Self-Guided Stereo Correspondence Estimation Algorithm

This paper introduces an innovative algorithm, “Self-guided Stereo Correspondence” (SGSC), that is directed by photometric properties of the candidate pixels. As the photometric properties of reference image (left image) pixel and its neighbor’s pixel are similar in most cases, so the upcoming corresponding pixel exists in the surrounding of the previous matching pixel. Searching performance is greatly improved by utilizing this photometric property of the candidate pixels. The searching performance is further improved by applying the pioneering threshold technique. These two key techniques sufficiently reduced the computational cost with no degradation of accuracy. The achievements of the proposed method are testified on Middlebury standard Stereo Datasets of 2003 and 2006 and the Middlebury latest Optical Flow Dataset. Finally, the proposed method is compared with present state-of-the-art methods and our SGSC outdoes the latest methods in terms of speed, visualization of hidden ground truth, 3D reconstruction and accuracy.

Web Service Discovery for Cloud-Based Mobile Application Using Multi-Level Clustering and QoS-Based Ranking

Since many service providers are providing similar web services, finding an accurate web service based on user preferences is becoming a challenging task. Therefore, enhancing web service discovery (WSD) method will improve the searching performance. In this paper, we firstly discuss and review some existing web service discovery approaches and identify their limitations. Subsequently, we propose a web service discovery method for cloud-based mobile application by using multi-level clustering technique to improve performance by reducing the searching scope. Our web service discovery architecture is able to increase the discoverability of more accurate web services based on user's preferences. Meanwhile, user preference Quality of Services (QoS) attributes are also used for ranking procedure to allow user to decide the quality of the mobile application. The experimental results show that our approach is able to increase the searching performance and provide a reliable list of selection for users.

New Method of Optimal Deployment of Radar Network

In order to improve the detection performance with the limited radar resources in the given defense zone, it is necessary to make reasonable and effective deployment of radar network. According to the principles of radar network deployment, its mathematical model is established at the beginning. And then, on the base of the shuffled frog leaping algorithm (SFLA) principle, a new method-improved shuffled frog leaping algorithm (ISFLA) is introduced through the technique of algorithm hybrid. By integrating updated strategy and chaotic optimization into SFLA, it greatly enhances the local searching efficiency and global searching performance. Moreover, the frogs are divided into two types and perform different operations to co-evolve. Finally, by analyzing an example and comparing the results with those algorithms, it comes to a conclusion that several network schemes can be obtained much more quickly by this way with better operability.

A Novel Seam-Searching Approach for Image Mosaic

In this paper, we propose a novel two-step seam-searching method based on Dijkstra algorithm in order to improve the seam-searching performance of image mosaic. Parameters of this algorithm are analyzed to improve the overall performance. Experiments show that the proposed method can obtain better seam-searching result than the algorithm based on greedy method and can reduce the computational burden.