http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : ( Beanbonyka Rim ) (검색결과 2 건)
- 무료
- 기관 내 무료
- 유료
-
Real-time Vehicle Classification on Phnom Penh Road in Video Surveillance
Beanbonyka Rim,Sovila Srun,Arnold Williem,Brian C. Lovell 대한전자공학회 2017 대한전자공학회 학술대회 Vol.2017 No.1
In this work we tackle traffic analysis problems for Phnom Penh roads. Unlike in most developed countries such as Australia and USA, the traffic conditions in developing countries such as Cambodia pose unique challenges. For instance, motorcycles are popular vehicles. This means, during peak hours, where the traffic for cars is congested, the traffic for motorcycles could still be flowing. Thus, any approaches using the whole video to determine the traffic condition are not suitable. To that end, this work provides the first stepping-stone by addressing the Phnom Penh vehicle classification problem. We propose a novel dataset capturing CCTV of Phnom Penh roads in 5 locations from 7am until 5pm on five sunny days. Then, we perform the study by proposing a baseline method comprising three steps: (1) background subtraction; (2) bag-of-word histogram feature extraction; and (3) classification using Support Vector Machine (SVM). Evaluation results show promising results with accuracy 0.76, 0.63 and 0.40 for light, medium and heavy traffic.
-
Empirical Comparison of Deep Learning Networks on Backbone Method of Human Pose Estimation
( Beanbonyka Rim ),( Junseob Kim ),( Yoo-joo Choi ),( Min Hong ) 한국인터넷정보학회 2020 인터넷정보학회논문지 Vol.21 No.5
Accurate estimation of human pose relies on backbone method in which its role is to extract feature map. Up to dated, the method of backbone feature extraction is conducted by the plain convolutional neural networks named by CNN and the residual neural networks named by Resnet, both of which have various architectures and performances. The CNN family network such as VGG which is well-known as a multiple stacked hidden layers architecture of deep learning methods, is base and simple while Resnet which is a bottleneck layers architecture yields fewer parameters and outperform. They have achieved inspired results as a backbone network in human pose estimation. However, they were used then followed by different pose estimation networks named by pose parsing module. Therefore, in this paper, we present a comparison between the plain CNN family network (VGG) and bottleneck network (Resnet) as a backbone method in the same pose parsing module. We investigate their performances such as number of parameters, loss score, precision and recall. We experiment them in the bottom-up method of human pose estimation system by adapted the pose parsing module of openpose. Our experimental results show that the backbone method using VGG network outperforms the Resent network with fewer parameter, lower loss score and higher accuracy of precision and recall.
ScienceON연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
