In the intelligent transportation system, vehicle detection is one of the essential technologies in obstacle avoidance and navigation, however the existing vehicle detection methods cannot meet the actual needs. This ...
In the intelligent transportation system, vehicle detection is one of the essential technologies in obstacle avoidance and navigation, however the existing vehicle detection methods cannot meet the actual needs. This paper presents a vehicle detection method combines the intensity and distance information of point cloud, which improves the segmentation performance of nearby objects. Specifically, the data of point cloud collected by lidar is preprocessed first. Then the processed point cloud is clustered by combining its coordinate and intensity information. Finally, the clustered suspected targets are fed to the random forest classifier. Our method can efficiently detect and classify targets in large-scale disordered 3D point cloud with high accuracy. In the real-scanned Livox Mid-40 Lidar dataset, our proposed method improves the detection accuracy by 31% compared with the traditional Euclidean clustering.
Brain-computer interface (BCI) provides a new way to express our minds without peripheral nerves and muscles. In this work, a process control recognition method based on continuous flickering is proposed to output con...
Brain-computer interface (BCI) provides a new way to express our minds without peripheral nerves and muscles. In this work, a process control recognition method based on continuous flickering is proposed to output continuous commands. Phase matching method was applied in this work, matching the test data with the template with the same phase to improve the accuracy. We also put forward a high tolerance criterion and give a new definition to the recognition result of attention shift period. We first conducted a screen-based continuous flickering feasibility verification experiment using correlation component analysis algorithm (TRCA) method, and the recognition accuracy reached 85% and 90% under high tolerance criterion. The average offline simulation information translates rate (ITR) was 455.8 bit/min, and the highest ITR reached 524.7bit/min, which certificated the feasibility. Furthermore, we carried out a drone control experiment based on augmented reality (AR)-BCI using extended filter bank canonical correlation analysis (extended-FBCCA), and achieved an average accuracy of 90% and ITR of 49.1 bit/min, having better performance than repetitive visual stimulus (RVS) with intervals.
Reduced manning is the process (and the result) of removing human functions from a system while retaining or improving system operability and effectiveness. Reliability and maintainability characterize a system's ...
详细信息
Reduced manning is the process (and the result) of removing human functions from a system while retaining or improving system operability and effectiveness. Reliability and maintainability characterize a system's operability and effectiveness. Reduced manning impacts system reliability by changing the characteristics of (1) human error associated with system operation and maintenance, (2) time to repair failed components, and (3) mean-time-between-failures (MBTF) in a reduced manning environment. Simply reducing manning without compensating for system dependence on human involvement generally has a negative impact on system maintainability. Methods to address this include (1) human-system integration design of maintenance interfaces and (2) design of operations activities that are closely related to device failures. After demonstrating reliable performance through testing and operation, ship commanders can be assured that fewer people can effectively operate and maintain Navy ships and systems.
暂无评论