HMHuan Ma

Huan Ma

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Huan Ma has a total of 3 co-authors. Here are the top co-authors by number of shared publications:

  • Jingjing Ji

    State Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan, China

    3 shared publications
  • Bangyan Niu

    State Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan, China

    1 shared publication
  • Yuting Liu

    State Key Lab of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, China

    1 shared publication

Latest Publications

  • A Mesh-Type Topology Pattern for Robust Marker Tracking in Visuotactile Sensor

    by Huan Ma, Bangyan Niu, Jingjing Ji

    Visuotactile sensors (VTS) perceive the tactile information through the elastomer deformation captured by the embedded camera. Markers are commonly added to the elastomer surface for VTS to get physical process sensing capabilities, whatever the imaging environment. Consequently, the success of marker tracking is a prerequisite for VTS perception. Marker missing and mismatching become one of the biggest limitations of VTS performance improvement. In this paper, a mesh-type topology pattern-based frame-independent marker tracking method is proposed to enhance the tracking robustness, particularly when large deformation occurs. The mesh pattern provides connectivity between different markers and the corresponding algorithm fully utilizes the inherent topological relations of all neighboring markers within the mesh for marker tracking. The effectiveness of the proposed method is validated both numerically and experimentally. The tracking accuracy is qualitatively analyzed by comparing it with traditional tracking methods and further evaluated based on a VTS prototype. Results confirmed that the proposed method significantly enhances the tracking robustness under large deformations and its compatibility with texture perception in photometric stereo environment.

  • Full-Array Markers Tracking Adapted to Large Contact Distortion in Visuotactile Sensing

    by Huan Ma, Jingjing Ji

    Visuotactile sensors (VTS) achieve tactile sensing based on camera-captured images, where the problem of losing markers during tracking may lead to inferior sensor performance. This paper proposes a methodology adapted to large contact distortion in VTS sensing, including the geometric constrained marker pattern design, and the dynamic full-array markers tracking method. The tracking method couples the traditional sparse optical flow (SOF) and the lost marker relocation algorithm, thus it maintains high accuracy in the non-contact region, while the complementary markers are patched in the contact region ensuring the integrity of tracking markers when localized large distortion occurs. Based on the numerical benchmark, the proposed method is compared with the conventional SOF method (two marker patterns with array or checkerboard markers). The results show that, in the case of large deformation, the leakage rate of the tracking markers with the proposed method (0%) is significantly lower compared to that of SOF methods (>10%). Furthermore, a compact binocular VTS is prototyped, where the press-release tests with multiple types of objects are performed, and the contact sensing performance is analyzed. Full-array markers can be tracked dynamically with root mean square error of tracking at the sub-pixel level (0.26 pixels). In terms of dynamic force sensing, the proposed method is capable of tracking sudden changes in contact force by relocating the lost markers, whereas the traditional methods are usually ineffective.


  • Open Access

    Model-Based 3D Contact Geometry Perception for Visual Tactile Sensor

    by Jingjing Ji, Yuting Liu, Huan Ma

    Tactile sensing plays an important role for robots’ perception, but the existing tactile technologies have multiple limitations. Visual-tactile sensor (VTS) is a newly developed tactile detector; it perceives the contacting surface shape, or even more refined texture, by way of the contact deformation image captured by a camera. A conventional visual perception is usually formulated as a data processing. It suffers issues of cumbersome training set and complicated calibration procedures. A novel model-based depth perceptual scheme is proposed where a mapping from the image intensity to the contact geometry is mathematically formulated with an associated tailored fast solver. The hardware calibration requires single image only, leading to an outstanding algorithmic robustness. The non-uniformity of the illumination condition is embodied by the stereo model, resulting in a robust depth perception precision. Compression tests on a prototype VTS showed the method’s capability in high-quality geometry reconstruction. Both contacting shape and texture were captured at a root-mean-square error down to a sub-millimeter level. The feasibility of the proposed in a pose estimation application is further experimentally validated. The associated tests yielded estimation errors that were all less than 3° in terms of spatial orientation and all less than 1mm in terms of translation.