RESUMEN
In object detection systems for autonomous driving, LIDAR sensors provide very useful information. However, problems occur because the object representation is greatly distorted by changes in distance. To solve this problem, we propose a LIDAR shape set that reconstructs the shape surrounding the object more clearly by using the LIDAR point information projected on the object. The LIDAR shape set restores object shape edges from a bird's eye view by filtering LIDAR points projected on a 2D pixel-based front view. In this study, we use this shape set for two purposes. The first is to supplement the shape set with a LIDAR Feature map, and the second is to divide the entire shape set according to the gradient of the depth and density to create a 2D and 3D bounding box proposal for each object. We present a multimodal fusion framework that classifies objects and restores the 3D pose of each object using enhanced feature maps and shape-based proposals. The network structure consists of a VGG -based object classifier that receives multiple inputs and a LIDAR-based Region Proposal Networks (RPN) that identifies object poses. It works in a very intuitive and efficient manner and can be extended to other classes other than vehicles. Our research has outperformed object classification accuracy (Average Precision, AP) and 3D pose restoration accuracy (3D bounding box recall rate) based on the latest studies conducted with KITTI data sets.
RESUMEN
INTRODUCTION: The cancer risk of radiation exposure in the moderate-to-high dose range has been well established. However, the risk remains unclear at low-dose ranges with protracted low-dose rate exposure, which is typical of occupational exposure. Several epidemiological studies of Korean radiation workers have been conducted, but the data were analysed retrospectively in most cases. Moreover, groups with relatively high exposure, such as industrial radiographers, have been neglected. Therefore, we have launched a prospective cohort study of all Korean radiation workers to assess the health effects associated with occupational radiation exposure. METHODS AND ANALYSIS: Approximately 42 000 Korean radiation workers registered with the Nuclear Safety and Security Commission from 2016 to 2017 are the initial target population of this study. Cohort participants are to be enrolled through a nationwide self-administered questionnaire survey between 24 May 2016 and 30 June 2017. As of 31 March 2017, 22 982 workers are enrolled in the study corresponding to a response rate of 75%. This enrolment will be continued at 5-year intervals to update information on existing study participants and recruit newly hired workers. Survey data will be linked with the national dose registry, the national cancer registry, the national vital statistics registry and national health insurance data via personal identification numbers. Age-specific and sex-specific standardised incidence and mortality ratios will be calculated for overall comparisons of cancer risk. For dose-response assessment, excess relative risk (per Gy) and excess absolute risk (per Gy) will be estimated with adjustments for birth year and potential confounders, such as lifestyle factors and socioeconomic status. ETHICS AND DISSEMINATION: This study has received ethical approval from the institutional review board of the Korea Institute of Radiological and Medical Sciences (IRB No. K-1603-002-034). All participants provided written informed consent prior to enrolment. The findings of the study will be disseminated through scientific peer-reviewed journals and be provided to the public, including radiation workers, via the study website (http://www.rhs.kr/) and onsite radiation safety education.