Extraction of the tongue body from digital images is essential for automated tongue diagnoses in traditional Chinese medicine. This paper presents a fully automated active contour initial method that utilizes prior kn...
详细信息
Extraction of the tongue body from digital images is essential for automated tongue diagnoses in traditional Chinese medicine. This paper presents a fully automated active contour initial method that utilizes prior knowledge of the tongue shape and its location in tongue images. Then colorspace information is introduced to control curve evolution. Combining the geometrical Snake model with the parameterized GVFSnake model, a novel approach for automatic tongue segmentation: C2G2FSnake (color control-geometric & gradient flow Snake) is proposed. This method increases the curve velocity but decreases the complexity. C2G2FSnake greatly extends practical usage to tongue segmentation, at the same time increasing the precision. Compared with other state-of-the-art works using different images of tongue color, C2G2FSnake realizes automatic tongue segmentation with greatly improved accuracy.
Semantic segmentation is an essential task in plenty of real-life applications such as virtual reality, video analysis, autonomous driving, etc. Recent advancements in fundamental vision-based tasks ranging from image...
详细信息
Semantic segmentation is an essential task in plenty of real-life applications such as virtual reality, video analysis, autonomous driving, etc. Recent advancements in fundamental vision-based tasks ranging from image classification to semantic segmentation have demonstrated deep learning-based models' high capability in learning complicated representation on large datasets. Nevertheless, manually labeling semantic segmentation dataset with pixel-level annotation is extremely labor-intensive. To address this problem, we propose a novel multi-level feature alignment framework for cross-domain semantic segmentation of urban scenes by exploiting generative adversarial networks. In the proposed multi-level feature alignment method, we first translate images from one domain to another one. Then the discriminative feature representations extracted by the deep neural network are concatenated, followed by domain adversarial learning to make the intermediate feature distribution of the target domain images close to those in the source domain. With these domain adaptation techniques, models trained with images in the source domain where the labels are easy to acquire can be deployed to the target domain where the labels are scarce. Experimental evaluations on various mainstream benchmarks confirm the effectiveness as well as robustness of our approach.
A new book-lending system is designed and analyzed based on logic Petri nets in this paper. The batch processing function and indeterminacy of readers are included in the system. Its logic Petri net model is establish...
详细信息
ISBN:
(纸本)9781424480364
A new book-lending system is designed and analyzed based on logic Petri nets in this paper. The batch processing function and indeterminacy of readers are included in the system. Its logic Petri net model is established and some important properties of the system are verified based on the model.
This paper studies power allocation in coordinated multi-point (CoMP) transmission of 3GPP LTE-Advanced system with remote radio units(RRUs) power constraints. We apply block diagonal (BD) precoding to downlink transm...
详细信息
This paper is concerned with the problems of quantized *** for discrete-time Markovian jump linear systems over networks with non-accessible mode information. The quantizer considered here is logarithmic quantizer. In...
详细信息
This paper is concerned with the problems of quantized *** for discrete-time Markovian jump linear systems over networks with non-accessible mode information. The quantizer considered here is logarithmic quantizer. In this paper, a linear time-invariant mode-independent quantized *** is designed such *** error system is stochastically stable. *** conditions for the existence of *** is given in terms of linear matrix inequalities. A numerical example is provided to demonstrate the effectiveness of the proposed approach.
A remote network monitoring model for large-scale materials manufacturing is proposed, including five modules: center control module, data collection and fault alarm module, graph drawing module and data storage modul...
详细信息
A remote network monitoring model for large-scale materials manufacturing is proposed, including five modules: center control module, data collection and fault alarm module, graph drawing module and data storage module. The center control module not only interacts with users, but also controls the other four modules to work together in harmony. According to this monitoring model, a remote network monitoring platform is designed and realized. The user can interact with the control center module through an Internet browser, and the information about the monitored manufacturing machines and devices can be displayed by means of text, chart, graphic and sound, etc. Moreover, the details about the problems or faults from the monitored objects can be obtained in time. The experimental results indicate that the network monitoring platform can accurately get the information of the monitored objects, and users can conveniently get the online running state of those monitored objects.
Grid is a promising infrastructure which enables scientists and engineers to access geographically distributed resources. Grid computing is a new technology which focuses on aggregating various kinds of resource (e.g....
详细信息
ISBN:
(纸本)9781424476169
Grid is a promising infrastructure which enables scientists and engineers to access geographically distributed resources. Grid computing is a new technology which focuses on aggregating various kinds of resource (e.g., processor cycles, disk storage, and contents) into one computing platform. The realization of grid computing requires a resource agent to manage and monitor available resources. Based on study of past models, this paper presents a new agent-based resource monitoring model whose main feature is multi-layered monitoring architecture, which enhances the ability to monitor related resource efficiently. In the meantime, the new model has been implemented in the development of a resource monitoring module integrated within a academic grid project.
Lane detection based on computer vision is a key technology of Automatic Drive system for intelligent vehicles. In this paper, we propose a real-time and efficient lane detection algorithm that can detect lanes appear...
详细信息
ISBN:
(纸本)9781479982622
Lane detection based on computer vision is a key technology of Automatic Drive system for intelligent vehicles. In this paper, we propose a real-time and efficient lane detection algorithm that can detect lanes appearing in urban streets and highway roads under complex background. In order to enhance lane boundary information and to be suitable for various light conditions, we adopt canny algorithm for edge detection to get good feature points. We use the generalized curve lane parameter model, which can describe both straight and curved lanes. We propose an improved random sample consensus (RANSAC) algorithm combined with the least squares technique to estimate lane model parameters based on feature extraction. Experiments are conducted on both real road lane videos captured by Tongji University and Caltech Lane Datasets. The experimental results show that our algorithm is can meet the real time requirement and fit lane boundaries well in various challenging road conditions.
In the field of identity authentication, existing researches on user keystroke authentication only focus on the situation in which a single user uses a single account. When multiple users share one account, there emer...
详细信息
This paper proposes an enhanced scheduling solution to support different quality of service (QoS) for IEEE 802.16e broadband wireless access network. Based on the existing scheduling algorithm M-LWDF, we do deeper res...
详细信息
This paper proposes an enhanced scheduling solution to support different quality of service (QoS) for IEEE 802.16e broadband wireless access network. Based on the existing scheduling algorithm M-LWDF, we do deeper research into how to integrate it into IEEE 802.16e. The proposed scheduling solution combines the keyservice flow parameters defined by IEEE 802.16e standard with M-LWDF scheme. Simulation results show that the delay character is improved for real-time services using the proposed method.
暂无评论