Investigating the Resolution-Performance Trade-off of Object Detection Models in Support of the Sustainable Development Goals

Clark, Chris; Bedada, Adane; Huff, Brian; Lita, B.; Newbury, Amy B.; Pacifici, Fabio

doi:10.1109/jstars.2023.3284309

Cited by 4 publications

(2 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also expand upon the results of current publications investigating the resolution-performance trade-off for accurate small object detection in satellite imagery 20 – 25 . Results of these studies indicate accuracy of small object detection in satellite imagery may be improved by increasing spatial resolution.…”

Section: Background and Summarymentioning

confidence: 75%

A solar panel dataset of very high resolution satellite imagery to support the Sustainable Development Goals

Clark,

Pacifici

2023

Sci Data

Self Cite

View full text Add to dashboard Cite

Effectively supporting the United Nations’ Sustainable Development Goals requires reliable, substantial, and timely data. For solar panel installation monitoring, where accurate reporting is crucial in tracking green energy production and sustainable energy access, official and regulated documentation remains inconsistent. Reports of solar panel installations have been supplemented with object detection models developed and used on openly available aerial imagery, a type of imagery collected by aircraft or drones and limited by cost, extent, and geographic location. We address these limitations by providing a solar panel dataset derived from 31 cm resolution satellite imagery to support rapid and accurate detection at regional and international scales. We also include complementary satellite imagery at 15.5 cm resolution with the aim of further improving solar panel detection accuracy. The dataset of 2,542 annotated solar panels may be used independently to develop detection models uniquely applicable to satellite imagery or in conjunction with existing solar panel aerial imagery datasets to support generalized detection models.

show abstract

Section: Background and Summarymentioning

confidence: 75%

A solar panel dataset of very high resolution satellite imagery to support the Sustainable Development Goals

Clark,

Pacifici

2023

Sci Data

Self Cite

View full text Add to dashboard Cite

show abstract

“…To achieve the sustainable development goals (SDGs), efforts are being undertaken within various sectors through awareness campaigns and dialogues [1], and are being examined [2]. In the engineering field, advanced technologies based on the IoT network technology have been considered as new scenarios, particularly since COVID-19 [3].…”

Section: Introductionmentioning

confidence: 99%

Energy-Harvesting System and Transfer Matrix Model for Pressure Regulators

Yoshida,

Hamada,

Watanabe

et al. 2023

IEEE Access

View full text Add to dashboard Cite

This study is focused on energy harvesting. The goal was to develop a new energy-harvesting system using a pressure regulator and establish an efficient energy flow model within it. The harvested electrical energy can be used as a power source for devices around the regulator, such as primary battery-powered gas meters, thereby enabling battery-free operation. Here, we focus on pressure regulators for LP and city gases, which are used by a vast number of consumers. We systematically modeled complicated energy-conversion processes using the transfer matrix method to maximize the recovered electrical energy. Under normal gas usage conditions, the gas flow is low, and the harvested energy is limited. However, it surpasses the energy supplied by the primary batteries. The results obtained under the actual operational conditions were compared with those calculated using a theoretical model. Within the system, a DC motor and an AC motor were used as generators, and the results were compared. When a DC motor was used as the generator under 0.05 MPa, 0.8 L/m, and maximum power-harvesting load conditions, the harvested power was 0.237 W, which is sufficient to drive the meters. Additionally, the error between the experimental and theoretical results ranged from 2.6% to 4.6%. When an AC motor was used as a generator, the harvested energy was 0.015 W and the error was -14.7%. Utilizing this theoretical model allows for the calculation of the optimal conditions for energy harvesting from various pressure regulators, thereby offering design guidelines for energy-harvesting systems.

show abstract

Design of an iterative method for environmental-sustainable development: Integrating bioinspired computing techniques

Chatrabhuj,

Meshram

2024

Environmental Development

View full text Add to dashboard Cite

Investigating the Resolution-Performance Trade-off of Object Detection Models in Support of the Sustainable Development Goals

Cited by 4 publications

References 82 publications

A solar panel dataset of very high resolution satellite imagery to support the Sustainable Development Goals

A solar panel dataset of very high resolution satellite imagery to support the Sustainable Development Goals

Energy-Harvesting System and Transfer Matrix Model for Pressure Regulators

Design of an iterative method for environmental-sustainable development: Integrating bioinspired computing techniques

Contact Info

Product

Resources

About