Lin Kunhui
Xiamen University
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Lin Kunhui.
international conference on computer science and education | 2010
Wu Tunhua; Bai Baogang; Zhou Chang-le; Li Shaozi; Lin Kunhui
A real-time eye tracking method was introduced. The method integrates several algorithms such as AdaBoost, optical flow, and Camshift. First, lighting condition was standardized, and the camera was placed below face. Second, the nostril tracking points were localized and taken as reference points. Third, the Camshift algorithm and Lucas-Kanade optical flow algorithm were respectively utilized to track the face and nostrils, and the pupils were positioned using gradient Hough circle transform. Finally, with the coordinates of nostrils and pupils, the velocity and trajectory of eye movement were calculated. The experiments on a video of resolution at 640⋆480 result a tracking speed of 25 frames per second. Results prove the effectiveness and efficiency of this method.
international conference on instrumentation and measurement, computer, communication and control | 2012
Zhang Leilei; Lin Kunhui; Ye Weichuan
With the fast evolution of computer technology, the service from search engines has been providing more and more convenience to mobile terminals. However, traditional key-word search engines have their own deficiency on certain areas which take geographical factors into account. To overcome this deficiency, this paper discusses about another new type of search, location-based search. After analyzing the background of Location-Based Service (LBS), this paper proposed the architecture for LBS systems, and put forward a scheme of constructing server database by using spatial index, and finally implemented one application of searching for hotels.
international conference on intelligent computation technology and automation | 2010
Yan Yan; Lin Kunhui
The high-speed connection of 3G network has transferred cell-phone applications’ bottleneck from network speed to both the performance of hardware and software and the presentational layer of applications. The 3D visualization on search results for mobile search client can meet the needs of 3G new business. And this technology can be widely used in the areas such as product display, advertising, real estate and the game industry. This paper took searching buildings for the real estate field as an example. Firstly the parallel computing was introduced to enhance the process of modeling calculation and rendering for 3D building model. Then search result presented in the form of 3D visualization on the user interface of mobile search. Finally, the experiment emulated the post-drawing 3D building on mobile phone. And the simulation result showed that the 3D building was displayed in high-speed rate, and changed smoothly with a strong sense of 3D.
international conference on instrumentation and measurement, computer, communication and control | 2012
Ye Weichuan; Lin Kunhui; Zhang Leilei; Deng Xiang
Collaborative filtering recommendation algorithm is currently the most widely used personalized recommendation algorithm. Sparsity problem of user rating data led to the recommendation quality of traditional collaborative filtering algorithms are far from ideal. To solve the problem, the paper first cloud model and project characteristic attributes to calculate the similarity between the project has taken into consideration in computing project similarity scores were similar between the project and consider the project between the characteristic attribute similarity, and then to predict ungraded items rated. Finally, the cloud model to calculate the similarity between users to obtain the target users nearest neighbor. Experimental results show that the algorithm improves the accuracy of the similarity of the calculated project, and effectively solve the problem of data sparsity, and improve the quality of the recommendation system recommended.
international conference on computer science and education | 2012
Lin Kunhui; Yang Pingping
The paper designs the system of real-time streaming media transmission based on multiple 3G-card in the mobile environment especially for news workers to report news events quickly and duly. The paper introduces the system framework including 3 big modules: capturing and transportation subsystem, multiple 3G cards controlling subsystem and media receiving subsystem. Among them transmission and 3G controlling subsystem and quality of service is the key technology of the real-time transmission system. The paper adapts popular compressing algorithm, H.264 for video and AAC for audio. In order to ensure the real time and quality of the streaming media, it adapts the Matron card to capture and compress the media streaming and multiple 3G cards to add the network bandwidth.
international conference on computer science and education | 2010
Yang Pingping; Lin Kunhui
Because of the best-effort characteristics of the Internet, it is important to suppress the degradation of communication quality on the receiving side caused by data packet loss and errors as well as the limited network bandwidth. This paper focus on MPEG transmission over the Internet and Differentiated Services architecture established to improve Quality of Services (QoS). Packets are classified using a frame-based scheme in the mechanism so as to discard the unimportant packets marked at the edge router and insure the packets with higher-priority sent from core router to destination host first. The simulation results and mathematical analysis demonstrate that the proposed mechanism achieves better quality of media streaming compared with the current best-effort Internet, in terms of playable frame rate and real-time performance at the receiving side.
Archive | 2007
Wu Qingfeng; Lin Kunhui; Zhou Chang-le; M Li; 吴清锋
Computer Engineering | 2005
Lin Kunhui
Archive | 2007
Lin Kunhui; Wang Wei; Wu Tunhua; Zhou Chang-le; Ni Ziwei; M Li; 周昌乐
Archive | 2007
Lin Kunhui; Zhang Lei; Zhou Chang-le; Ni Ziwei; Wu Qingfeng; M Li; 吴清锋