• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.10
• /
• pp.2163-2170
• /
• 2009

We present an automated, energy minimized-based method for Lung parenchyma segmenting Chest Computed Tomography(CT) datasets. Deformable model is used for energy minimized segmentation. Quantitative knowledge including expected volume, shape of Chest CT provides more feature constrain to diagnosis or surgery operation planning. Segmentation subdivides an lung image into its consistent regions or objects. Depends on energy-minimizing, the level detail image of subdivision is carried. Segmentation should stop when the objects or region of interest in an application have been detected. The deformable model that has attracted the most attention to date is popularly known as snakes. Snakes or deformable contour models represent a special case of the general multidimensional deformable model theory. This is used extensively in computer vision and image processing applications, particularly to locate object boundaries, in the mean time a new type of external force for deformable models, called gradient vector flow(GVF) was introduced by Xu. Our proposed algorithm of deformable model is new external energy of GVF for exact segmentation. In this paper, Clinical material for experiments shows better results of proposal algorithm in Lung parenchyma segmentation on Chest CT.

• 한국HCI학회:학술대회논문집
• /
• 2007.02c
• /
• pp.306-317
• /
• 2007

We present an interactive and accurate collision detection algorithm for deformable, polygonal objects based on the streaming computational model. Our algorithm can detect all possible pairwise primitive-level intersections between two severely deforming models at highly interactive rates. In our streaming computational model, we consider a set of axis aligned bounding boxes (AABBs) that bound each of the given deformable objects as an input stream and perform massively-parallel pairwise, overlapping tests onto the incoming streams. As a result, we are able to prevent performance stalls in the streaming pipeline that can be caused by expensive indexing mechanism required by bounding volume hierarchy-based streaming algorithms. At run-time, as the underlying models deform over time, we employ a novel, streaming algorithm to update the geometric changes in the AABB streams. Moreover, in order to get only the computed result (i.e., collision results between AABBs) without reading back the entire output streams, we propose a streaming en/decoding strategy that can be performed in a hierarchical fashion. After determining overlapped AABBs, we perform a primitive-level (e.g., triangle) intersection checking on a serial computational model such as CPUs. We implemented the entire pipeline of our algorithm using off-the-shelf graphics processors (GPUs), such as nVIDIA GeForce 7800 GTX, for streaming computations, and Intel Dual Core 3.4G processors for serial computations. We benchmarked our algorithm with different models of varying complexities, ranging from 15K up to 50K triangles, under various deformation motions, and the timings were obtained as 30~100 FPS depending on the complexity of models and their relative configurations. Finally, we made comparisons with a well-known GPU-based collision detection algorithm, CULLIDE [4] and observed about three times performance improvement over the earlier approach. We also made comparisons with a SW-based AABB culling algorithm [2] and observed about two times improvement.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.4120-4132
• /
• 2017

In this research, we implement a deformable object simulation system using OpenGL's shader language, GLSL4.3. Deformable object simulation is implemented by using volumetric mass-spring system suitable for real-time simulation among the methods of deformable object simulation. The compute shader in GLSL 4.3 which helps to access the GPU resources, is used to parallelize the operations of existing deformable object simulation systems. The proposed system is implemented using a compute shader for parallel processing and it includes a bounding box-based collision detection solution. In general, the collision detection is one of severe computing bottlenecks in simulation of multiple deformable objects. In order to validate an efficiency of the system, we performed the experiments using the 3D volumetric objects. We compared the performance of multiple deformable object simulations between CPU and GPU to analyze the effectiveness of parallel processing using GLSL. Moreover, we measured the computation time of bounding box-based collision detection to show that collision detection can be processed in real-time. The experiments using 3D volumetric models with 10K faces showed the GPU-based parallel simulation improves performance by 98% over the CPU-based simulation, and the overall steps including collision detection and rendering could be processed in real-time frame rate of 218.11 FPS.

• Journal of the Korea Computer Graphics Society
• /
• v.6 no.1
• /
• pp.19-27
• /
• 2000

This paper proposes a non-self-intersecting multiresolution deformable model to extract and reconstruct three-dimensional boundaries of objects from volumetric data. Deformable models offer an attractive method for extracting and reconstructing the boundary surfaces. However, convensional deformable models have three limitations- sensitivity to model initialization, difficulties in dealing with severe object concavities, and model self-intersections. We address the initialization problem by multiresolution model representation, which progressively refines the deformable model based on multiresolution volumetric data in order to extract the boundaries of the objects in a coarse-to-fine fashion. The concavity problem is addressed by mesh size regularization, which matches its size to the unit voxel of the volumetric data. We solve the model self-intersection problem by including a non-self-intersecting force among the customary internal and external forces in the physics-based formulation. This paper presents results of applying our new deformable model to extracting a sphere surface with concavities from a computer-generated volume data and a brain cortical surface from a MR volume data.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.11
• /
• pp.589-600
• /
• 2002

Deformable models offer an attractive approach for extracting three-dimensional boundary structures from volumetric images. However, conventional deformable models have three major limitations - sensitive to initial condition, difficult to represent complex boundaries with severe object concavities and protrusions, and self-intersective between model elements. This paper proposes a deformable model that is effective to extract geometrically complex boundary surfaces by improving away the limitations of conventional deformable models. First, the proposed deformable model resamples its elements hierarchically based on volume image pyramid. The hierarchical resampling overcomes sensitivity to initialization by extracting the boundaries of objects in a multiscale scheme and enhances geometric flexibility to be well adapted to complex image features by refining and regularizing the size of model elements based on voxel size. Second, the physics-based formulation of our model integrates conventional internal and external forces, as well as a non-self-intersecting force. The non-self-intersecting force effectively prevents collision or crossing over between non-neighboring model elements by pushing each other apart if they are closer than a limited distance. We show that the proposed model successively extracts the complex boundaries including severe concavities and protrusions, neither depending on initial position nor causing self-intersection, through the experiments on several computer-generated volume images and brain MR volume images.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.183-188
• /
• 2007

In this paper, we propose a 2D-FE model in single impact with combined physical factors to obtain a unique residual stress by shot peening. Applied physical parameters include elastic-plastic deformation of shot ball, material damping coefficients, strain rate, dynamic friction coefficients. Single impact FE model consists of 2D axisymmetric elements. The FE model with combined factors showed converged and unique distributions of surface stress, maximum compressive residual stress and deformation depth. Further, in contrast to the FE models with rigid shot and elastic deformable shot, FE model with plastic deformable shot produces residual stresses very close to experimental solutions by X-ray diffraction. We therefore validated the 2D FE model with combined peeing factors and plastic deformable shot. This FE model will be a base of the 3D FE model for residual stresses by multi-impact shot peening.

• Journal of Broadcast Engineering
• /
• v.25 no.3
• /
• pp.362-373
• /
• 2020

Recently, as autonomous vehicles and intelligent CCTV are growing more interest, the efficient object detection is essential technique. The DPM(Deformable Part Models) which is basis of this paper have used a typical object system that represents highly variable objects using mixtures of deformable part for object. Although it shows high detection performance by capturing part shape and configuration of object model, but it is limited to use in real application due to the complicated algorithm. In this paper, instead of image feature pyramid that takes up a large amount of computation in one part of the detector, we propose a method to reduce the computation speed by reconstructing a new image feature pyramid that uses adaptive bilinear interpolation of feature maps obtained on a specific image scale. As a result, the detection performance for object was lowered a little by 2.82%, however, the proposed detection method improved the speed performance by 10% in comparison with original DPM.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.31 no.8
• /
• pp.855-861
• /
• 2007

Haptic rendering is a process providing force feedback during interactions between a user and a virtual object. This paper presents a real-time haptic rendering technique for deformable objects based on visual information of intervention between a tool and a real object in a remote place. A user can feel the artificial reaction force through a haptic device in real-time when a slave system exerts manipulation tasks on a deformable object. The models of the deformable object and the manipulator are created from the captured image obtained with a CCD camera and the recognition of objects is achieved using image processing techniques. The force at a rate of 1 kHz for stable haptic interaction is deduced using extrapolation of forces at a low update rate. The rendering algorithm developed was tested and validated on a test platform consisting of a one-dimensional indentation device and an off-the shelf force feedback device. This software system can be used in a cellular manipulation system providing artificial force feedback to enhance a success rate of operations.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2002.10a
• /
• pp.70-77
• /
• 2002

Since our physical world cannot be modeled as rigid body, deformable object models are important. For real-time simulation of elastic object, it must be guaranteed by its exact solution and low-latency computational cost. In this paper, we describe the boundary integral equation formulation of linear elastic body and related boundary element method(BEM). The deformation of elastic body can be effectively solved with 1ow run-time computational costs, using precomputed Green Function and fast low-rank updates based on Capacitance Matrix Algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.3
• /
• pp.25-33
• /
• 2023

Noise generated during the acquisition and transmission of CT images acts as a factor that degrades image quality. Therefore, noise removal to solve this problem is an important preprocessing process in image processing. In this paper, we remove noise by using a deformable convolutional autoencoder (DeCAE) model in which deformable convolution operation is applied instead of the existing convolution operation in the convolutional autoencoder (CAE) model of deep learning. Here, the deformable convolution operation can extract features of an image in a more flexible area than the conventional convolution operation. The proposed DeCAE model has the same encoder-decoder structure as the existing CAE model, but the encoder is composed of deformable convolutional layers and the decoder is composed of conventional convolutional layers for efficient noise removal. To evaluate the performance of the DeCAE model proposed in this paper, experiments were conducted on CT images corrupted by various noises, that is, Gaussian noise, impulse noise, and Poisson noise. As a result of the performance experiment, the DeCAE model has more qualitative and quantitative measures than the traditional filters, that is, the Mean filter, Median filter, Bilateral filter and NL-means method, as well as the existing CAE models, that is, MAE (Mean Absolute Error), PSNR (Peak Signal-to-Noise Ratio) and SSIM. (Structural Similarity Index Measure) showed excellent results.