recognition accuracy while keeping the model at a reasonable number of parameters and computation requirements for embedded systems. Experiments conducted on public dataset VEDAI and our collected datasets show that our model has a higher accuracy than state-of-the-art methods such as ResNet, Faster RCNN, ComNet, ViT, YOLOv5, SMPNet, and DPNetV3. Experiments on the embedded computer Jetson AGX show that our model achieves a real-time computation speed with a stability rate of over 90%.

Thi Thanh Van Nguyen, Manh Duong Phung, Thuan Hoang Tran et al.

This paper proposes a novel approach to improve the performance of the extended Kalman filter (EKF) for the problem of mobile robot localization. A fuzzy logic system is employed to continuous-ly adjust the noise covariance matrices of the filter. A neural network is implemented to regulate the membership functions of the antecedent and consequent parts of the fuzzy rules. The aim is to gain the accuracy and avoid the divergence of the EKF when the noise covariance matrices are fixed or wrongly determined. Simulations and experiments have been conducted. The results show that the proposed filter is better than the EKF in localizing the mobile robot.

Manh Duong Phung, Cong Hoang Quach, Quang Vinh Tran

In this study, a novel eye tracking system using a visual camera is developed to extract human's gaze, and it can be used in modern game machines to bring new and innovative interactive experience to players. Central to the components of the system, is a robust iris-center and eye-corner detection algorithm basing on it the gaze is continuously and adaptively extracted. Evaluation tests were applied to nine people to evaluate the accuracy of the system and the results were 2.50 degrees (view angle) in horizontal direction and 3.07 degrees in vertical direction.

Qiuchen Zhu, Tran Hiep Dinh, Manh Duong Phung et al.

Drone imagery is increasingly used in automated inspection for infrastructure surface defects, especially in hazardous or unreachable environments. In machine vision, the key to crack detection rests with robust and accurate algorithms for image processing. To this end, this paper proposes a deep learning approach using hierarchical convolutional neural networks with feature preservation (HCNNFP) and an intercontrast iterative thresholding algorithm for image binarization. First, a set of branch networks is proposed, wherein the output of previous convolutional blocks is half-sizedly concatenated to the current ones to reduce the obscuration in the down-sampling stage taking into account the overall information loss. Next, to extract the feature map generated from the enhanced HCNN, a binary contrast-based autotuned thresholding (CBAT) approach is developed at the post-processing step, where patterns of interest are clustered within the probability map of the identified features. The proposed technique is then applied to identify surface cracks on the surface of roads, bridges or pavements. An extensive comparison with existing techniques is conducted on various datasets and subject to a number of evaluation criteria including the average F-measure (AF\b{eta}) introduced here for dynamic quantification of the performance. Experiments on crack images, including those captured by unmanned aerial vehicles inspecting a monorail bridge. The proposed technique outperforms the existing methods on various tested datasets especially for GAPs dataset with an increase of about 1.4% in terms of AF\b{eta} while the mean percentage error drops by 2.2%. Such performance demonstrates the merits of the proposed HCNNFP architecture for surface defect inspection.

Manh Duong Phung, Quang Phuc Ha

This paper presents a novel algorithm named the motion-encoded particle swarm optimization (MPSO) for finding a moving target with unmanned aerial vehicles (UAVs). From the Bayesian theory, the search problem can be converted to the optimization of a cost function that represents the probability of detecting the target. Here, the proposed MPSO is developed to solve that problem by encoding the search trajectory as a series of UAV motion paths evolving over the generation of particles in a PSO algorithm. This motion-encoded approach allows for preserving important properties of the swarm including the cognitive and social coherence, and thus resulting in better solutions. Results from extensive simulations with existing methods show that the proposed MPSO improves the detection performance by 24\% and time performance by 4.71 times compared to the original PSO, and moreover, also outperforms other state-of-the-art metaheuristic optimization algorithms including the artificial bee colony (ABC), ant colony optimization (ACO), genetic algorithm (GA), differential evolution (DE), and tree-seed algorithm (TSA) in most search scenarios. Experiments have been conducted with real UAVs in searching for a dynamic target in different scenarios to demonstrate MPSO merits in a practical application.

Khai Ky Ly, Manh Duong Phung

This study presents an inspecting system using real-time control unmanned aerial vehicles (UAVs) to investigate structural surfaces. The system operates under favourable weather conditions to inspect a target structure, which is the Wentworth light rail base structure in this study. The system includes a drone, a GoPro HERO4 camera, a controller and a mobile phone. The drone takes off the ground manually in the testing field to collect the data requiring for later analysis. The images are taken through HERO 4 camera and then transferred in real time to the remote processing unit such as a ground control station by the wireless connection established by a Wi-Fi router. An image processing method has been proposed to detect defects or damages such as cracks. The method based on intensity histogram algorithms to exploit the pixel group related to the crack contained in the low intensity interval. Experiments, simulation and comparisons have been conducted to evaluate the performance and validity of the proposed system.

Cong Hoang Quach, Minh Trien Pham, Anh Viet Dang et al.

In this study, we present an model-based approach to recognize full 26 degrees of freedom of a human hand. Input data include RGB-D images acquired from a Kinect camera and a 3D model of the hand constructed from its anatomy and graphical matrices. A cost function is then defined so that its minimum value is achieved when the model and observation images are matched. To solve the optimization problem in 26 dimensional space, the particle swarm optimization algorimth with improvements are used. In addition, parallel computation in graphical processing units (GPU) is utilized to handle computationally expensive tasks. Simulation and experimental results show that the system can recognize 26 degrees of freedom of hands with the processing time of 0.8 seconds per frame. The algorithm is robust to noise and the hardware requirement is simple with a single camera.

Thi Thanh Van Nguyen, Manh Duong Phung, Dinh Tuan Pham et al.

A Building Automation System (BAS) has functions of monitoring and controlling the operation of all building sub-systems such as HVAC (Heating-Ventilation, Air-conditioning Control), electric consumption management, fire alarm control, security and access control, and appliance switching control. In the BAS, almost operations are automatically performed at the control centre, the building security therefore must be strictly protected. In the traditional system, the security is usually ensured by a number of cameras installed at fixed positions and it may results in a limited vision. To overcome this disadvantage, our paper presents a novel security system in which a mobile robot is used as a patrol. The robot is equipped with fuzzy-based algorithms to allow it to avoid the obstacles in an unknown environment as well as other necessary mechanisms demanded for its patrol mission. The experiment results show that the system satisfies the requirements for the objective of monitoring and securing the building.

Thi Thanh Van Nguyen, Manh Duong Phung, Quang Vinh Tran

The paper proposes the stable motion control law design method for non-honomic differential-drive mobile robot with system and measurement noise in discrete time domain. This method is performed basing on dividing operating configuration of robot into two parts: glocal and local configuration then the control law is designed following Lyapunov stable theory for two configuration. The proposed stable control laws is able to reach asymptotically stably to target position and orientation from any initial conditions even existing noise in the system. Some simulation results have demonstrated the effect of proposed method.

Thuan Hoang Tran, Manh Duong Phung, Anh Viet Dang et al.

This paper presents the use of multi-sensor measurement system to guide autonomous mobile robot in the house. The system allows the 3D image acquisition to global mapping, and algorithms to reduce the dimensionality of images to 2D global map navigation, trajectory design approach using the Lyapunov function method and avoid obstacles by the potential energy can also be presented. Also, sensor integrated method based on extended Kalman filter allows us to identify the exact location and orientation of the robot in the presence of interference from the environment.

Manh Duong Phung, Thi Thanh Van Nguyen, Thuan Hoang Tran et al.

This paper addresses the stabilization control problem for networked mobile robot subject to communication delay. A new state estimation filter namely past observation-based predictive filter is developed. This filter enables the prediction of system state from delayed measurement. The state estimator combined with developed control laws ensures the asymptotic stability of the networked system. Simulations with parameters extracted from a real robot system were conducted and results confirmed the correctness as well as applicability of proposed approach.

Qiuchen Zhu, Manh Duong Phung, Quang Ha

Unmanned aerial vehicles (UAV) are expected to replace human in hazardous tasks of surface inspection due to their flexibility in operating space and capability of collecting high quality visual data. In this study, we propose enhanced hierarchical convolutional neural networks (HCNN) to detect cracks from image data collected by UAVs. Unlike traditional HCNN, here a set of branch networks is utilised to reduce the obscuration in the down-sampling process. Moreover, the feature preserving blocks combine the current and previous terms from the convolutional blocks to provide input to the loss functions. As a result, the weights of resized images can be reduced to minimise the information loss. Experiments on images of different crack datasets have been carried out to demonstrate the effectiveness of proposed HCNN.

V. T. Hoang, M. D. Phung, T. H. Dinh et al.

In this paper, we propose an algorithm for the formation of multiple UAVs used in vision-based inspection of infrastructure. A path planning algorithm is first developed by using a variant of the particle swarm optimisation, named theta-PSO, to generate a feasible path for the overall formation configuration taken into account the constraints for visual inspection. Here, we introduced a cost function that includes various constraints on flight safety and visual inspection. A reconfigurable topology is then added based on the use of intermediate waypoints to allow the formation to avoid collision with obstacles during operation. The planned path and formation are then combined to derive the trajectory and velocity profiles for each UAV. Experiments have been conducted for the task of inspecting a light rail bridge. The results confirmed the validity and effectiveness of the proposed algorithm.

Q. Zhu, T. H. Dinh, V. T. Hoang et al.

This paper proposes a thresholding approach for crack detection in an unmanned aerial vehicle (UAV) based infrastructure inspection system. The proposed algorithm performs recursively on the intensity histogram of UAV-taken images to exploit their crack-pixels appearing at the low intensity interval. A quantified criterion of interclass contrast is proposed and employed as an object cost and stop condition for the recursive process. Experiments on different datasets show that our algorithm outperforms different segmentation approaches to accurately extract crack features of some commercial buildings.

Cong Hoang Quach, Van Lien Tran, Duy Hung Nguyen et al.

This paper addresses the problem of lane detection which is fundamental for self-driving vehicles. Our approach exploits both colour and depth information recorded by a single RGB-D camera to better deal with negative factors such as lighting conditions and lane-like objects. In the approach, colour and depth images are first converted to a half-binary format and a 2D matrix of 3D points. They are then used as the inputs of template matching and geometric feature extraction processes to form a response map so that its values represent the probability of pixels being lane markers. To further improve the results, the template and lane surfaces are finally refined by principal component analysis and lane model fitting techniques. A number of experiments have been conducted on both synthetic and real datasets. The result shows that the proposed approach can effectively eliminate unwanted noise to accurately detect lane markers in various scenarios. Moreover, the processing speed of 20 frames per second under hardware configuration of a popular laptop computer allows the proposed algorithm to be implemented for real-time autonomous driving applications.

Manh Duong Phung, Cong Hoang Quach, Tran Hiep Dinh et al.

In built infrastructure monitoring, an efficient path planning algorithm is essential for robotic inspection of large surfaces using computer vision. In this work, we first formulate the inspection path planning problem as an extended travelling salesman problem (TSP) in which both the coverage and obstacle avoidance were taken into account. An enhanced discrete particle swarm optimization (DPSO) algorithm is then proposed to solve the TSP, with performance improvement by using deterministic initialization, random mutation, and edge exchange. Finally, we take advantage of parallel computing to implement the DPSO in a GPU-based framework so that the computation time can be significantly reduced while keeping the hardware requirement unchanged. To show the effectiveness of the proposed algorithm, experimental results are included for datasets obtained from UAV inspection of an office building and a bridge.

Manh Duong Phung, Thi Thanh Van Nguyen, Thuan Hoang Tran et al.

This paper presents a new optimal filter namely past observation-based extended Kalman filter for the problem of localization of Internet-based mobile robot in which the control input and the feedback measurement suffer from communication delay. The filter operates through two phases: the time update and the data correction. The time update predicts the robot position by reformulating the kinematics model to be non-memoryless. The correction step corrects the prediction by extrapolating the delayed measurement to the present and then incorporating it to the being estimate as there is no delay. The optimality of the incorporation is ensured by the derivation of a multiplier that reflects the relevance of past observations to the present. Simulations in MATLAB and experiments in a real networked robot system confirm the validity of the proposed approach.

Manh Duong Phung, Quang Vinh Tran, Kenji Hara et al.

Tracking the movement of human eyes is expected to yield natural and convenient applications based on human-computer interaction (HCI). To implement an effective eye-tracking system, eye movements must be recorded without placing any restriction on the user's behavior or user discomfort. This paper describes an eye movement recording system that offers free-head, simple configuration. It does not require the user to wear anything on her head, and she can move her head freely. Instead of using a computer, the system uses a visual digital signal processor (DSP) camera to detect the position of eye corner, the center of pupil and then calculate the eye movement. Evaluation tests show that the sampling rate of the system can be 300 Hz and the accuracy is about 1.8 degree/s.

Tran Hiep Dinh, Minh Trien Pham, Manh Duong Phung et al.

This study proposes an approach to segment human object from a depth image based on histogram of depth values. The region of interest is first extracted based on a predefined threshold for histogram regions. A region growing process is then employed to separate multiple human bodies with the same depth interval. Our contribution is the identification of an adaptive growth threshold based on the detected histogram region. To demonstrate the effectiveness of the proposed method, an application in driver distraction detection was introduced. After successfully extracting the driver's position inside the car, we came up with a simple solution to track the driver motion. With the analysis of the difference between initial and current frame, a change of cluster position or depth value in the interested region, which cross the preset threshold, is considered as a distracted activity. The experiment results demonstrated the success of the algorithm in detecting typical distracted driving activities such as using phone for calling or texting, adjusting internal devices and drinking in real time.