• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.813-826
• /
• 2022

AI-based image processing technologies in various fields have been widely studied. However, the lighter the board, the more difficult it is to reduce the weight of image processing algorithm due to a lot of computation. In this paper, we propose a method using deep learning for object recognition algorithm in lightweight embedded boards. We can determine the area using a deep neural network architecture algorithm that processes semantic segmentation with a relatively small amount of computation. After masking the area, by using more accurate deep learning algorithm we could operate object detection with improved accuracy for efficient neural network (ENet) and You Only Look Once (YOLO) toward executing object recognition in real time for lightweighted embedded boards. This research is expected to be used for autonomous driving applications, which have to be much lighter and cheaper than the existing approaches used for object recognition.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.59-68
• /
• 2021

As artificial intelligence(AI) technologies, which have made rapid growth recently, began to be applied to the marine environment such as ships, there have been active researches on the application of CNN-based models specialized for digital videos. In E-Navigation service, which is combined with various technologies to detect floating objects of clash risk to reduce human errors and prevent fires inside ships, real-time processing is of huge importance. More functions added, however, mean a need for high-performance processes, which raises prices and poses a cost burden on shipowners. This study thus set out to propose a method capable of processing information at a high rate while maintaining the accuracy by applying Quantization techniques of a deep learning model. First, videos were pre-processed fit for the detection of floating matters in the sea to ensure the efficient transmission of video data to the deep learning entry. Secondly, the quantization technique, one of lightweight techniques for a deep learning model, was applied to reduce the usage rate of memory and increase the processing speed. Finally, the proposed deep learning model to which video pre-processing and quantization were applied was applied to various embedded boards to measure its accuracy and processing speed and test its performance. The proposed method was able to reduce the usage of memory capacity four times and improve the processing speed about four to five times while maintaining the old accuracy of recognition.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.5
• /
• pp.186-201
• /
• 2021

As autonomous driving technology advances, the accuracy of the vehicle position is important for recognizing the environments around driving. Map-matching localization techniques based on high definition (HD) maps have been studied to improve localization accuracy. Because conventional map-matching techniques estimate the vehicle position based on an HD map reference dataset representing the center of the lane, the estimated position does not reflect the deviation of the lateral distance within the lane. Therefore, this paper proposes a localization system based on the reference lateral position dataset extracted using image processing and HD maps. Image processing extracts the driving lane number using inverse perspective mapping, multi-lane detection, and yellow central lane detection. The lane departure method estimates the lateral distance within the lane. To collect the lateral position reference dataset, this approach involves two processes: (i) the link and lane node is extracted based on the lane number obtained from image processing and position from GNSS/INS, and (ii) the lateral position is matched with the extracted link and lane node. Finally, the vehicle position is estimated by matching the GNSS/INS local trajectory and the reference lateral position dataset. The performance of the proposed method was evaluated by experiments carried out on a highway environment. It was confirmed that the proposed method improves accuracy by about 1.0m compared to GNSS / INS, and improves accuracy by about 0.04m~0.21m (7~30%) for each section when compared with the existing lane-level map matching method.