http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
드론의 변전소 애자 이상현상 탐지를 위한 심층신경망 경량화 모델 기반 알고리즘 개발 연구
오선택(SeonTaek Oh),김형우(HyungWoo Kim),조성현(SungHyun Cho),유지환(JiHwan You),권용성(Youngsung Kwon),나원상(Won-Sang Ra),김영근(Young-Keun Kim) 제어로봇시스템학회 2020 제어·로봇·시스템학회 논문지 Vol.26 No.11
This paper proposes a method to detect defected insulators of electrical substations in real-time on an embedded graphics processing unit (GPU) by using a drone camera. The proposed algorithm is based on a compressed deep neural network to detect defected insulators with a corona effect arising from an overcurrent. A compressed deep neural network model is developed to reduce the computation time while maintaining high detection accuracy for the embedded GPU board. This paper applies the MobileNetv2 structure and compression technique, a residual block, on YOLOv3 to reduce the overall memory size and calculation time of the detection architecture. The proposed network is trained with an image data set of a mockup insulator with and without the corona effect. The performance evaluation shows that the algorithm is able to detect the object with an accuracy of 85% at an average speed of 40 FPS on a NVIDIA Xavier board. In addition, the results show that the proposed detection network uses half the memory and less computation time than YOLOv3-Tiny.
라이다 및 카메라 듀얼 센서 모니터링 기반의 곡선 차선인식 알고리즘 연구
서주찬(JuChan Seo),오선택(SeonTaek Oh),김영근(Young-Keun Kim) 한국자동차공학회 2021 한국 자동차공학회논문집 Vol.29 No.2
The accurate detection of road markings is a pre-requisite for safe advanced driver-assistance systems(ADAS). LiDAR-based lane detection has some advantages over camera-based detection in terms of robustness in various weather conditions, such as rain, and at night. However, LiDAR has a much lower resolution that may not detect enough lane markings and can give false markings depending on the reflectivity of lanes and surroundings. Therefore, this paper proposes a method to improve the LiDAR-based lane detection with the supplement of a camera. If the LiDAR-detected lane does not pass the proposed validation logic, the algorithm determines the use of a camera-based lane detection or estimates the upcoming lane from the previous data. The proposed algorithm is evaluated by using the KITTI road lane data set consisting of 851 frames. The proposed algorithm showed about 22 % accuracy improvement compared to the lane detection using LiDAR alone.
스마트시티 시범구역 주차점유현황 예측을 위한 CNN기반 알고리즘 기초 연구
박재은(Jae-Eun Park),조사무엘(Samuel Jo),전찬영(Chanyeong Jeon),오선택(SeonTaek Oh),김영근(Young-Keun Kim) 대한전기학회 2021 대한전기학회 학술대회 논문집 Vol.2021 No.10
스마트시티 시범구역에서는 운전자의 편의를 위해 실시간으로 주차여유공간 및 위치정보 제공시스템을 개발하는 것이 하나의 주요과제다. 이에 따라 본 연구에서는 시범구역 CCTV에서 취득된 일부 교통정보로부터 인근 주차공간의 점유현황을 예측하는 알고리즘을 제안하고자 한다. 모든 구역의 주차정보를 기 설치된 CCTV로 관측하기는 불가하고, 실데이터 부족으로 인해 소수의 라벨링된 데이터를 기반으로 재현데이터를 생성하여 가상학습데이터를 구축하였다. 예측모델은 CNN 구조로 설계되어 지도학습되었으며, 성능평가를 통해 한정된 라벨데이터로부터 주차점유현황예측 가능성을 재단한다.
자율주행용 임베디드 플랫폼 탑재를 위한 YOLOv4 기반 객체탐지 경량화 모델 개발
심이삭(Isaac Shim),임주형(Ju-Hyung Lim),장영완(Young-Wan Jang),유지환(JiHwan You),오선택(SeonTaek Oh),김영근(Young-Keun Kim) 한국자동차공학회 2021 한국 자동차공학회논문집 Vol.29 No.10
The latest CNN-based object detection models are quite accurate, but they require a high-performance GPU to run in real-time. For an embedded system with limited memory space, they are still are heavy in terms of memory size and speed. Since the object detection for autonomous system is run on an embedded processor, it is preferable to compress the detection network as light as possible while preserving detection accuracy. There are several popular lightweight detection models; however, their accuracy is too low for safe driving applications. Therefore, this paper proposes YOffleNet, a new object detection model that is compressed at a high ratio while minimizing the accuracy loss for real-time and safe driving application on an autonomous system. The backbone network architecture is based on YOLOv4, but we could significantly compress the network by replacing the high-calculation-load CSP DenseNet with the lighter modules of ShuffleNet. Experiments with KITTI dataset showed that the proposed YOffleNet is compressed by 4.7 times than the YOLOv4-s that could achieve as fast as 32 FPS on an embedded GPU system(NVIDIA Jetson AGX Xavier). When compared to the high compression ratio, the accuracy is reduced slightly to 85.8 % mAP, which is only 3.6 % lower than YOLOv4-s. As a result, the proposed network showed a high potential for deployment on the embedded system of the autonomous system for real-time and accurate object detection applications.