No abstract

The main loads and forces on the tire are carried by its cord-rubber composites structure. The geometry of the cord rubber composites needs to be measured during the production of the tire to ensure its quality. In this paper, a vision-based high-speed cord-rubber composites measurement system is developed. The system can accomplish the high-precision calibration of the linear camera based on the Checkerboard calibration board. Integration of the infrared light source into the system to improve image quality at high-speed motion. Based on this, the edge extraction and geometric parameter calculation of the measurement object are realized by using the Hough transform and GPU acceleration algorithm. Finally, the system is verified by measuring a standard sample and comparing the measurement results with the standard values. The standard deviations of the two angle measurements are 0.004° and 0.014°.

As important side information, attributes have been widely exploited in the existing recommender system for better performance. In the real-world scenarios, it is common that some attributes of items/users are missing (e.g., some movies miss the genre data). Prior studies usually use a default value (i.e., "other") to represent the missing attribute, resulting in sub-optimal performance. To address this problem, in this paper, we present an attribute-aware attentive graph convolution network (A 2 -GCN). In particular, we first construct a graph, whereby users, items, and attributes are three types of nodes and their associations are edges. Thereafter, we leverage the graph convolution network to characterize the complicated interactions among . To learn the node representation, we turn to the message-passing strategy to aggregate the message passed from the other directly linked types of nodes (e.g., a user or an attribute). To this end, we are capable of incorporating associate attributes to strengthen the user and item representations, and thus naturally solve the attribute missing problem. Considering the fact that for different users, the attributes of an item have different influence on their preference for this item, we design a novel attention mechanism to filter the message passed from an item to a target user by considering the attribute information. Extensive experiments have been conducted on several publicly accessible datasets to justify our model. Results show that our model outperforms several state-of-the-art methods and demonstrate the effectiveness of our attention method.

In this paper, a swarm spherical robot based on machine vision is proposed to adapt to the special applications of robots in the fields of land-based safety, navigation, surveillance and exploration, and discusses the spherical robot in terms of mechanism, control principles and positioning, respectively. The spherical robot structure is a telescopic low-degree-of-freedom parallel metamorphic mechanism, which is first analyzed mechanically using a modified Grubler-Kutzbach criterion to determine the degrees of freedom and to analyse the mechanics of key components. Secondly, the swarm robot consists of multiple spherical robots connected by magnetic forces. By designing a relevant path planning scheme to control the sequence of movements of these spherical robots, the movement of the whole swarm in the direction of a specific point can be achieved. Finally, the positioning and wireless control scheme of swarm robot based on machine vision is presented, and the motion principle of swarm robot is briefly introduced.

No abstract