Real-time needle shape prediction in soft-tissue based on image segmentation and particle filtering

2016 ◽  
Author(s):  
Jay Carriere ◽  
Carlos Rossa ◽  
Ronald Sloboda ◽  
Nawaid Usmani ◽  
Mahdi Tavakoli
Keyword(s):  
Image Segmentation ◽  
Soft Tissue ◽  
Real Time ◽  
Particle Filtering ◽  
Shape Prediction

A study of real-time simulation of liver of virtual surgical robot based on biologically position-based dynamic model

2021 ◽  
pp. 1-16
Author(s):  
Dan Luo ◽  
Yu Zhang ◽  
Jia Li ◽  
Jisheng Li
Keyword(s):  
Soft Tissue ◽  
Real Time ◽  
Surgical Instruments ◽  
Organic Polymer ◽  
Tetrahedral Mesh ◽  
Virtual Surgery ◽  
Constraint Force ◽  
Real Time Simulation ◽  
Time Simulation ◽  
Spring Force

Virtual surgery robot can accurately modeling of surgical instruments and human organs, and realistic simulation of various surgical phenomena such as deformation of organic tissues, surgery simulation system can provide operators with reusable virtual training and simulation environment. To meet the requirement of virtual surgery robot for the authenticity and real-time of soft tissue deformation and surgical simulation in liver surgery, a new method is proposed to simulate the deformation of soft tissue. This method combines the spring force, the external force of the system, and the constraint force produced by the constraint function of the position-based dynamics. Based on the position-based dynamics, an improved three-parameter mass-spring model is added. In the calculation of the elastic force, the nonlinearity and viscoelasticity of the soft tissue are introduced, and the joint force of the constraint projection process and the constraint force of the position-based dynamics is used to modify mass points movement. The method of position-based dynamics based on biological characteristics, not only considers the biomechanical properties of biological soft tissue as an organic polymer such as viscoelasticity, nonlinearity, and incompressibility but also retains the rapidity and stability of the position based dynamic method. Through the simulation data, the optimal side length of tetrahedral mesh in the improved three-parameter model is obtained, and the physical properties of the model are proved. The real-time simulation of the liver and other organs is completed by using the Geomagic touch force feedback device, which proves the practicability and effectiveness of this method.

Near-Band IR Small Scene Star Image Segmentation Based on Partial Histogram Grey Level

2014 ◽  
Vol 496-500 ◽  
pp. 1834-1839
Author(s):  
Zhe Wang ◽  
Zhe Yan ◽  
Wei Tan
Keyword(s):  
Image Processing ◽  
Image Segmentation ◽  
Real Time ◽  
Grey Level ◽  
Star Image ◽  
Star Images

The near-band IR star images segmentation and recognition is key technique in day time star navigation. Due to the scene of near-band IR star imaging relative small and stellar with high star grade are limited. Pertinence and dynamic grey level threshold is necessary for image processing arithmetic. In order to enhance near-band IR star images segmentation and recognition in real-time, this paper present the process of partial histogram grey level threshold and improve for actually near-band IR star images with scene of no more than 1.5°×1.5°. It can reduce the calculation of near-band IR star images with adjustable threshold. And get rid of disturbance of small imaging square stars and noise points.

Real Time Interactive Image Segmentation Using User Indicated Real-World Seeds

2012 ◽  
Author(s):  
Rafael Beserra Gomes ◽  
Rafael Vidal Aroca ◽  
Bruno Motta de Carvalho ◽  
Luiz Marcos Garcia Goncalves
Keyword(s):  
Image Segmentation ◽  
Real Time ◽  
Real World ◽  
Interactive Image Segmentation

scholarly journals A Multiobjective Piglet Image Segmentation Method Based on an Improved Noninteractive GrabCut Algorithm

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Feilong Kang ◽  
Chunguang Wang ◽  
Jia Li ◽  
Zheying Zong
Keyword(s):  
Image Segmentation ◽  
Real Time ◽  
Monitoring System ◽  
Structural Similarity ◽  
Morphological Processing ◽  
Video Monitoring ◽  
Segmentation Method ◽  
Time Requirements ◽  
And Behavior ◽  
Grabcut Algorithm

In the video monitoring of piglets in pig farms, study of the precise segmentation of foreground objects is the work of advanced research on target tracking and behavior recognition. In view of the noninteractive and real-time requirements of such a video monitoring system, this paper proposes a method of image segmentation based on an improved noninteractive GrabCut algorithm. The functions of preserving edges and noise reduction are realized through bilateral filtering. An adaptive threshold segmentation method is used to calculate the local threshold and to complete the extraction of the foreground target. The image is simplified by morphological processing; the background interference pixels, such as details in the grille and wall, are filtered, and the foreground target marker matrix is established. The GrabCut algorithm is used to split the pixels of multiple foreground objects. By comparing the segmentation results of various algorithms, the results show that the segmentation algorithm proposed in this paper is efficient and accurate, and the mean range of structural similarity is [0.88, 1]. The average processing time is 1606 ms, and this method satisfies the real-time requirement of an agricultural video monitoring system. Feature vectors such as edges and central moments are calculated and the database is well established for feature extraction and behavior identification. This method provides reliable foreground segmentation data for the intelligent early warning of a video monitoring system.

scholarly journals MSPPNet: A Lightweight Network for Real-time Semantic Image Segmentation

2021 ◽  
Vol 2010 (1) ◽  
pp. 012128
Author(s):  
Yuting Liang ◽  
Tangtian Hang ◽  
Jie Chen ◽  
Lei Liu
Keyword(s):  
Image Segmentation ◽  
Real Time ◽  
Semantic Image Segmentation
Sign in / Sign up

Export Citation Format

Share Document