Ryuhei Hamaguchi

Ryuhei Hamaguchi

Auto-generated profile, based on publicly available information

Ryuhei Hamaguchi

Satellite Business Division, PASCO CORPORATION, Tokyo, Japan

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
3 December 2020 in Remote Sensing
Verified
Journal Article
Open access
PDF file
JPJi Hyun Park
Ji Hyun Park
TITakaya Inamori
Takaya Inamori
RHRyuhei Hamaguchi
Ryuhei Hamaguchi
KOKensuke Otsuki
Kensuke Otsuki
JKJung Eun Kim
Jung Eun Kim
KYKazutaka Yamaoka
Kazutaka Yamaoka
Nanosatellites are being widely used in various missions, including remote sensing applications. However, the difficulty lies in mission operation due to downlink speed limitation in nanosatellites. Considering the global cloud fraction of 67%, retrieving clear images through the limited downlink capacity becomes a larger issue. In order to solve this problem, we propose an image prioritization method based on cloud coverage using CNN. The CNN is designed to be lightweight and to be able to prioritize RGB images for nanosatellite application. As previous CNNs are too heavy for onboard processing, new strategies are introduced to lighten the network. The input size is reduced, and patch decomposition is implemented for reduced memory usage. Replication padding is applied on the first block to suppress border ambiguity in the patches. The depth of the network is reduced for small input size adaptation, and the number of kernels is reduced to decrease the total number of parameters. Lastly, a multi-stream architecture is implemented to suppress the network from optimizing on color features. As a result, the number of parameters was reduced down to 0.4%, and the inference time was reduced down to 4.3% of the original network while maintaining approximately 70% precision. We expect that the proposed method will enhance the downlink capability of clear images in nanosatellites by 112%.

1 November 2016 in Journal of Aerospace Engineering
Verified
Journal Article
Closed access
TITakaya Inamori
Takaya Inamori
RHRyuhei Hamaguchi
Ryuhei Hamaguchi
KOKouhei Ozawa
Kouhei Ozawa
PSPhongsatorn Saisutjarit
Phongsatorn Saisutjarit
NSNobutada Sako
Nobutada Sako
SNShinichi Nakasuka
Shinichi Nakasuka
Magnetic sensors are reliable, lightweight, and low power consumption sensors that are utilized in almost all nanosatellites and microsatellites for a magnetic attitude control system using magnetic torquers (MTQs). In some nanosatellites and microsatellites, magnetic sensors are utilized for magnetic moment estimation to compensate for torques owing to magnetic dipole disturbances, which are the dominant disturbances in these small satellites. To estimate the magnetic moment accurately, the errors of the magnetic sensors caused by the magnetic anomaly and bias noise from electrical devices should be estimated and compensated precisely. Although several previous studies have focused on the estimation and compensation of the errors of the magnetic sensors, the magnetic anomaly of the geomagnetic field has not been considered, even though the anomaly introduces large estimation errors. This research proposes a method to estimate the time-variable errors arising from both magnetometer bias and the ma...

10 October 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
RHRyuhei Hamaguchi
Ryuhei Hamaguchi
AFAito Fujita
Aito Fujita
KNKeisuke Nemoto
Keisuke Nemoto
This paper presents a novel Convolutional Neural Network (CNN) architecture for segmenting significantly small and crowded objects in remote sensing imagery. Although such small objects are characteristic in the remote sensing domain, the previous works mostly follow the state-of-the-art CNN models designed for ground-based images and have yet to fully explore the method for segmenting the small objects. To this end, we propose a network with no downsampling layers by utilizing dilated convolutions. We find that naive use of dilated convolutions with “increasing” dilation rates fails to capture local relationships among neighboring features, resulting in grid-like noise in the prediction. To alleviate this problem, we propose a novel scheme of “increasing-decreasing” dilation rates. Specifically, we propose a network module with decreasing dilation rates and attach it to the dilated backbone to reconnect the neighboring pixels of the backbone features. In the experiments, we evaluated the proposed model on six remote sensing datasets, where the model showed remarkably high performance, especially for small objects.

3 September 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
RHRyuhei Hamaguchi
Ryuhei Hamaguchi
This paper presents multi-branch network architecture for addressing the problem of large intra-class variation in building detection task. Previous methods solved the problem by learning single structured and shared feature space with regularization. However, we reveal that the feature sharing strategy is less advantageous at deeper layers. We have analyzed the channel-wise contribution of the deep features for recognizing individual buildings and find that the feature space is separated into several clusters, among which the discriminative features are not shared much. Based on the analysis, we propose a multi-branch neural network that solves the problem by decomposing a building class into sub-classes and learning specialized feature space for each sub-class. The proposed model is demonstrated on two remote sensing building detection benchmarks, where the model outperforms the state-of-the-art segmentation models and the previous techniques for addressing the large intra-class variation.

1 November 2026 in IEEE Robotics and Automation Letters
Verified
Journal Article
Open access
ETEisho Tsuji
Eisho Tsuji
RHRyuhei Hamaguchi
Ryuhei Hamaguchi
MOMasaki Onishi
Masaki Onishi
KSKen Sakurada
Ken Sakurada