Masahiro Hirano

Dr. Masahiro Hirano


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
31 May 2022 in Sensors
Verified
Journal Article
Open access
PDF file
SQShengjiang QUAN
Shengjiang QUAN
XLXiao Liang
Xiao Liang
HZHairui Zhu
Hairui Zhu
MHMasahiro Hirano
Masahiro Hirano
YYYuji Yamakawa
Yuji Yamakawa
Although they have been under development for years and are attracting a lot of attention, vision-based tactile sensors still have common defects—the use of such devices to infer the direction of external forces is poorly investigated, and the operating frequency is too low for them to be applied in practical scenarios. Moreover, discussion of the deformation of elastomers used in vision-based tactile sensors remains insufficient. This research focuses on analyzing the deformation of a thin elastic layer on a vision-based tactile sensor by establishing a simplified deformation model, which is cross-validated using the finite element method. Further, this model suggests a reduction in the number of markers required by a vision-based tactile sensor. In subsequent testing, a prototype HiVTac is fabricated, and it demonstrates superior accuracy to its vision-based tactile sensor counterparts in reconstructing an external force. The average error of inferring the direction of external force is 0.32∘, and the root mean squared error of inferring the magnitude of the external force is 0.0098 N. The prototype was capable of working at a sampling rate of 100 Hz and a processing frequency of 1.3 kHz, even on a general PC, allowing for real-time reconstructions of not only the direction but also the magnitude of an external force.

15 August 2023 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
JSJunzhe Su
Junzhe Su
MHMasahiro Hirano
Masahiro Hirano
YYYuji Yamakawa
Yuji Yamakawa
This paper proposes an online method for calibrating the orientation of cameras mounted on vehicles. To calibrate the orientation of the target camera relative to the vehicle, we propose using a high-speed vision sensor, focused on the ground, in conjunction with the target camera. First, the high-speed camera's planar motion parallel to ground plane and target camera's motion are estimated by a semi-dense approach and visual odometry method, respectively. Then, the motions are used to calibrate the target camera's orientation through nonlinear optimization based on the invariance constraint of the extrinsic parameters and the nonholonomic constraint of the vehicle. Unlike traditional methods, this approach does not depend on artificial features such as lane markings and utilizes ground information more efficiently, making it applicable in broader scenarios. Simulation and field tests have demonstrated that the target camera orientation calibration errors are approximately 1°, even on a bumpy road, affirming the accuracy and robustness of the proposed method.

20 October 2022 in Journal of Robotics and Mechatronics
Verified
Journal Article
Open access
XLXiao Liang
Xiao Liang
MHMasahiro Hirano
Masahiro Hirano
YYYuji Yamakawa
Yuji Yamakawa
Object tracking and pose estimation have always been challenging tasks in robotics, particularly for rotating objects. Rotating objects move quickly and with complex pose variations. In this study, we introduce a marker-based tracking and pose estimation method for rotating objects using a high-speed vision system. The method can obtain pose information at frequencies greater than 500 Hz, and can still estimate the pose when parts of the markers are lost during tracking. A robot catching experiment shows that the accuracy and frequency of this system are capable of high-speed tracking tasks.

4 March 2026 in Robotics
Verified
Journal Article
Open access
PDF file
CYChunxin Yang
Chunxin Yang
RJRuoyu Jia
Ruoyu Jia
QGQitong Guo
Qitong Guo
XSXiaohang Shi
Xiaohang Shi
MHMasahiro Hirano
Masahiro Hirano
YYYuji Yamakawa
Yuji Yamakawa
Most existing research in human pose estimation focuses on predicting joint positions, paying limited attention to recovering the full 6D human pose, which comprises both 3D joint positions and bone orientations. Position-only methods treat joints as independent points, often resulting in structurally implausible poses and increased sensitivity to depth ambiguities—cases where poses share nearly identical joint positions but differ significantly in limb orientations. Incorporating bone orientation information helps enforce geometric consistency, yielding more anatomically plausible skeletal structures. Additionally, many state-of-the-art methods rely on large, computationally expensive models, which limit their applicability in real-time scenarios, such as human–robot collaboration. In this work, we propose STAG-Net, a novel 2D-to-6D lifting network that integrates Graph Convolutional Networks (GCNs), attention mechanisms, and Temporal Convolutional Networks (TCNs). By simultaneously learning joint positions and bone orientations, STAG-Net promotes geometrically consistent skeletal structures while remaining lightweight and computationally efficient. On the Human3.6M benchmark, STAG-Net achieves an MPJPE of 41.8 mm using 243 input frames. In addition, we introduce a lightweight single-frame variant, STG-Net, which achieves 50.8 mm MPJPE while operating in real time at 60 FPS using a single RGB camera. Extensive experiments on multiple large-scale datasets demonstrate the effectiveness and efficiency of the proposed approach.

22 April 2026 in IEEE Access
Verified
Journal Article
Open access
JSJunzhe Su
Junzhe Su
MHMasahiro Hirano
Masahiro Hirano
YYYuji Yamakawa
Yuji Yamakawa
Accurate velocity estimation plays a key role in ensuring precise motion control and safe navigation of ground robots. Ground-view event cameras provide a reliable sensing modality for this task. They exploit the static and stable nature of the ground, together with the sensor’s high temporal resolution, to extract motion cues robustly even under challenging environments such as scene dynamics. Building on this observation, this paper proposes a novel velocity estimation method for ground robots using a ground-view event camera, whose application in a ground-looking configuration has received limited attention, and leverages a spiking neural network to process event-based visual information. The neural network exploits its intrinsic temporal dynamics to infer motion directly from ground texture event streams, eliminating the need for long-term event accumulation. The recurrence of output spikes is also integrated into the network to aid in preserving past sequential information. To address the challenge of costly hyperparameter tuning associated with the conventional loss function, we propose a novel geometric loss function that automatically balances translation and rotation by utilizing the differences between the coordinates of events, warped by the predicted and ground-truth motion, as the loss, thereby leading to more balanced learning across outputs and more accurate motion estimation. Experiment results on both synthetic and real-world data demonstrate that the proposed method not only can effectively handle diverse ground surface textures and variations in the camera’s pose relative to the ground, but also generalizes well to real-world scenarios, even when the network is trained exclusively on synthetic data.

1 January 2019 in The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)
Verified
Journal Article
Closed access
PDF file
MHMasahiro Hirano
Masahiro Hirano
YKYota Kaiho
Yota Kaiho
TSTaku Senoo
Taku Senoo
NKNorimasa Kishi
Norimasa Kishi
MIMasatoshi Ishikawa
Masatoshi Ishikawa
We propose an absolute velocity estimation method of surrounding objects using stereo high-speed vision. Surrounding objects are detected and tracked at high-speed by stereo inverse perspective mapping (stereo IPM), meanwhile relative positions are estimated. Relative positions at two adjacent frames are transformed to the same coordinates by using ego-motion information to compute absolute velocity. Ego-motion is estimated by computing relative motion against the ground surface using vacant area detected by stereo IPM to achieve robust and accurate estimation. We demonstrated the proposed method greatly improved the accuracy of absolute velocity estimation through experiments in a vehicle scenario.