HIGH-RESOLUTION REMOTE SENSING IMAGE SEGMENTATION METHOD BASED ON SReLU

Chenming Li; Xiaoyu Qu; Yao Yang; Hongmin Gao; Yongchang Wang; Dan Yao; Wenjing Yuan

doi:10.2316/j.2019.206-0134

ScienceGate Book Chapters

JOURNAL ARTICLE

HIGH-RESOLUTION REMOTE SENSING IMAGE SEGMENTATION METHOD BASED ON SReLU

Chenming Li Xiaoyu Qu Yao Yang Hongmin Gao Yongchang Wang Dan Yao Wenjing Yuan

Year: 2019 Journal: International Journal of Robotics and Automation Vol: 34 (3)

DOI: 10.2316/j.2019.206-0134

Get Full-Text PDF Get Analytical Report

Abstract

This study proposes a new activation function, namely, S-type rectiﬁed linear unit activation function (SReLU), to alleviate the gradientdispersion of neural network model and improve the segmentationprecision of high-resolution remote sensing images (HRIs).

Keywords:

Activation function Computer science Resolution (logic) Segmentation Function (biology) Image (mathematics) Artificial intelligence Artificial neural network Image segmentation Remote sensing High resolution Computer vision Geology

Metrics

Cited By

0.00

FWCI (Field Weighted Citation Impact)

Refs

0.01

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Advanced Measurement and Detection Methods

Physical Sciences → Engineering → Electrical and Electronic Engineering

Image Processing Techniques and Applications

Physical Sciences → Engineering → Media Technology

Optical Systems and Laser Technology

Physical Sciences → Engineering → Electrical and Electronic Engineering

HIGH-RESOLUTION REMOTE SENSING IMAGE SEGMENTATION METHOD BASED ON SReLU

Abstract

Metrics

Citation History

Topics

Related Documents

FAST SEGMENTATION METHOD OF HIGH-RESOLUTION REMOTE SENSING IMAGE

A Segmentation Based Change Detection Method for High Resolution Remote Sensing Image

High Resolution Remote Sensing Image Segmentation Method with Improved DeepLabv3+

Cascaded panoptic segmentation method for high resolution remote sensing image

Accuracy evaluating method for object-based segmentation of high resolution remote sensing image