Kohichi Ogata

Kohichi Ogata

Auto-generated profile, based on publicly available information

Kohichi Ogata

Faculty of Advanced Science and Technology, Kumamoto University, Kumamoto, Japan

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 April 2021 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
BRBudiman Rohman
Budiman Rohman
MNMasahiko Nishimoto
Masahiko Nishimoto
KOKohichi Ogata
Kohichi Ogata
Ground-penetrating radar is an effective tool for the exploration of subsurface and obscured objects by exploiting the electromagnetic wave characteristics. However, some problems in the measurement process produce missing traces. The resulting incomplete data create difficulties in visualization, interpretation, and analysis. This article proposes a lightweight deep learning method to reconstruct the missing traces. The model is a simplification of a well-known convolutional neural network model, U-Net, which performs well in this context. We use a multi-and-wide kernel size, shallow convolutional layers, a reduced encoding-decoding step, and a minimized feature map size to minimize the model while maintaining high performance. In this study, we focus on the case of inspection of reinforced concrete, where the examined structure consists of a series of rebar and/or void cracks. The numerical and experimental field data results indicate that the method can reconstruct the missing traces with high accuracy. The proposed method also shows comparable performance with U-Net, although the model size is more than 45 times smaller, and its computation speed is more than three times faster. Thus, the proposed method is promising for use in a wide range of applications and devices.

25 December 2023 in IEEE Access
Verified
Journal Article
Open access
OPOddy Virgantara Putra
Oddy Virgantara Putra
MRMoch. Iskandar Riansyah
Moch. Iskandar Riansyah
FRFarah Zakiyah Rahmanti
Farah Zakiyah Rahmanti
APArdyono Priyadi
Ardyono Priyadi
DWDiah Puspito Wulandari
Diah Puspito Wulandari
MPMauridhi Hery Purnomo
Mauridhi Hery Purnomo
Object recognition in Point Cloud data from LiDAR sensors often faces challenges like noise, clutter, and ground interference, significantly affecting tasks such as segmentation, classification, and detection. To address these issues, we introduced a framework comprising a denoiser and a classifier, enhancing the robustness of LiDAR-based object recognition. The denoiser plays a crucial role in noise mitigation and operates as a two-part system, utilizing ScoreNet and the Guided Filter. ScoreNet employs advanced scoring techniques to separate valuable information from noise, while the Guided Filter further refines the data, preserving crucial details. The output from the denoiser seamlessly feeds into the classifier, leveraging a modified GDANet architecture with depthwise overparameterized convolution (DOConv) to capture intricate features. We evaluated our approach using Point-to-Point, Hausdorff distance, and Accuracy metrics, comparing it with other denoising methods and point cloud classifiers. Our models demonstrated significant improvements in denoising and classification tasks, with the denoiser achieving outstanding results in the Hausdorff Distance metric, reaching a score of 0.177. Simultaneously, the classifier outperformed other point cloud classifiers, achieving accuracy scores of 90.7% and 96.7% for ModelNet40-C and Human Pose Dataset, respectively. These achievements underscore the importance of our framework in addressing the challenges of noise and clutter in Point Cloud data, ultimately advancing LiDAR-based object recognition.

27 January 2022 in IEEE Access
Verified
Journal Article
Open access
BRBudiman Rohman
Budiman Rohman
MNMasahiko Nishimoto
Masahiko Nishimoto
KOKohichi Ogata
Kohichi Ogata
Ground penetrating radar (GPR) is widely applied for civil engineering, such as for building health assessments or pavement inspections. In these applications, information on the material permittivity is important for internal structure inspection and characterization. However, in the case of a large building area, a lightweight, fast and effective permittivity measurement technique is required. In addition, the estimation method for different GPR types and range configurations must be generalized for adaptability and wide applicability. This paper proposes a material permittivity estimation technique for air-coupled GPR that effectively works for mobile and large observation missions. The method employs the peak ratio of analytic representation signals between the antenna direct coupling and the material surface reflection. An interpolation algorithm is applied to the reference characteristic curves generated by the finite-difference time-domain technique to adapt the change in radar range configuration. The proposed method has been tested to estimate the permittivity in three different construction materials and measure two metal rebar depths inside reinforced concrete. The experimental results show that the method works with acceptable accuracy. Therefore, the method is sufficiently promising to be utilized in real applications, especially those that require adaptability and mobility, such as ground and aerial vehicle-based radar systems.

1 August 2024 in Bulletin of Electrical Engineering and Informatics
Verified
Journal Article
Open access
PDF file
RIRiyandi Banovbi Putera Irsal
Riyandi Banovbi Putera Irsal
FUFitri Utaminingrum
Fitri Utaminingrum
KOKohichi Ogata
Kohichi Ogata
Highways are an important component of any country. However, some highways in Indonesia endanger users while maintaining road safety. Crack detection early in the deterioration process can prevent further damage and lower maintenance costs. A recent study sought to develop a method for detecting road damage by combining the road damage detection (RDD) dataset with generative adversarial network technology and data augmentation to improve training. The current study aims to broaden the you only look once (YOLO) framework by incorporating the Swin Transformer into the chiral stationary phases (CSP) component of YOLOv7, with the goal of improving object detection accuracy in a variety of visual scenarios. The study compares the performance of various object detection models with varying parameters and configurations, such as YOLOv5l, YOLOv6l, YOLOv7-tiny, YOLOv7, and YOLOv7x. YOLOv5l has 46 million parameters and 108 billion floating point operations per second (FLOPS), whereas YOLOv6l has 59.5 million parameters and 150 billion FLOPS. With 31 million parameters and 140 billion FLOPS, the YOLOv7-swin model performs best with mean average precision (mAP), mAP_0.50 of 0.47. and mAP_0.5:0.95 of 0.232. The experimental results show that our YOLOv7-swin model outperforms both YOLOv7x and YOLOv7-tiny. The proposed model significantly improves object detection accuracy while keeping complexity and performance in balance.

1 March 2015 in Optics & Laser Technology
Verified
Journal Article
Closed access
KOKohichi Ogata
Kohichi Ogata
SNShingo Niino
Shingo Niino

19 October 2021
Verified
Conference Paper
Closed access
MNMasahiko Nishimoto
Masahiko Nishimoto
BRBudiman Rohman
Budiman Rohman
KOKohichi Ogata
Kohichi Ogata
This paper describes phase parameter extraction from ultra-wideband (UWB) radar response and investigate the effectiveness of it for non-destructive inspection of concrete. The phase parameter introduced in this study contains information on the phase-shift of scattering by a corroded rebar and is effective for estimating the corrosion stage of the rebar. Simulation results indicate that the corrosion rate of the rebar can be estimated by using the extracted phase parameter even when the commonly used correlation coefficient is not effective.