http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
객체 영역에 특화된 뎁스 추정 기반의 충돌방지 기술개발
황규태,송지민,이상준,Gyutae Hwang,Jimin Song,Sang Jun Lee 대한임베디드공학회 2024 대한임베디드공학회논문지 Vol.19 No.2
Collision avoidance system is important to improve the robustness and functional safety of autonomous vehicles. This paper proposes an object-level distance estimation method to develop a collision avoidance system, and it is applied to golfcarts utilized in country club environments. To improve the detection accuracy, we continually trained an object detection model based on pseudo labels generated by a pre-trained detector. Moreover, we propose object-aware depth estimation (OADE) method which trains a depth model focusing on object regions. In the OADE algorithm, we generated dense depth information for object regions by utilizing detection results and sparse LiDAR points, and it is referred to as object-aware LiDAR projection (OALP). By using the OALP maps, a depth estimation model was trained by backpropagating more gradients of the loss on object regions. Experiments were conducted on our custom dataset, which was collected for the travel distance of 22 km on 54 holes in three country clubs under various weather conditions. The precision and recall rate were respectively improved from 70.5% and 49.1% to 95.3% and 92.1% after the continual learning with pseudo labels. Moreover, the OADE algorithm reduces the absolute relative error from 4.76% to 4.27% for estimating distances to obstacles.
황규태,김수석 한국조명전기설비학회 1992 조명.전기설비 Vol.6 No.1
In this paper, the basic idea of optimum electric system design by means of the forecasting of maximum demand is presented, and the load characteristics and practical operating conditions are based on the technical data. After reconstruction of th model plant by use of above method, power supply reliability, future extention, initial cost, and running cost saving effects are analyzed. As a result, it is verified that the systems wherein the power is supply to each load frm main transformer whose capacity is calculated by forecasting are economic rather than the systems wherein the power is supply to each electric feeders from each corresponding transformer.
얼굴 영상 기반의 심박수 추정을 위한 딥러닝 모델의 경량화 기법
황규태,박명근,이상준 대한임베디드공학회 2023 대한임베디드공학회논문지 Vol.18 No.2
This paper proposes a deep learning method for estimating the heart rate from facial videos. Our proposed method estimates remote photoplethysmography (rPPG) signals to predict the heart rate. Although there have been proposed several methods for estimating rPPG signals, most previous methods can not be utilized in low-power single board computers due to their computational complexity. To address this problem, we construct a lightweight student model and employ a knowledge distillation technique to reduce the performance degradation of a deeper network model. The teacher model consists of 795k parameters, whereas the student model only contains 24k parameters, and therefore, the inference time was reduced with the factor of 10. By distilling the knowledge of the intermediate feature maps of the teacher model, we improved the accuracy of the student model for estimating the heart rate. Experiments were conducted on the UBFC-rPPG dataset to demonstrate the effectiveness of the proposed method. Moreover, we collected our own dataset to verify the accuracy and processing time of the proposed method on a real-world dataset. Experimental results on a NVIDIA Jetson Nano board demonstrate that our proposed method can infer the heart rate in real time with the mean absolute error of 2.5183 bpm.
음곡(KI10) 구기자 약침이 난소적출 생쥐의 골다공증에 미치는 영향
황규태 ( Gyu Tae Hwang ),이현 ( Hyun Lee ) 대한경락경혈학회 2009 Korean Journal of Acupuncture Vol.26 No.1
Objective & Methods: The purpose of this study is to observe the effects of herbal-acupuncture with Lycii Fructus (LF-HA) at KI10 (Eumgok) on osteoporosis in ovariectomized (OVX) ddy mice. We carried out several experimental items which were known to be related with osteoporosis. Results: 1. Tibial BMD was significantly increased in the LF-HA group. 2. Tibial Ca level was significantly increased in the LF-HA group. 3. Osteoclast like cell in tibia was significantly decreased in the LF-HA group. 4. Histological change of tibia was improved, the trabecular bone thickness was significantly increased and the growth plate length was significantly decreased in the LF-HA group. Conclusion: These results suggest that LF-HA at KI10 has therapeutic effects on osteoporosis especially by way of suppressing osteoclast cells in ovariectomized ddy mice.