Sökning: WFRF:(Li Peiran) >
Understanding rooft...
Understanding rooftop PV panel semantic segmentation of satellite and aerial images for better using machine learning
-
- Li, Peiran (författare)
- The University of Tokyo, Japan
-
- Zhang, Haoran (författare)
- Mälardalens universitet,Framtidens energi,The University of Tokyo, Japan
-
- Guo, Zhiling (författare)
- The University of Tokyo, Japan
-
visa fler...
-
- Lyu, Suxing (författare)
- The University of Tokyo, Japan
-
- Chen, Jinyu (författare)
- The University of Tokyo, Japan
-
- Li, Wenjing (författare)
- The University of Tokyo, Japan
-
- Song, Xuan (författare)
- SUSTech-UTokyo Joint Research Center on Super Smart City, Department of Computer Science and Engineering, Southern University of Science and Technology (SUSTech), Shenzhen, China
-
- Shibasaki, Ryosuke (författare)
- The University of Tokyo, Japan
-
- Yan, Jinyue, 1959- (författare)
- Mälardalens universitet,Framtidens energi
-
visa färre...
-
(creator_code:org_t)
- Elsevier BV, 2021
- 2021
- Engelska.
-
Ingår i: Advances in Applied Energy. - : Elsevier BV. - 2666-7924. ; 4, s. 100057-100057
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- The photovoltaic (PV) industry boom and increased PV applications call for better planning based on accurate and updated data on the installed capacity. Compared with the manual statistical approach, which is often time-consuming and labor-intensive, using satellite/aerial images to estimate the existing PV installed capacity offers a new method with cost-effective and data-consistent features. Previous studies investigated the feasibility of segmenting PV panels from images involving machine learning technologies. However, due to the particular characteristics of PV panel semantic-segmentation, the machine learning tools need to be designed and applied with careful considerations of the issue formulation, data quality, and model explainability. This paper investigated the characteristics of PV panel semantic-segmentation from the perspective of computer vision. The results reveal that the PV panel image data has several specific characteristics: highly class-imbalance and non-concentrated distribution; homogeneous texture and heterogenous color features; and the notable resolution threshold for effective semantic-segmentation. Moreover, this paper provided recommendations for data obtaining and model design, aiming at each observed character from the viewpoints of recent solutions in computer vision, which can be helpful for future improvement of the PV panel semantic-segmentation.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Maskinteknik -- Energiteknik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Mechanical Engineering -- Energy Engineering (hsv//eng)
Nyckelord
- PV Computer vision Deep learning Satellite and aerial image Semantic segmentation
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas
- Av författaren/redakt...
-
Li, Peiran
-
Zhang, Haoran
-
Guo, Zhiling
-
Lyu, Suxing
-
Chen, Jinyu
-
Li, Wenjing
-
visa fler...
-
Song, Xuan
-
Shibasaki, Ryosu ...
-
Yan, Jinyue, 195 ...
-
visa färre...
- Om ämnet
-
- TEKNIK OCH TEKNOLOGIER
-
TEKNIK OCH TEKNO ...
-
och Maskinteknik
-
och Energiteknik
- Artiklar i publikationen
-
Advances in Appl ...
- Av lärosätet
-
Mälardalens universitet