Ryoichi Ishikawa

Dr. Ryoichi Ishikawa


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
30 June 2020 in IEEE Robotics and Automation Letters
Verified
Journal Article
Open access
YYYasuhiro Yao
Yasuhiro Yao
MRMenandro Roxas
Menandro Roxas
RIRyoichi Ishikawa
Ryoichi Ishikawa
SAShingo Ando
Shingo Ando
JSJun Shimamura
Jun Shimamura
TOTakeshi Oishi
Takeshi Oishi
We propose an unsupervised real time dense depth completion from sparse depth maps guided by a single image. Our method generates smooth depth maps while preserving discontinuity between different objects. Our key idea is a Binary Anisotropic Diffusion Tensor (B-ADT) which can completely eliminate smoothness constraint at intended positions and directions by applying variational regularization. We also propose an Image Guided Nearest Neighbor Search (IGNNS) to derive piecewise constant depth maps which are used for B-ADT derivation and in the data term of the variational energy. Our experiments show that our method can outperform previous unsupervised and semi-supervised depth completion methods in terms of accuracy. Moreover, since our resulting depth maps preserve the discontinuity between objects, the results can be converted to visually plausible point clouds. This is remarkable since previous methods generate unnatural surface-like artifacts between discontinuous objects.

5 July 2019 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
AHAtsuki Hirata
Atsuki Hirata
RIRyoichi Ishikawa
Ryoichi Ishikawa
MRMenandro Roxas
Menandro Roxas
TOTakeshi Oishi
Takeshi Oishi
In this letter, we present a method for estimating a dense depth map from a sparse LIDAR point cloud and an image sequence. Our proposed method relies on a directionally biased propagation of known depth to missing areas based on semantic segmentation. Additionally, we classify different object boundaries as either occluded or connected to limit the extent of the data propagation. At the regions with large missing point cloud data, we depend on estimated depth using motion stereo. We embed our method on a bounded interpolation strategy which also considers pixel distance, depth difference and color gradient. We then perform an optimization step based on tensor-based TGV-L2 denoising. Our results show that directional propagation and semantic boundary classification can improve the accuracy of interpolation along the edges for different types of objects. Moreover, our motion stereo scheme increases the reliability of extrapolated depth at the regions with large missing point cloud data. Finally, we show that our implementation strategy can achieve reliable results in real time.

19 March 2025 in IEEE Robotics and Automation Letters
Verified
Journal Article
Open access
SZShuyi Zhou
Shuyi Zhou
SXShuxiang Xie
Shuxiang Xie
RIRyoichi Ishikawa
Ryoichi Ishikawa
TOTakeshi Oishi
Takeshi Oishi
LiDAR-camera systems have become increasingly popular in robotics recently. A critical and initial step in integrating the LiDAR and camera data is the calibration of the LiDAR-camera system. Most existing calibration methods rely on auxiliary target objects, which often involve complex manual operations, whereas targetless methods have yet to achieve practical effectiveness. Recognizing that 2D Gaussian Splatting (2DGS) can reconstruct geometric information from camera image sequences, we propose a calibration method that estimates LiDAR-camera extrinsic parameters using geometric constraints. The proposed method begins by reconstructing colorless 2DGS using LiDAR point clouds. Subsequently, we update the colors of the Gaussian splats by minimizing the photometric loss. The extrinsic parameters are optimized during this process. Additionally, we address the limitations of the photometric loss by incorporating the reprojection and triangulation losses, thereby enhancing the calibration robustness and accuracy.

4 October 2021 in IEEE Access
Verified
Journal Article
Open access
YYYasuhiro Yao
Yasuhiro Yao
RIRyoichi Ishikawa
Ryoichi Ishikawa
SAShingo Ando
Shingo Ando
KKKana Kurata
Kana Kurata
NINaoki Ito
Naoki Ito
TOTakeshi Oishi
Takeshi Oishi
We propose a non-learning depth completion method for a sparse depth map captured using a light detection and ranging (LiDAR) sensor guided by a pair of stereo images. Generally, conventional stereo-aided depth completion methods have two limiations. (i) They assume the given sparse depth map is accurately aligned to the input image, whereas the alignment is difficult to achieve in practice. (ii) They have limited accuracy in the long range because the depth is estimated by pixel disparity. To solve the abovementioned limitations, we propose selective stereo matching (SSM) that searches the most appropriate depth value for each image pixel from its neighborly projected LiDAR points based on an energy minimization framework. This depth selection approach can handle any type of mis-projection. Moreover, SSM has an advantage in terms of long-range depth accuracy because it directly uses the LiDAR measurement rather than the depth acquired from the stereo. SSM is a discrete process; thus, we apply variational smoothing with binary anisotropic diffusion tensor (B-ADT) to generate a continuous depth map while preserving depth discontinuity across object boundaries. Experimentally, compared with the previous state-of-the-art stereo-aided depth completion, the proposed method reduced the mean absolute error (MAE) of the depth estimation to 0.65 times and demonstrated approximately twice more accurate estimation in the long range. Moreover, under various LiDAR-camera calibration errors, the proposed method reduced the depth estimation MAE to 0.34-0.93 times from previous depth completion methods.

17 March 2025 in IEEE Robotics and Automation Letters
Verified
Journal Article
Open access
YYYasuhiro Yao
Yasuhiro Yao
RIRyoichi Ishikawa
Ryoichi Ishikawa
TOTakeshi Oishi
Takeshi Oishi
We present a real-time, non-learning depth estimation method that fuses Light Detection and Ranging (LiDAR) data with stereo camera input. Our approach comprises three key techniques: Semi-Global Matching (SGM) stereo with Discrete Disparity-matching Cost (DDC), semidensification of LiDAR disparity, and a consistency check that combines stereo images and LiDAR data. Each of these components is designed for parallelization on a GPU to realize real-time performance. When it was evaluated on the KITTI dataset, the proposed method achieved an error rate of 2.79%, outperforming the previous state-of-the-art real-time stereo-LiDAR fusion method, which had an error rate of 3.05%. Furthermore, we tested the proposed method in various scenarios, including different LiDAR point densities, varying weather conditions, and indoor environments, to demonstrate its high adaptability. We believe that the real-time and non-learning nature of our method makes it highly practical for applications in robotics and automation.

13 January 2025 in IEEE Access
Verified
Journal Article
Open access
RIRyoichi Ishikawa
Ryoichi Ishikawa
TYTomohisa Yuzawa
Tomohisa Yuzawa
TFTaiki Fukiage
Taiki Fukiage
MKMasataka Kagesawa
Masataka Kagesawa
TWToru Watsuji
Toru Watsuji
TOTakeshi Oishi
Takeshi Oishi
X-ray image enhancement can aid a physician’s diagnosis by improving lesion visibility. This study proposes a chest X-ray image enhancement framework for enhancing lesion visibility while preserving image features. Our framework assesses the background signals, whereas conventional methods focus on the visibility of the global image. The proposed method predicts the image processing parameters that enhance the lesion signals via the inference neural network. The framework consists of an X-ray image enhancer and an enhanced model predictor for reference. The enhancer regressively estimates the processing parameters for enhancing the lesions using the inference network and processes the input X-ray image. As the inference network requires training, the model predictor computes the reference parameters that maximize the visibility of the lesions within a tolerable loss of fidelity using image pairs—with and without lesions. We created a synthesized dataset, with and without lesions, from healthy chest and phantom lesion X-ray images. The experiments show that after the proposed method was trained on 2000 images, it improved lesion visibility with an acceptable fidelity loss. We also performed pairwise comparisons and confirmed that trade-offs between fidelity loss and visibility gain were attained. A technique for improving lesion visibility while maintaining the fidelity of X-ray images was developed. This method enabled the enhancement of specific signals in the background. Various image processing methods that require parameters could be incorporated into this framework for many different applications.