TY - GEN
T1 - Optical Remote Sensing Images Feature Extraction of Forest Regions
AU - Du, Hailin
AU - Zhuang, Yin
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/12
Y1 - 2019/12
N2 - The forest region saliency extraction technology based on optical remote sensing image plays an important role in forest fire risk monitoring and forest area protection in the process of urbanization. In this paper, the large-area forest area in the optical remote sensing image is highlighted in the feature map, and the salient map is further obtained through the generated feature map to achieve accurate extraction of the optical remote sensing image forest area. Feature extraction includes two parts: adaptive color region extraction through DC (Definition Circle Model) model and corner feature extraction including suppression mechanism through edge detection model. After a series of experiments, the feature-significant extraction technique is more adaptive and accurate than other unsupervised target detection models.
AB - The forest region saliency extraction technology based on optical remote sensing image plays an important role in forest fire risk monitoring and forest area protection in the process of urbanization. In this paper, the large-area forest area in the optical remote sensing image is highlighted in the feature map, and the salient map is further obtained through the generated feature map to achieve accurate extraction of the optical remote sensing image forest area. Feature extraction includes two parts: adaptive color region extraction through DC (Definition Circle Model) model and corner feature extraction including suppression mechanism through edge detection model. After a series of experiments, the feature-significant extraction technique is more adaptive and accurate than other unsupervised target detection models.
KW - Edge detection operator
KW - K-means clustering algorithm
KW - Optical remote sensing image
UR - http://www.scopus.com/inward/record.url?scp=85091937208&partnerID=8YFLogxK
U2 - 10.1109/ICSIDP47821.2019.9173339
DO - 10.1109/ICSIDP47821.2019.9173339
M3 - Conference contribution
AN - SCOPUS:85091937208
T3 - ICSIDP 2019 - IEEE International Conference on Signal, Information and Data Processing 2019
BT - ICSIDP 2019 - IEEE International Conference on Signal, Information and Data Processing 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2019
Y2 - 11 December 2019 through 13 December 2019
ER -