Search results

Cloud manufacturing platform has a high degree of openness, with a large variety of users having different needs. Designers on such platforms exhibit great differences in their knowledge abilities and knowledge needs, necessitating the cloud platform to provide personalized knowledge recommendation. To satisfy the personalized knowledge needs of the designers in product design tasks and other manufacturing tasks on a cloud manufacturing platform and provide them with high-quality knowledge resources, a knowledge recommendation method based on designers’ knowledge ability is proposed. The proposed method, with appropriate adjustments, can also be used for personalized knowledge recommendation to other personnel or institutions in cloud manufacturing platforms.

A knowledge recommendation method model is developed. The method consists of three stages. First, a designer knowledge system is constructed based on customer reviews in historical tasks, and designer knowledge ability and knowledge demand degree are quantitatively evaluated by synthesizing customer reviews and expert evaluations. Subsequently, the design knowledge domain ontology is constructed, and knowledge resources and tasks are modeled based on the ontology. Finally, the semantic similarity between tasks and knowledge resources and the knowledge demand degree of designers are integrated to calculate the knowledge recommendation coefficient, which realizes the personalized knowledge recommendation of designers.

Two design tasks of a 3D printing cloud platform are taken as examples to verify the feasibility and effectiveness of the proposed method. Compared with other methods, it is proved that the method proposed in this paper can obtain more knowledge resources that meet the needs of designers and tasks.

The method proposed in this paper is important for the expansion of data applications of the cloud manufacturing platform and for enriching the knowledge recommendation method. The proposed method has two innovations. First, both designer needs and task needs are considered in knowledge recommendation. Compared with most of the existing methods, which only consider one factor, this method is more comprehensive. Second, the designer’s knowledge ability model is constructed by using customer reviews on the cloud manufacturing platform. This overcomes the defect of low accuracy of the interest model in existing methods and makes full use of the big data of the cloud manufacturing platform.

The purpose of this paper is to present a novel registration method for augmented reality (AR) systems based on robust estimation of trifocal tensor using point and line correspondence simultaneously.

The proposed method distinguishes itself in following three ways: first, to establish the world coordinate system, the restriction that the four specified points must form an approximate square is relaxed, the only requirement is that these four points should not be collinear. Second, besides feature points, line segments are also used to calculate the needed trifocal tensors. The registration process can still be achieved even without the use of feature points. Third, to estimate trifocal tensors precisely, progressive sample consensus (PROSAC) is used instead of random sample consensus to remove outliers.

As shown in the experiments, the proposed method really enhances the usability of this system. To calculate trifocal tensor, a PROSAC based algebraic minimization algorithm is put forward which improves the accuracy and reduces the computation complexity.

In current system, it is stipulated that there is no large rotation of the user's head relative to the registration scenes, because the NCC will degrade when there is a large rotation between images.

A more robust feature matching strategy is needed. Treating feature matching as a classification problem may be a good choice.

This paper presents a novel registration approach for AR system.