- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[ACM Press the 10th International Conference - Nanjing, China (2018.08.17-2018.08.19)] Proceedings of the 10th International Conference on Internet Multimedia Computing and Service - ICIMCS '18 - Joint segmentation and registration for 4D lung CT images based on Markov random field
摘要： The study of segmentation and registration of lung volume in medical images has been an active area with the emergence and development of 4D CT (Computed Tomography) medical imaging techniques. Precise image segmentation and registration methods are becoming more and more important in computer-aided diagnosis and treatment. Despite the significant progress which has been made in the medical image segmentation and registration, lung segmentation and registration is still a challenging task. In this paper, a joint segmentation and registration method for 4D lung CT images is proposed, which extends a general simultaneous segmentation and registration framework based on MRF (Markov Random Field) and utilizes the segmentation results of one frame as an atlas for the initialization step. Furthermore, a stochastic sampling approach is introduced for the computation of registration similarity measurement. The proposed method is evaluated on a public lung CT data set and the experimental results show its improved performance compared with the conventional methods.
关键词： Markov Random Field,Registration,4D Image Processing,Lung CT,Segmentation
更新于2025-09-23 15:23:52
-
[IEEE 2018 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) - Poznan, Poland (2018.9.19-2018.9.21)] 2018 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) - Hardware implementation of the Gaussian Mixture Model foreground object segmentation algorithm working with ultra-high resolution video stream in real-time
摘要： In this paper a hardware implementation of the Gaussian Mixture Model algorithm for background modelling and foreground object segmentation is presented. The proposed vision system is able to handle video stream with resolution up to 4K (3840x2160 pixels) and 60 frames per second. Moreover, the constraints caused by memory bandwidth limit are also discussed and a few different solutions to tackle this issue have been considered. The designed modules have been verified on the ZCU102 development board with Xilinx Zynq UltraScale+ MPSoC device. Additionally, the computing performance and power consumption have been estimated.
关键词： FPGA,4K video,background modelling,real-time processing,GPU,Gaussian Mixture Model,foreground object segmentation
更新于2025-09-23 15:23:52
-
Multiple deep-belief-network-based spectral-spatial classification of hyperspectral images
摘要： A deep-learning-based feature extraction has recently been proposed for HyperSpectral Images (HSI) classification. A Deep Belief Network (DBN), as part of deep learning, has been used in HSI classification for deep and abstract feature extraction. However, DBN has to simultaneously deal with hundreds of features from the HSI hyper-cube, which results into complexity and leads to limited feature abstraction and performance in the presence of limited training data. Moreover, a dimensional-reduction-based solution to this issue results in the loss of valuable spectral information, thereby affecting classification performance. To address the issue, this paper presents a Spectral-Adaptive Segmented DBN (SAS-DBN) for spectral-spatial HSI classification that exploits the deep abstract features by segmenting the original spectral bands into small sets/groups of related spectral bands and processing each group separately by using local DBNs. Furthermore, spatial features are also incorporated by first applying hyper-segmentation on the HSI. These results improved data abstraction with reduced complexity and enhanced the performance of HSI classification. Local application of DBN-based feature extraction to each group of bands reduces the computational complexity and results in better feature extraction improving classification accuracy. In general, exploiting spectral features effectively through a segmented-DBN process and spatial features through hyper-segmentation and integration of spectral and spatial features for HSI classification has a major effect on the performance of HSI classification. Experimental evaluation of the proposed technique on well-known HSI standard data sets with different contexts and resolutions establishes the efficacy of the proposed techniques, wherein the results are comparable to several recently proposed HSI classification techniques.
关键词： hyperspectral image classification,support vector machine,deep belief network,segmentation
更新于2025-09-23 15:23:52
-
Ant Colony Optimization and image model-based robot manipulator system for pick-and-place tasks
摘要： A visual servo control system combines with the model-based image segmentation and an Ant Colony Optimization (ACO) algorithm to design an excellent six-Degree-of-Freedom (6-DOF) robot manipulator for solving the complicated combinations of pick-and-place tasks. A simple but efficient vision-based segmentation methodology is developed to extract the object information by getting appropriate feature of the controlled platform when the robot is tracking the manipulated image patterns. The evolutionary ACO learning algorithm explores the near-optimal path selections to drive the 6 DOF robot arm kinematics model for completing the Pick-and-Place tasks as soon as possible. Inverse orientation kinematic machine is proposed to successfully guide the robot manipulator into the desired position. Several software simulations include image segmentations, the shortest path selection, and the performance validation in various experiments. These results are described and presented to demonstrate that the designed image model-based robot manipulator wins the excellent Pick-and-Place task. Not only the software simulation, the practical robot synchronously performed in real-world to reach the higher feasible functions in the eye-to-hand experiments.
关键词： image segmentation,pick-and-place task,Ant Colony Optimization,eye-to-hand,Robot manipulator
更新于2025-09-23 15:23:52
-
Segmentation of Sloped Roofs from Airborne LiDAR Point Clouds Using Ridge-Based Hierarchical Decomposition
摘要： This paper presents a new approach for roof facet segmentation based on ridge detection and hierarchical decomposition along ridges. The proposed approach exploits the fact that every roof can be composed of a set of gabled roofs and single facets which are separated by the gabled roofs. In this work, firstly, building footprints stored in OpenStreetMap are used to extract 3D points on roofs. Then, roofs are segmented into roof facets. The algorithm starts with detecting roof ridges using RANSAC since they are parallel to the horizon and situated on the top of the roof. The roof ridges are utilized to indicate the location and direction of the gabled roof. Thus, points on the two roof facets along a roof ridge can be identified based on their connectivity and coplanarity. The results of the segmentation benefit the further process of roof reconstruction because many parameters, including the position, angle and size of the gabled roof can be calculated and used as priori knowledge for the model-driven approach, and topologies among the point segments are made known for the data-driven approach. The algorithm has been validated in the test sites of two towns next to Bavaria Forest national park. The experimental results show that building roofs can be segmented with both high correctness and completeness simultaneously.
关键词： OpenStreetMap,building roof,LiDAR,segmentation
更新于2025-09-23 15:23:52
-
Segmentation for remote-sensing imagery using the object-based Gaussian-Markov random field model with region coefficients
摘要： The Markov random ?eld (MRF) model is a widely used method for remote-sensing image segmentation, especially the object-based MRF (OMRF) method has attracted great attention in recent years. However, the OMRF method usually fails to capture the correlation between regional features by just considering the mixed-Gaussian model. In order to solve this problem and improve the segmentation accuracy, this article proposes a new method, object-based Gaussian-Markov random ?eld model with region coe?cients (OGMRF-RC), for remote-sensing image segmentation. First, to describe the complicated interactions among regional features, the OGMRF-RC method employs the region size and edge information as region coe?cients to build the each object-based region. Second, the classic Gaussian-Markov model is extended to region level for modelling the errors in OLREs. Finally, the segmentation is achieved through a principled probabilistic inference designed for the OGMRF-RC method. Experimental results over synthetic texture images and remote-sensing images from di?erent datasets show that the proposed OGMRF-RC method can achieve more accurate segmentation than other state-of-the-art MRF-based methods and the method using convolutional neural networks.
关键词： Segmentation,Gaussian-Markov random field,region coefficients,object-based,remote-sensing imagery
更新于2025-09-23 15:23:52
-
LEFMIS: locally-oriented evaluation framework for medical image segmentation algorithms
摘要： This article proposes a novel framework for the locally-oriented evaluation of segmentation algorithms (LEFMIS). The presented approach is robust and takes into account local inter/intra-observer variability and the anisotropy of medical images. What is more, the framework makes it possible to distinguish types of error locally. These features are crucial in the context of cancer image data. The proposed framework is based on use of the signed anisotropic Euclidean distance transform and the distance projection. It can be used easily in many different applications with or without additional expert outlines (both inter- and intra-observer variability). The performance of the proposed framework is depicted using both artificial and kidney cancer CT data with experts’ manual outlines. In the article, in the case of artificial data, it is presented that the manual outlines dispersion is symmetric in relation to the truth border. The effectiveness of the selected segmentation algorithm was analysed in the context of kidney cancer using computed tomography data. For the calculated local inter-observer variability, 80.11% of the surface points generated by the kidney segmentation algorithm are within one expert outline standard deviation and 97.96% are within five. An error distribution shift in the direction of type I error equivalent was also observed. Finally, the significance of the local estimation of error type differences is presented. The article shows the greater usefulness and flexibility of the proposed framework in comparison to the state-of-the-art methods. The exemplary usage of the LEFMIS with or without inter-/intra-observer variability is also presented.
关键词： evaluation,validation,cancer images,intraobserver variability,kidney segmentation,interobserver variability,error types
更新于2025-09-23 15:23:52
-
Interactive Image Segmentation on Multiscale Appearances
摘要： Interactive segmentation algorithms based on graph cuts can extract the foreground successfully from a simple scene. However, they are ineffective for complex-scene images. To improve the segmentation performance, we propose an interactive segmentation algorithm, which combines the segmentation and the multiscale smoothing into a unified model. This model consists of the segmentation and the smoothing. The segmentation relies on the multiscale appearances, which depend on the smoothing. In the smoothing part, the total variation is used to preserve the geometric shape of the foreground and captures different scale edges and appearances for segmentation. Combining the multiscale edges and appearances, we propose a novel Gibbs energy functional for segmentation. The exact global minima of the energy can be found by jointing the image smoothing and the optimization of segmentation. In this algorithm, the smoothing motivates that the foreground could be detected easily from a proper scale. Experimental results on the BSD300 data set and Weizmann horse's database indicate that, compared with the existing interactive segmentation algorithms, the proposed algorithm provides competitive performance in terms of segmentation accuracy.
关键词： multiscale appearance,multiscale edge,Interactive image segmentation,graph cut
更新于2025-09-23 15:23:52
-
A Robust Parameter-free Thresholding Method for Image Segmentation
摘要： In this paper, we presented a new parameter-free thresholding method for image segmentation. In separating an image into two classes, the method employs an objective function that not only maximizes the between-class variance but also the distance between the mean of each class and the global mean of the image. The design of the objective function aims to circumvent the challenge that many existing techniques encounter when the underlying two classes have very different sizes or variances. The advantages of the new method are twofold. First, it is parameter-free, meaning that it can generate consistent results. Second, the new method has a simple form that makes it easy to adapt to different applications. We tested and compared the new method with the standard Otsu method, the maximum entropy method, and the 2D Otsu method on the simulated and real biomedical and photographic images and found that the new method can achieve a more accurate and robust performance.
关键词： histogram,parameter-free thresholding,Segmentation,objective function
更新于2025-09-23 15:23:52
-
Automatic Image Segmentation with Superpixels and Image-level Labels
摘要： Automatically and ideally segmenting the semantic region of each object in an image will greatly improve the precision and efficiency of subsequent image processing. We propose an automatic image segmentation algorithm based on superpixels and image-level labels. The proposed algorithm consists of three stages. At the stage of superpixel segmentation, we adaptively generate the initial number of superpixels using minimum spatial distance and the total number of pixels in the image. At the stage of superpixel merging, we define small superpixels and directly merge the most similar superpixel pairs without considering the adjacency, until the number of superpixels equals the number of groupings contained in image-level labels. Furthermore, we add a stage of reclassification of disconnected regions after superpixel merging to enhance the connectivity of segmented regions. On the widely-used Microsoft Research Cambridge data set and Berkeley segmentation data set, we demonstrate that our algorithm can produce high-precision image segmentation results compared to the state-of-the-art algorithms.
关键词： superpixels,image-level labels,Image segmentation,disconnected regions
更新于2025-09-23 15:23:52