Hock Soon Seah
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hock Soon Seah has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
- Feng Lin
China-Singapore International Joint Research Institute
7 shared publications - Budianto Tandianus
Nanyang Technological University (NTU)
5 shared publications - Henry Johan
Fraunhofer IDM@NTU
3 shared publications - Qian Kemao
Nanyang Technological University
3 shared publications - Zhongke Wu
School of Artificial Intelligence, Beijing Normal University, Beijing, China
3 shared publications - Chee Kwang Quah
ST Electronics (Training & Simulation Systems) Pte Ltd., Singapore 567714, Singapore
2 shared publications
Latest Publications
- Open Access
- 2 February 2026
- Published by Springer Nature in Journal on Advances in Signal Processing
- Vol. 2026 (1)
Fast shape recognition through dual constraint reduction and adaptive orthogonal wavelet transform
In the realm of image and vision computing, shape recognition remains challenging due to intra-class variations that can degrade performance. To address this, we propose an enhanced shape recognition method leveraging dual constraint reduction and adaptive orthogonal wavelet transform (ADCR). Firstly, we refine shape contours by reducing salient points to strong feature points (bone points), mitigating the impact of shape deformation. Secondly, we employ an adaptive orthogonal wavelet transform to ensure scale and mirror invariance, significantly accelerating recognition speed. Thirdly, we streamline the feature structure after wavelet transformation, retaining only minimum, mean, and maximum eigenvectors for efficient shape representation. Experimental results on multiple datasets demonstrate the effectiveness of our method, achieving a MAP score of 79.2% on the ICL dataset with an average recognition time of 26.9 ms, outperforming similar methods by over 200 times in efficiency. Our ADCR method significantly enhances shape recognition capabilities.
- 2 February 2026
- Published by Springer Nature in Journal on Advances in Signal Processing
- Vol. 2026 (1)
Open AccessFast shape recognition through dual constraint reduction and adaptive orthogonal wavelet transform
In the realm of image and vision computing, shape recognition remains challenging due to intra-class variations that can degrade performance. To address this, we propose an enhanced shape recognition method leveraging dual constraint reduction and adaptive orthogonal wavelet transform (ADCR). Firstly, we refine shape contours by reducing salient points to strong feature points (bone points), mitigating the impact of shape deformation. Secondly, we employ an adaptive orthogonal wavelet transform to ensure scale and mirror invariance, significantly accelerating recognition speed. Thirdly, we streamline the feature structure after wavelet transformation, retaining only minimum, mean, and maximum eigenvectors for efficient shape representation. Experimental results on multiple datasets demonstrate the effectiveness of our method, achieving a MAP score of 79.2% on the ICL dataset with an average recognition time of 26.9 ms, outperforming similar methods by over 200 times in efficiency. Our ADCR method significantly enhances shape recognition capabilities.
- 14 December 2023
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 239
MLGPnet: Multi-granularity neural network for 3D shape recognition using pyramid data
- 14 December 2023
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 239
MLGPnet: Multi-granularity neural network for 3D shape recognition using pyramid data
- Open Access
- 1 September 2023
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 9 (3) , 633-656
Shape correspondence for cel animation based on a shape association graph and spectral matching
We present an effective spectral matching method based on a shape association graph for finding region correspondences between two cel animation keyframes. We formulate the correspondence problem as an adapted quadratic assignment problem, which comprehensively considers both the intrinsic geometric and topology of regions to find the globally optimal correspondence. To simultaneously represent the geometric and topological similarities between regions, we propose a shape association graph (SAG), whose node attributes indicate the geometric distance between regions, and whose edge attributes indicate the topological distance between combined region pairs. We convert topological distance to geometric distance between geometric objects with topological features of the pairs, and introduce Kendall shape space to calculate the intrinsic geometric distance. By utilizing the spectral properties of the affinity matrix induced by the SAG, our approach can efficiently extract globally optimal region correspondences, even if shapes have inconsistent topology and severe deformation. It is also robust to shapes undergoing similarity transformations, and compatible with parallel computing techniques.
- 1 September 2023
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 9 (3) , 633-656
Open AccessShape correspondence for cel animation based on a shape association graph and spectral matching
We present an effective spectral matching method based on a shape association graph for finding region correspondences between two cel animation keyframes. We formulate the correspondence problem as an adapted quadratic assignment problem, which comprehensively considers both the intrinsic geometric and topology of regions to find the globally optimal correspondence. To simultaneously represent the geometric and topological similarities between regions, we propose a shape association graph (SAG), whose node attributes indicate the geometric distance between regions, and whose edge attributes indicate the topological distance between combined region pairs. We convert topological distance to geometric distance between geometric objects with topological features of the pairs, and introduce Kendall shape space to calculate the intrinsic geometric distance. By utilizing the spectral properties of the affinity matrix induced by the SAG, our approach can efficiently extract globally optimal region correspondences, even if shapes have inconsistent topology and severe deformation. It is also robust to shapes undergoing similarity transformations, and compatible with parallel computing techniques.
- Open Access
- 1 May 2022
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12177, 87-43
Expressive B-spline curves: a pilot study on a flexible shape representation
We present a pilot study on expressive B-spline curves (XBSC), an extension of disk B-spline curves (DBSC). XBSC facilitates expressive drawings in terms of shape and color. For shape, colors on both sides of XBSC strokes are defined independently instead of using a single parameter for both sides as in DBSC. We perform coloring by considering the envelopes of XBSC as diffusion curves. Our results show that XBSC can be used to easily draw a wide range of images with fewer number of primitives compared to previous methods.
- 1 May 2022
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12177, 87-43
Open AccessExpressive B-spline curves: a pilot study on a flexible shape representation
We present a pilot study on expressive B-spline curves (XBSC), an extension of disk B-spline curves (DBSC). XBSC facilitates expressive drawings in terms of shape and color. For shape, colors on both sides of XBSC strokes are defined independently instead of using a single parameter for both sides as in DBSC. We perform coloring by considering the envelopes of XBSC as diffusion curves. Our results show that XBSC can be used to easily draw a wide range of images with fewer number of primitives compared to previous methods.
- 11 October 2021
- Published by Springer Nature
- p. 167-177
Reinforcement Learning for Quadruped Locomotion
- 11 October 2021
- Published by Springer Nature
- p. 167-177
Reinforcement Learning for Quadruped Locomotion
- 31 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computer Graphics and Applications
- Vol. 41 (3) , 59-70
Skeleton-Based Parametric 2-D Region Representation: Disk B-Spline Curves
The skeleton, or medial axis, is an important attribute of 2-D shapes. The disk B-spline curve (DBSC) is a skeleton-based parametric freeform 2-D region representation, which is defined in the B-spline form. The DBSC describes not only a 2-D region, which is suitable for describing heterogeneous materials in the region, but also the center curve (skeleton) of the region explicitly, which is suitable for animation, simulation, and recognition. In addition to being useful for error estimation of the B-spline curve, the DBSC can be used in designing and animating freeform 2-D regions. Despite increasing DBSC applications, its theory and fundamentals have not been thoroughly investigated. In this article, we discuss several fundamental properties and algorithms, such as the de Boor algorithm for DBSCs. We first derive the explicit evaluation and derivatives formulas at arbitrary points of a 2-D region (interior and boundary) represented by a DBSC and then provide heterogeneous object representation. We also introduce modeling and interactive heterogeneous object design methods for a DBSC, which consolidates DBSC theory and supports its further applications.
- 31 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computer Graphics and Applications
- Vol. 41 (3) , 59-70
Skeleton-Based Parametric 2-D Region Representation: Disk B-Spline Curves
The skeleton, or medial axis, is an important attribute of 2-D shapes. The disk B-spline curve (DBSC) is a skeleton-based parametric freeform 2-D region representation, which is defined in the B-spline form. The DBSC describes not only a 2-D region, which is suitable for describing heterogeneous materials in the region, but also the center curve (skeleton) of the region explicitly, which is suitable for animation, simulation, and recognition. In addition to being useful for error estimation of the B-spline curve, the DBSC can be used in designing and animating freeform 2-D regions. Despite increasing DBSC applications, its theory and fundamentals have not been thoroughly investigated. In this article, we discuss several fundamental properties and algorithms, such as the de Boor algorithm for DBSCs. We first derive the explicit evaluation and derivatives formulas at arbitrary points of a 2-D region (interior and boundary) represented by a DBSC and then provide heterogeneous object representation. We also introduce modeling and interactive heterogeneous object design methods for a DBSC, which consolidates DBSC theory and supports its further applications.
- 18 October 2020
- Published by Springer Nature
- p. 394-402
Generating Orthogonal Voronoi Treemap for Visualization of Hierarchical Data
- 18 October 2020
- Published by Springer Nature
- p. 394-402
Generating Orthogonal Voronoi Treemap for Visualization of Hierarchical Data
- Open Access
Multi-View Fusion-Based 3D Object Detection for Robot Indoor Scene Perception
To autonomously move and operate objects in cluttered indoor environments, a service robot requires the ability of 3D scene perception. Though 3D object detection can provide an object-level environmental description to fill this gap, a robot always encounters incomplete object observation, recurring detections of the same object, error in detection, or intersection between objects when conducting detection continuously in a cluttered room. To solve these problems, we propose a two-stage 3D object detection algorithm which is to fuse multiple views of 3D object point clouds in the first stage and to eliminate unreasonable and intersection detections in the second stage. For each view, the robot performs a 2D object semantic segmentation and obtains 3D object point clouds. Then, an unsupervised segmentation method called Locally Convex Connected Patches (LCCP) is utilized to segment the object accurately from the background. Subsequently, the Manhattan Frame estimation is implemented to calculate the main orientation of the object and subsequently, the 3D object bounding box can be obtained. To deal with the detected objects in multiple views, we construct an object database and propose an object fusion criterion to maintain it automatically. Thus, the same object observed in multi-view is fused together and a more accurate bounding box can be calculated. Finally, we propose an object filtering approach based on prior knowledge to remove incorrect and intersecting objects in the object dataset. Experiments are carried out on both SceneNN dataset and a real indoor environment to verify the stability and accuracy of 3D semantic segmentation and bounding box detection of the object with multi-view fusion.
Open AccessMulti-View Fusion-Based 3D Object Detection for Robot Indoor Scene Perception
To autonomously move and operate objects in cluttered indoor environments, a service robot requires the ability of 3D scene perception. Though 3D object detection can provide an object-level environmental description to fill this gap, a robot always encounters incomplete object observation, recurring detections of the same object, error in detection, or intersection between objects when conducting detection continuously in a cluttered room. To solve these problems, we propose a two-stage 3D object detection algorithm which is to fuse multiple views of 3D object point clouds in the first stage and to eliminate unreasonable and intersection detections in the second stage. For each view, the robot performs a 2D object semantic segmentation and obtains 3D object point clouds. Then, an unsupervised segmentation method called Locally Convex Connected Patches (LCCP) is utilized to segment the object accurately from the background. Subsequently, the Manhattan Frame estimation is implemented to calculate the main orientation of the object and subsequently, the 3D object bounding box can be obtained. To deal with the detected objects in multiple views, we construct an object database and propose an object fusion criterion to maintain it automatically. Thus, the same object observed in multi-view is fused together and a more accurate bounding box can be calculated. Finally, we propose an object filtering approach based on prior knowledge to remove incorrect and intersecting objects in the object dataset. Experiments are carried out on both SceneNN dataset and a real indoor environment to verify the stability and accuracy of 3D semantic segmentation and bounding box detection of the object with multi-view fusion.
- Open Access
Orthogonal Voronoi Diagram and Treemap
In this paper, we propose a novel space partitioning strategy for implicit hierarchy visualization such that the new plot not only has a tidy layout similar to the treemap, but also is flexible to data changes similar to the Voronoi treemap. To achieve this, we define a new distance function and neighborhood relationship between sites so that space will be divided by axis-aligned segments. Then a sweepline+skyline based heuristic algorithm is proposed to allocate the partitioned spaces to form an orthogonal Voronoi diagram with orthogonal rectangles. To the best of our knowledge, it is the first time to use a sweepline-based strategy for the Voronoi treemap. Moreover, we design a novel strategy to initialize the diagram status and modify the status update procedure so that the generation of our plot is more effective and efficient. We show that the proposed algorithm has an O(nlog(n)) complexity which is the same as the state-of-the-art Voronoi treemap. To this end, we show via experiments on the artificial dataset and real-world dataset the performance of our algorithm in terms of computation time, converge rate, and aspect ratio. Finally, we discuss the pros and cons of our method and make a conclusion.
Open AccessOrthogonal Voronoi Diagram and Treemap
In this paper, we propose a novel space partitioning strategy for implicit hierarchy visualization such that the new plot not only has a tidy layout similar to the treemap, but also is flexible to data changes similar to the Voronoi treemap. To achieve this, we define a new distance function and neighborhood relationship between sites so that space will be divided by axis-aligned segments. Then a sweepline+skyline based heuristic algorithm is proposed to allocate the partitioned spaces to form an orthogonal Voronoi diagram with orthogonal rectangles. To the best of our knowledge, it is the first time to use a sweepline-based strategy for the Voronoi treemap. Moreover, we design a novel strategy to initialize the diagram status and modify the status update procedure so that the generation of our plot is more effective and efficient. We show that the proposed algorithm has an O(nlog(n)) complexity which is the same as the state-of-the-art Voronoi treemap. To this end, we show via experiments on the artificial dataset and real-world dataset the performance of our algorithm in terms of computation time, converge rate, and aspect ratio. Finally, we discuss the pros and cons of our method and make a conclusion.
- Open Access
Multi-Channel Convolutional Neural Network Based 3D Object Detection for Indoor Robot Environmental Perception
Environmental perception is a vital feature for service robots when working in an indoor environment for a long time. The general 3D reconstruction is a low-level geometric information description that cannot convey semantics. In contrast, higher level perception similar to humans requires more abstract concepts, such as objects and scenes. Moreover, the 2D object detection based on images always fails to provide the actual position and size of an object, which is quite important for a robot’s operation. In this paper, we focus on the 3D object detection to regress the object’s category, 3D size, and spatial position through a convolutional neural network (CNN). We propose a multi-channel CNN for 3D object detection, which fuses three input channels including RGB, depth, and bird’s eye view (BEV) images. We also propose a method to generate 3D proposals based on 2D ones in the RGB image and semantic prior. Training and test are conducted on the modified NYU V2 dataset and SUN RGB-D dataset in order to verify the effectiveness of the algorithm. We also carry out the actual experiments in a service robot to utilize the proposed 3D object detection method to enhance the environmental perception of the robot.
Open AccessMulti-Channel Convolutional Neural Network Based 3D Object Detection for Indoor Robot Environmental Perception
Environmental perception is a vital feature for service robots when working in an indoor environment for a long time. The general 3D reconstruction is a low-level geometric information description that cannot convey semantics. In contrast, higher level perception similar to humans requires more abstract concepts, such as objects and scenes. Moreover, the 2D object detection based on images always fails to provide the actual position and size of an object, which is quite important for a robot’s operation. In this paper, we focus on the 3D object detection to regress the object’s category, 3D size, and spatial position through a convolutional neural network (CNN). We propose a multi-channel CNN for 3D object detection, which fuses three input channels including RGB, depth, and bird’s eye view (BEV) images. We also propose a method to generate 3D proposals based on 2D ones in the RGB image and semantic prior. Training and test are conducted on the modified NYU V2 dataset and SUN RGB-D dataset in order to verify the effectiveness of the algorithm. We also carry out the actual experiments in a service robot to utilize the proposed 3D object detection method to enhance the environmental perception of the robot.