Search

With the development of deep learning technology, there are many cases of using DNNs in embedded systems such as unmanned vehicles, drones, and robotics. Typically, in the case of an autonomous driving system, it is crucial to run several DNNs which have high accuracy results and large computation amount at the same time. However, running multiple DNNs simultaneously in an embedded system with relatively low performance increases the time required for the inference. This phenomenon may cause a problem of performing an abnormal function because the operation according to the inference result is not performed in time. To solve this problem, the solution proposed in this paper first reduces the computation by applying the Tucker decomposition to DNN models with big computation amount, and then, make DNN models run in parallel as much as possible in the unit of hidden layer inside the GPU. The experimental result shows that the DNN inference time decreases by up to 75.6% compared to the case before applying the proposed technique. [ABSTRACT FROM AUTHOR]

As the world is trying to establish smart city, unmanned vehicle control systems are being widely used. This paper writes about an unmanned parking control system that uses an adaptive background image modeling method, suggesting the method of updating the background image, modeled with an adaptive Gaussian mixture model, in both global and local way according to the moving object. Specifically, this paper focuses on suggesting two methods; a method of minimizing the influence of a moving object on a background image and a method of accurately updating the background image by quickly removing afterimages of moving objects within the area of interest to be monitored. In this paper, through the implementation of the unmanned vehicle control system, we proved that the proposed system can quickly and accurately distinguish both moving and static objects such as vehicles from the background image. [ABSTRACT FROM AUTHOR]

The application of the unmanned vehicles in various fields has been attracting attention, and the development of a service utilizing unmanned vehicles has been proceeding. As the service market using the unmanned vehicles rapidly increases, the demand for the development of software for performing the mission with unmanned vehicles is increasing. In particular, as the demand for unmanned vehicle utilization services for public missions such as fire detection, mail delivery, and facility management increases, the importance of developing mission software for unmanned vehicle is increasing. To develop common mission software, architecture design should be made so that unmanned vehicle service provider can easily develop software using reusable libraries or functions through analysis commonly required by various public institutions. In this paper, we discuss the research trends of mission software for public mission unmanned vehicles. In addition, the architecture design of developing formal mission software is proposed. Finally, we propose a data transfer architecture between mission software and data platform. [ABSTRACT FROM AUTHOR]