Comprehensive Performance Evaluation for Video Surveillance Cameras

2015 ◽  
Vol 52 (9) ◽  
pp. 091102
Author(s):  
卢树华 Lu Shuhua ◽  
黄鸿志 Huang Hongzhi ◽  
张鸿洲 Zhang Hongzhou ◽  
王丽辉 Wang Lihui ◽  
王照明 Wang Zhaoming ◽  
...  
2021 ◽  
Vol 13 (9) ◽  
pp. 4678
Author(s):  
Yi-Jia Xing ◽  
Tse-Lun Chen ◽  
Meng-Yao Gao ◽  
Si-Lu Pei ◽  
Wei-Bin Pan ◽  
...  

Green infrastructure practices could provide innovative solutions for on-site stormwater management and runoff pollution control, which could relieve the stress of nonpoint pollution resulting from heavy rainfall events. In this study, the performance and cost-effectiveness of six green infrastructure practices, namely, green roofs, rain gardens, pervious surfaces, swales, detention basins, and constructed wetlands, were investigated. The comprehensive performance evaluation in terms of the engineering performance, environmental impact, and economic cost was determined in the proposed engineering–environmental–economic (3E) triangle model. The results revealed that these green infrastructure practices were effective for stormwater management in terms of runoff attenuation, peak flow reduction and delay, and pollutant attenuation. It was suggested that for pollution control, detention basins can efficiently reduce the total suspended solids, total nitrogen, total phosphorus, and lead. The implementation of detention basins is highly recommended due to their higher engineering performance and lower environmental impact and economic cost. A case study of a preliminary cost–benefit analysis of green infrastructure practice exemplified by the Pearl River Delta in China was addressed. It suggested that green infrastructure was cost-effective in stormwater management in this area, which would be helpful for sustaining healthy urban watersheds.


2021 ◽  
Vol 54 ◽  
pp. 775-782
Author(s):  
Dmitry Gura ◽  
Ivan Markovskii ◽  
Nafset Khusht ◽  
Irina Rak ◽  
Saida Pshidatok

With the emergence of new concepts like smart hospitals, video surveillance cameras should be introduced in each room of the hospital for the purpose of safety and security. These surveillance cameras can also be used to provide assistance to patients and hospital staff. In particular, a real-time fall of a patient can be detected with the help of these cameras and accordingly, assistance can be provided to them. Different models have already been developed by researchers to detect a human fall using a camera. This paper proposes a vision based deep learning model to detect a human fall. Along with this model, two mathematical based models have also been proposed which uses pre-trained YOLO FCNN and Faster R-CNN architecture to detect the human fall. At the end of this paper, a comparison study has been done on these models to specify which method provides the most accurate results


Sign in / Sign up

Export Citation Format

Share Document