Work

Small Target Detection and Geolocation Software in Satellite-Based Remote Sensing Image

Year: 2024

Type: conference-paper

Abstract: Due to the limited computing power and storage capacity of satellite equipment, current pixel level small target detection methods cannot operate effectively. This paper proposes a small target detection and geolocation software. To solve the difficulty of detecting pixel-level small targets based on shape, we use K-means clustering based on feature colors for detection. To determine the latitude and longitude of specific locations in remote sensing images captured by satellites, we use maps for image registration to calculate the pixel coordinates of small targets. Finally, the folium library is used to parse the latitude and longitude of that location. The experimental results are consistent with manual annotation and show high accuracy.

DOI: 10.1145/3744103.3744122

Authors: Yuzhou Liu, Ang Yan, Enyue Ji, Peng Wang

Institutions: Nanjing Hydraulic Research Institute, Ministry of Water Resources of the People's Republic of China, Nanjing University of Aeronautics and Astronautics

Language: English

Topic: Remote-Sensing Image Classification

Subfield: Media Technology

Field: Engineering

Domain: Physical Sciences

Open Access status: gold

Funders: Ministry of Water Resources, Nanjing University of Aeronautics and Astronautics, Changjiang River Scientific Research Institute

OpenAlex ID: W4413080866

FWCI:

Cites: 6

Cited by:

Related to: 10