Relevance feedback is an interactive querying process of CBIR, which can help the retrieval system adapt to the dynamic user demand and achieve more accuracy for the representation of image similarity according to the...
详细信息
Relevance feedback is an interactive querying process of CBIR, which can help the retrieval system adapt to the dynamic user demand and achieve more accuracy for the representation of image similarity according to the user's view. In this paper, we bring up the concept of the separability of image data as the theoretical criterion to guide generating the best feature vector set to better classify images. We build an energy function for the training of the eigenvectors on the basis of separability, and then apply simulated annealing optimization algorithm to minimize energy function in order to accomplish the generation of the optimal feature vectors set in a particular database. The experiment result shows that this new algorithm for relevance feedback can effectively improve the retrieval accuracy.
Swarm Intelligence is applied to multi-agent system collaboration in order to improve the flexibility and adaptability of multi-agent system. According to the similarities between multi-robots pursuing and ants foragi...
详细信息
Swarm Intelligence is applied to multi-agent system collaboration in order to improve the flexibility and adaptability of multi-agent system. According to the similarities between multi-robots pursuing and ants foraging, ant colony task allocation model is applied to multi-robots collaborative pursuing. Artificial potential method is introduced to ant colony task allocation model, and defined adaptive task allocation model. Experiment results show that it is consistent between the experiments and the actual situation expectations, and the whole experiments in our work can fulfill the demand of coordination in multi-robots pursuing. The extended task allocation model can farther be applied into other multi-agents application, and it has a broader foreground.
In this work, by integrating omni-wheel mobile robots with X-Bee communication protocol, Arduino control, IR range finders, and CMOS camera, as well as wiimote multizone localization, tasks such as obstacle and collis...
详细信息
In this work, by integrating omni-wheel mobile robots with X-Bee communication protocol, Arduino control, IR range finders, and CMOS camera, as well as wiimote multizone localization, tasks such as obstacle and collision avoidances, following, autonomously movement, and indoor localization of group robots are implemented as the first step toward an autonomously control of group robots for smart living and biomimetic applications. In conjunction with hardware design, novel algorithms are also developed to realize these tasks for future group robot applications in indoor service and biomimetic tasks.
Traditional gradient based edge detection methods such as Sobel, Laplacian of Gaussian and Canny detectors which have charming applications in common images are not satisfactory in dealing with noisy remote sensing im...
详细信息
Traditional gradient based edge detection methods such as Sobel, Laplacian of Gaussian and Canny detectors which have charming applications in common images are not satisfactory in dealing with noisy remote sensing images. Aiming to solve this problem, we introduce the trace of the nonlinear local structure tensor to sort edges out of noises. Then we extracted the contours of the trace and fill the gaps in the contours. At last, edge thinning is applied to the contour map to suppress the non-maximum pixels. Experiment results demonstrate that our robust tensor-based edge detection algorithm is effective under noisy condition.
Software Product Line (SPL) becomes a potential approach for software system engineering. Software artifacts based on different models and approaches are collected and deposited into repository in order to be reused...
详细信息
Software Product Line (SPL) becomes a potential approach for software system engineering. Software artifacts based on different models and approaches are collected and deposited into repository in order to be reused for a new software product in the future. Otherwise, identifying of reusable software artifacts is still difficult and time-consuming. In particular, requirements management for SPL becomes more complex process that should take into account requirements value for customers, cost of implementation, available resources, requirements interdependencies, system architecture and dependencies to the code base. In this paper we propose a social network representing the software product line artifacts and relationships between those artifacts. We believe the social network can be analyzed in order to acquire the information representing the dependencies between software artifacts and stakeholders. This information can be applied in order to improve software requirements management for SPL.
Dual-one-way ranging (DOWR) system is an effective instrument to measure the Earth's gravity field. It is important to analyze the error source before adopting the DOWR system. Based on the theory study of the DOW...
详细信息
Pedestrian detection in depth images can reduce the effect of clothing in appearance and unpredictable illumination changes, and its applications include robotics and surveillance, etc. Due to the TOF depth images eas...
详细信息
Pedestrian detection in depth images can reduce the effect of clothing in appearance and unpredictable illumination changes, and its applications include robotics and surveillance, etc. Due to the TOF depth images easily contaminated by noise, a parameter-free and framelet-based regularization approach is proposed to remove noise and preserve the object shape in depth images before feature detection and classifying. After noise removal, the histogram of depth difference (HDD) is utilized as a features descriptor and SVM with a linear kernel is adopted as a classifier. Experiments show that the framelet-based approach is adaptive and effective to denoise depth images and pedestrian detection in denoising depth images is feasible. The miss rate decreases from 9.1% of noisy images to 2.2% of denosing images at FPPW=10 -4 .
Nowadays, with the ever increasing complexity of multi-domain mechatronics products and the demand of reducing time-to-market, the system design approach which meets the requirements of virtualized, concurrent, and sy...
详细信息
Logs generated by network devices and systems provide important information for network management. In this paper, we describe a centralized syslog system which gathers and analyzes log messages from a number of route...
详细信息
Logs generated by network devices and systems provide important information for network management. In this paper, we describe a centralized syslog system which gathers and analyzes log messages from a number of routers, switches and firewalls. The gathered logs are filtered and categorized with regular expression, and finally stored in a MySQL database with format. Through the statistics analysis, feature-based detection on security events, the system can effectively find out abnormal behavior of network devices and ensure the network security. Some methods are found out to allow us to check if the network behavior is unusual. These perspective methods also provide the basis of network management and security strategy design for administrators, thereby strengthen further network management.
Flooding is the base of unstructured P2P (Peer to Peer) systems, such as Gnutella. Pure flooding mechanism doesn't be used in practice for a great amount of redundant generated during query propagated among networ...
详细信息
暂无评论