An Attachment Recognition Method Based on Image Generation and Semantic Segmentation for Marine Current Turbines

Author(s):  
Haiyang Peng ◽  
Tianzhen Wang ◽  
Shreya Pandey ◽  
Lisu Chen ◽  
Funa Zhou
2021 ◽  
Vol 93 ◽  
pp. 107182
Author(s):  
Haiyang Peng ◽  
Dingding Yang ◽  
Tianzhen Wang ◽  
Shreya Pandey ◽  
Lisu Chen ◽  
...  

2021 ◽  
Author(s):  
Jiajun Ai ◽  
Lijie Hua ◽  
Jin Liu ◽  
Shunshun Chen ◽  
Yongjian Xu ◽  
...  

2020 ◽  
Vol 34 (07) ◽  
pp. 11637-11644
Author(s):  
Yinglu Liu ◽  
Hailin Shi ◽  
Hao Shen ◽  
Yue Si ◽  
Xiaobo Wang ◽  
...  

Face parsing has recently attracted increasing interest due to its numerous application potentials, such as facial make up and facial image generation. In this paper, we make contributions on face parsing task from two aspects. First, we develop a high-efficiency framework for pixel-level face parsing annotating and construct a new large-scale Landmark guided face Parsing dataset (LaPa). It consists of more than 22,000 facial images with abundant variations in expression, pose and occlusion, and each image of LaPa is provided with an 11-category pixel-level label map and 106-point landmarks. The dataset is publicly accessible to the community for boosting the advance of face parsing.1 Second, a simple yet effective Boundary-Attention Semantic Segmentation (BASS) method is proposed for face parsing, which contains a three-branch network with elaborately developed loss functions to fully exploit the boundary information. Extensive experiments on our LaPa benchmark and the public Helen dataset show the superiority of our proposed method.


Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1700 ◽  
Author(s):  
Hyun-Koo Kim ◽  
Kook-Yeol Yoo ◽  
Ju H. Park ◽  
Ho-Youl Jung

A traffic light recognition system is a very important building block in an advanced driving assistance system and an autonomous vehicle system. In this paper, we propose a two-staged deep-learning-based traffic light recognition method that consists of a pixel-wise semantic segmentation technique and a novel fully convolutional network. For candidate detection, we employ a binary-semantic segmentation network that is suitable for detecting small objects such as traffic lights. Connected components labeling with an eight-connected neighborhood is applied to obtain bounding boxes of candidate regions, instead of the computationally demanding region proposal and regression processes of conventional methods. A fully convolutional network including a convolution layer with three filters of (1 × 1) at the beginning is designed and implemented for traffic light classification, as traffic lights have only a set number of colors. The simulation results show that the proposed traffic light recognition method outperforms the conventional two-staged object detection method in terms of recognition performance, and remarkably reduces the computational complexity and hardware requirements. This framework can be a useful network design guideline for the detection and recognition of small objects, including traffic lights.


2019 ◽  
Author(s):  
K Herdinai ◽  
S Urbán ◽  
Z Besenyi ◽  
L Pávics ◽  
N Zsótér ◽  
...  

2019 ◽  
Vol 6 (1) ◽  
pp. 1
Author(s):  
Yuli Anwar

Revenue and cost recognitions is the most important thing to be done by an entity,  time and the recognition method must be based on the rules from Financial Accounting Standards. Revenue and cost recognition which is done by PT. EMKL Jelutung Subur located on Pangkalpinang, Bangka Belitung province is done by using the accrual basis, and it can be seen with its influences to company profits every year.  This research is useful to get a data and information for preparing this thesis and improving my knowledge and also for comparing between theories accepted against facts applied in the field.  The result of this research shows that PT. EMKL Jelutung Subur has implemented one of the revenue and cost recognition method (accrual basis) continually, so that profit accuracy is accountable to be used for developing this kind of expedition business in order to become a better company. The accuracy is evaluated because all revenues received and cost spent  have clear evidence and found in the period of time.  The evaluation shows there is one thing that miss from revenue and cost recognition done by PT. EMKL Jelutung Subur, that is charge to the customers who use the storage service temporary, because some customers keep their goods for a long time in the warehouse, and it will increase the costs of loading, warehouse maintenance, damaged goods and decreasing a quantity of goods. If the storage service is charged to the customers, PT. EMKL Jelutung Subur will earn additional revenue to cover all the expenses above


Sign in / Sign up

Export Citation Format

Share Document