Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jaebyung Park has a total of 26 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Manipulator-based Active Exploration Strategy for Unexplored Areas Utilizing 3D-2D Spherical Projection

    by Hyeon-Wook Hong, Byeong-Seon Choi, Jaebyung Park

    The rapid aging of the agricultural workforce and the continued shrinkage of the rural population have heightened the need for affordable autonomous robotic solutions in agriculture. Visual simultaneous and localization mapping systems are widely used for environmental perception and localization, but their narrow field of view (FOV) limits their ability to map complex agricultural environments comprehensively. While multi-camera systems can address FOV limitations, their high costs and increased computational demands make them impractical for cost-sensitive applications. Herein, a low-cost and efficient methodology that employs active exploration using a robotic manipulator has been proposed to address these challenges. This unique approach reduces computational complexity while retaining essential environmental details by converting 3D point cloud data into 2D depth images through spherical projection. Such a transformation allows the system to effectively identify unexplored regions within the depth images, guiding the manipulator to explore these areas autonomously. As a result, this method enables comprehensive environmental mapping with minimal sensor requirements, offering a practical solution for agricultural automation.

  • Development of Hospital Guide Robot With Stable Mobility and Improved Human-robot Interaction

    by Byeongseon Choi, Jaebyung Park

    Using robots to guide humans in large and complex environments has been a longstanding research topic in robotics. Two technical factors for guide robots: 1) stable mobility and 2) human-robot interaction capability. This study introduces a hospital guide robot with improvements in these areas. We first constructed the robot’s mechanical and electrical systems. To achieve stable mobility, we analyzed the kinematics of the robot and implemented a pose estimation algorithm using a sensor fusion technique. Secondly, we developed the “Hospital Guidance System” software to enhance the human-robot interaction capability. Using a quick response code-based system, hospital visitors can seamlessly access medical care and guidance. We conducted experiments to validate the robot’s ability to provide hospital guidance services based on pre-defined scenarios.


  • Open Access

    A Novel Row Index Mathematical Procedure for the Mitigation of PV Output Power Losses during Partial Shading Conditions

    by Muhammad Zeeshan, Naeem Ul Islam, Faiz Faizullah, Ihsan Ullah Khalil, Jaebyung Park

    Energy demand forecasted for the next several years has been bench marked due to the massive need for electrical energy. Solar power plants have earned a great marketplace position in recent years, but also face challenges in terms of power dissipation due to the frequent occurrence of shade. As a result, the per unit solar electricity price increases drastically. There is an immense need to ensure the maximum dependable power conversion efficiency of Photovoltaic (PV) systems by mitigating power output losses during partial shading conditions. The reconfiguration of PV arrays is a useful, effective, and promising approach in this context. Though several reconfiguration techniques have been developed in recent years, their applicability to real-time power plants is debatable due to the requirement of many physical relocations, long interconnecting ties, and complexity. This research work proposes a novel row index mathematical procedure followed by a technique in which the reconfiguration matrix indexes are filled with a unique number so that no row number repeats in the same row and column. Additionally, the proposed approach uses small number of switches that reduce the cost as well as the computational complexity. To strengthen the analysis, very recent techniques such as Sudoku, Total Cross Tied (TCT), Chess-Knight, and Particle Swarm Optimization (PSO) based reconfiguration are compared against five different shading patterns. It has been observed that approximately 68% power loss is mitigated in TCT configuration. It is worth noting that it results in higher PV output power than the existing latest reconfiguration techniques such as PSO, Chess-Knight, Sudoku, and others.


  • Open Access

    Analyzing the Effectiveness of Classification and Regression for Depth Estimation of Highly Dynamic Terrain

    by Naeem Ul Islam, Jaebyung Park

    Depth estimation is considered a problem of translating RGB images to their corresponding depth maps. It plays an essential role in robotics and autonomous navigation as it allows for an understanding of the nature of the terrain. Owing to its natural importance, considerable attention has been paid by the research community in the past decade to depth estimations, including studies focusing on environmental condition-, classification-, or regression-based approaches. Among them, classification- and regression-based approaches are considered the key candidates for depth estimations, but it is not clear which approach performs better under what conditions. To investigate and define a clear method for providing an accurate depth estimation from a single RGB image, this study extensively evaluates these approaches qualitatively and quantitatively by considering a highly dynamic dataset. Based on extensive qualitative and quantitative experimental analyses, this study provides possible future directions for accurate depth estimation from a single RGB image.

  • Open Access

    Intelligent Carom Billiards Assistive System for automatic solution path generation and actual path prediction with principal component analysis-based ball motion detection

    by Jung-Kil Park, Jaebyung Park

    This article proposes an Intelligent Carom Billiards Assistive System for a novice at Carom Billiards. Since a novice player is very difficult to find the solution paths of the cue ball, the ICBAS automatically calculates the solution paths for given ball configuration which is detected by a monocular vision and displays them in a guidance monitor. For rapid and systematically calculating the solution paths, the five and half system that is the most representative method in the field of billiard is implemented. In addition, the paths of the cue ball changed by the direction of the cue stick are predicted in real time and projected onto the pool table bed. By comparing the solution paths of the cue ball with the projected paths, a player can hit the cue ball easily and successfully. For automatically providing the solution paths and the predicted paths during billiard game, the ball movement is detected by the principal component analysis under linear motion constraints robustly against image noise, occlusion, and so on. Whenever all of the balls stop, both paths are newly calculated and provided for a player. For verifying the feasibility of the proposed Intelligent Carom Billiards Assistive System, the experiments are conducted with the real pool table.


  • Four-Wheel Linear Steering Structure Design with Improved Maneuverability Based on a Single Motor and Linear Actuator

    by SooHwan Byeon, Jaebyung Park

    In this paper, we propose a new steering structure to improve the structural robustness and maneuverability of the original steering structure designed in our previous study. Most mobile robot platforms are designed with a differential drive or all-wheel steering (AWS) models. Differential-drive robots have a simple structure and are easy to manufacture, but this structure causes considerable slipping when the robots rotate. The AWS model has such a high maneuverability that it can reduce slip, but this structure requires as many steering motors as driving motors. To address these problems, in our previous research, we designed the steering structure to be as highly maneuverable as AWS models using a single steering motor and a solenoid actuator. However, the original structure requires nonlinear control and is too complex to analyze for selecting the proper steering motor. Thus, in this work, we design a steering structure with a simpler mechanical structure that has structural robustness and is easy to analyze, control, and manufacture. In addition, the proposed structure can steer faster than the original one and even move a four-wheel robot horizontally.

  • Open Access

    bCNN-Methylpred: Feature-Based Prediction of RNA Sequence Modification Using Branch Convolutional Neural Network

    by Naeem Islam, Jaebyung Park

    RNA modification is vital to various cellular and biological processes. Among the existing RNA modifications, N6-methyladenosine (m6A) is considered the most important modification owing to its involvement in many biological processes. The prediction of m6A sites is crucial because it can provide a better understanding of their functional mechanisms. In this regard, although experimental methods are useful, they are time consuming. Previously, researchers have attempted to predict m6A sites using computational methods to overcome the limitations of experimental methods. Some of these approaches are based on classical machine-learning techniques that rely on handcrafted features and require domain knowledge, whereas other methods are based on deep learning. However, both methods lack robustness and yield low accuracy. Hence, we develop a branch-based convolutional neural network and a novel RNA sequence representation. The proposed network automatically extracts features from each branch of the designated inputs. Subsequently, these features are concatenated in the feature space to predict the m6A sites. Finally, we conduct experiments using four different species. The proposed approach outperforms existing state-of-the-art methods, achieving accuracies of 94.91%, 94.28%, 88.46%, and 94.8% for the H. sapiens, M. musculus, S. cerevisiae, and A. thaliana datasets, respectively.


  • Open Access

    Depth Estimation From a Single RGB Image Using Fine-Tuned Generative Adversarial Network

    by Naeem Ul Islam, Jaebyung Park

    Estimating the depth map from a single RGB image is important to understand the nature of the terrain in robot navigation and has attracted considerable attention in the past decade. The existing approaches can accurately estimate the depth from a single RGB image, considering a highly structured environment. The problem becomes more challenging when the terrain is highly dynamic. We propose a fine-tuned generative adversarial network to estimate the depth map effectively for a given single RGB image. The proposed network is composed of a fine-tuned generator and a global discriminator. The encoder part of the generator takes input RGB images and depth maps and generates their joint distribution in the latent space. Subsequently, the decoder part of the generator decodes the depth map from the joint distribution. The discriminator takes real and fake pairs in three different configurations and then guides the generator to estimate the depth map from the given RGB image accordingly. Finally, we conducted extensive experiments with a highly dynamic environment dataset for verifying the effectiveness and feasibility of the proposed approach. The proposed approach could decode the depth map from the joint distribution more effectively and accurately than the existing approaches.


  • Open Access

    Prominent Attribute Modification using Attribute Dependent Generative Adversarial Network

    by Naeem Ul Islam, Sungmin Lee, Jaebyung Park

    Modifying the facial images with desired attributes is important, though challenging tasks in computer vision, where it aims to modify single or multiple attributes of the face image. Some of the existing methods are either based on attribute independent approaches where the modification is done in the latent representation or attribute dependent approaches. The attribute independent methods are limited in performance as they require the desired paired data for changing the desired attributes. Secondly, the attribute independent constraint may result in the loss of information and, hence, fail in generating the required attributes in the face image. In contrast, the attribute dependent approaches are effective as these approaches are capable of modifying the required features along with preserving the information in the given image. However, attribute dependent approaches are sensitive and require a careful model design in generating high-quality results. To address this problem, we propose an attribute dependent face modification approach. The proposed approach is based on two generators and two discriminators that utilize the binary as well as the real representation of the attributes and, in return, generate high-quality attribute modification results. Experiments on the CelebA dataset show that our method effectively performs the multiple attribute editing with preserving other facial details intactly.


  • Open Access

    Face Attribute Modification Using Fine-Tuned Attribute-Modification Network

    by Naeem Ul Islam, Jaebyung Park

    Multi-domain image-to-image translation with the desired attributes is an important approach for modifying single or multiple attributes of a face image, but is still a challenging task in the computer vision field. Previous methods were based on either attribute-independent or attribute-dependent approaches. The attribute-independent approach, in which the modification is performed in the latent representation, has performance limitations because it requires paired data for changing the desired attributes. In contrast, the attribute-dependent approach is effective because it can modify the required features while maintaining the information in the given image. However, the attribute-dependent approach is sensitive to attribute modifications performed while preserving the face identity, and requires a careful model design for generating high-quality results. To address this problem, we propose a fine-tuned attribute modification network (FTAMN). The FTAMN comprises a single generator and two discriminators. The discriminators use the modified image in two configurations with the binary attributes to fine tune the generator such that the generator can generate high-quality attribute-modification results. Experimental results obtained using the CelebA dataset verify the feasibility and effectiveness of the proposed FTAMN for editing multiple facial attributes while preserving the other details.