The human eye is a vital sensory organ that provides us with visual information about the world around us. It can also convey such information as our emotional state to people with whom we interact. In technology, eye tracking has become a hot research topic recently, and a growing number of eye-tracking devices have been widely applied in fields such as psychology, medicine, education, and virtual reality. However, most commercially available eye trackers are prohibitively expensive and require that the user’s head remain completely stationary in order to accurately estimate the direction of their gaze. To address these drawbacks, this paper proposes an inner corner-pupil center vector (ICPCV) eye-tracking system based on a deep neural network, which does not require that the user’s head remain stationary or expensive hardware to operate. The performance of the proposed system is compared with those of other currently available eye-tracking estimation algorithms, and the results show that it outperforms these systems.

Abstract-Tourist and destination maps are thematic maps designed to represent specific themes in maps. The road network topologies in these maps are generally more important than the geometric accuracy of roads. A road network warping method is proposed to facilitate map generation and improve theme representation in maps. The basic idea is deforming a road network to meet a user-specified mental map while an optimization process is performed to propagate distortions originating from road network warping. To generate a map, the proposed method includes algorithms for estimating road significance and for deforming a road network according to various geometric and aesthetic constraints. The proposed method can produce an iconic mark of a theme from a road network and meet a user-specified mental map. Therefore, the resulting map can serve as a tourist or destination map that not only provides visual aids for route planning and navigation tasks, but also visually emphasizes the presentation of a theme in a map for the purpose of advertising. In the experiments, the demonstrations of map generations show that our method enables map generation systems to generate deformed tourist and destination maps efficiently.

No abstract

No abstract

During large-size gear manufacturing by form grinding, the actual tooth surfaces will differ from the theoretical tooth surface because of errors in the clamping fixture and machine axes and machining deflection. Therefore, to improve gear precision, the gear tooth deviations should be measured first and the flank correction implemented based on these deviations. To address the difficulty in large-size gear transit, we develop an on-machine scanning measurement for cylindrical gears on the five-axis CNC gear profile grinding machine that can measure the gear tooth deviations on the machine immediately after grinding, but only four axes are needed for the measurement. Our results can serve as a foundation for follow-up research on closed-loop flank correction technology. This measuring process, which is based on the AGMA standards, includes the (1) profile deviation, (2) helix deviation, (3) pitch deviation, and (4) flank topographic deviation. The mathematical models for measuring probe positioning are derived using the base circle method. We also calculate measuring positions that can serve as a basis for programming the NC codes of the measuring process. Finally, instead of the gear profile grinding machine, we used the six-axis CNC hypoid gear cutting machine for measuring experiments to verify the proposed mathematical models, and the experimental result was compared with Klingelnberg P40 gear measuring center.