LRF-Net: Learning Local Reference Frames for 3D Local Shape Description and Matching

Zhu, Aijun; Yang, Jiaqi; Zhao, Weiyue; Cao, Zhiguo

doi:10.3390/s20185086

Cited by 8 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, LRFs have been developed and can be categorized into CA-Based [ 15 , 16 , 32 , 33 ], GA-Based [ 19 , 30 , 31 , 34 ], and Mix-Based [ 29 , 35 ]. The initial proposal of a reference frame to achieve rotational invariance of the descriptor was made by Mian [ 33 ].…”

Section: Related Workmentioning

confidence: 99%

SliceLRF: A Local Reference Frame Sliced along the Height on the 3D Surface

Zhong

Liu

2023

Sensors

View full text Add to dashboard Cite

The local reference frame (LRF) plays a vital role in local 3D shape description and matching. Numerous LRF methods have been proposed in recent decades. However, few LRFs can achieve a balance between repeatability and robustness under exposure to a variety of nuisances, including Gaussian noise, mesh resolution variation, clutter, and occlusion. Additionally, most LRFs are heuristic and lack generalizability to different applications and data modalities. In this paper, we first define the degree of distinction to describe the distribution of 2D point clouds and explore the relationship between the relative deviation of the distinction degree and the LRF error through experiments. Based on Gaussian noise and a random sampling analysis, several factors that affect the relative deviation of the distinction degree and result in the LRF error are identified. A scoring criterion is proposed to evaluate the robustness of the point cloud distribution. On this basis, we propose an LRF method (SliceLRF) based on slicing along the Z-axis, which selects the most robust adjacent slices in the point cloud region by scoring criteria for X-axis estimation to improve the repeatability and robustness. SliceLRF is rigorously tested on four public benchmark datasets which have different applications and involve different data modalities. It is also compared with the state-of-the-art LRFs. The experimental results show that the SliceLRF has more comprehensive repeatability and robustness than the other LRFs under exposure to Gaussian noise and random sampling.

show abstract

Section: Related Workmentioning

confidence: 99%

SliceLRF: A Local Reference Frame Sliced along the Height on the 3D Surface

Zhong

Liu

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…With modern vision devices, such as Microsoft Kinect and Intel RealSense, more information of the objects in the working scene could be obtained easily through perceiving systems. The depth-based 6-DoF grasping methods lead the research direction, and most of them are focused on 6D object pose perceiving [ 2 , 3 ]. Researchers also focus on the combination with deep learning to further improve intelligent perceiving [ 4 , 5 ].…”

Section: Introductionmentioning

confidence: 99%

Vision‐Based Intelligent Perceiving and Planning System of a 7‐DoF Collaborative Robot

Song

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In this paper, an intelligent perceiving and planning system based on deep learning is proposed for a collaborative robot consisting of a 7-DoF (7-degree-of-freedom) manipulator, a three-finger robot hand, and a vision system, known as IPPS (intelligent perceiving and planning system). The lack of intelligence has been limiting the application of collaborative robots for a long time. A system to realize “eye-brain-hand” process is crucial for the true intelligence of robots. In this research, a more stable and accurate perceiving process was proposed. A well-designed camera system as the vision system and a new hand tracking method were proposed for operation perceiving and recording set establishment to improve the applicability. A visual process was designed to improve the accuracy of environment perceiving. Besides, a faster and more precise planning process was proposed. Deep learning based on a new CNN (convolution neural network) was designed to realize intelligent grasping planning for robot hand. A new trajectory planning method of the manipulator was proposed to improve efficiency. The performance of the IPPS was tested with simulations and experiments in a real environment. The results show that IPPS could effectively realize intelligent perceiving and planning for the robot, which could realize higher intelligence and great applicability for collaborative robots.

show abstract