论文研究-基于语义分割的作物检测遥感数据融合_遥感农作物分割

行业研究

需积分: 0 464 浏览量更新于2023-05-26 评论 2 收藏 720KB PDF 举报

身份认证购VIP最低享 7 折!

领优惠券(最高得80元）

资源详情

资源评论

资源推荐

Journal of Computer and Communications, 2019, 7, 53-64

http://www.scirp.org/journal/jcc

ISSN Online: 2327-5227

ISSN Print: 2327-5219

DOI:

10.4236/jcc.2019.77006 Jul. 10, 2019 53 Journal of Computer and Communications

Semantic Segmentation Based Remote Sensing

Data Fusion on Crops Detection

Jose Pena

1,2

, Yumin Tan

, Wuttichai Boonpook

School of Transportation Science and Engineering, Beihang University, Beijing, China

Venezuela Space Agency (ABAE), Caracas, Venezuela

Abstract

Data fusion is usually an important process in multi-

sensor remotely sensed

imagery integration environments with the aim of enriching features lacking

in the sensors involved in the fusion process. This technique has attracted

much interest in many researches especially in the field of agriculture. On

the

other hand, deep learning (DL) based semantic segmentation shows high

performance in remote sensing classification, and it requires large datasets in

a supervised learning way. In the paper, a method of fusing multi-source re-

mote sensing images with c

onvolution neural networks (CNN) for semantic

segmentation is proposed and applied to identify crops. Venezuelan Remote

Sensing Satellite-2 (VRSS-2) and the high-

resolution of Google Earth (GE)

imageries have been used and more than 1000 sample sets have b

een collected

for supervised learning process. The experiment results show that the crops

extraction with an average overall accuracy more than 93% has been ob-

tained, which demonstrates that data fusion combined with DL is highly

feasible to crops extracti

on from satellite images and GE imagery, and it

shows that deep learning techniques can serve as an invaluable tools for larger

remote sensing data fusion frameworks, specifically for the applications in

precision farming.

Keywords

Data Fusion, Crops Detection, Semantic Segmentation, VRSS-2

1. Introduction

At present RS technology has received great attention in the agriculture com-

munity due to its ability to provide periodic and regional information for crop

monitoring and thematic mapping [1] [2]. Modern RS to identify any features

How to cite this paper:

Pena, J., Tan, Y.M

and

Boonpook, W. (2019) Semantic Seg-

mentation Based Remote Sensing Data

Fusion on Crops Detection

Journal of

Computer and

Communications

, 53-64.

https://doi.org/10.4236/jcc.2019.77006

Received:

May 20, 2019

Accepted:

July 7, 2019

Published:

July 10, 2019

J. Pena et al.

DOI:

10.4236/jcc.2019.77006 54 Journal of Computer and Communications

on the surface is no longer considered as a processing of a one-source single date

image. It has shifted to multi-source fusion of multi-temporal images. Several

spectral indices have been proven to be valuable tools in describing crop spatial

variability. In this context, the images of high spatial and spectral resolution

have already proved their potential and effectiveness in crop detection. However,

when we are considering to identify the types of crops with multispectral image-

ries, RS becomes more challenging. The main challenge of satellite based remote

sensing application in agricultural field at present is that there is no suitable

sensors with very high spatial resolution like below 50 centimeters and with a

good temporal resolution and spectral resolution at the same time.

Indeed, novel approaches and algorithms using Unmanned Aerial Vehicle

(UAV) or satellite based multispectral imaging have been developed for vegeta-

tion classification [3]. But, the acquisition of UAV images or images of other

platform such as GeoEye-1, WorldView-4 and KompSat 3a can be difficult to

acquire considering the high cost, and their availability only in the specific small

region. Google Earth (GE) provides an open data source with very high spatial

resolution, which represents a very good alternative for crops detection. Very

few studies have been undertaken to use GE images as the direct data source for

land use/cover mapping [4]. Numerous methods based on DL have been pro-

posed recently for agricultural applications over specific RS data, especially fo-

cusing on high resolution and hyperspectral images [5], plant phenotyping [6]

or weed scouting [7] and early disease detection [8]. However, some recent ap-

proaches have tried to directly adopt deep architectures designed to identify

other aspects related to the vegetation or the diseased plants, the results, al-

though very encouraging, appeared coarse [9].

In this research, we are going to identify several types of crops that has very

different shapes, sizes, and color intensities, and the surrounding plants and

background soil strongly differ across regions. In addition, data fusion of RGB

images (with high spatial resolution) obtained from Google platforms and mul-

tispectral satellite imagery obtained from Venezuelan Remote Sensing Satellite

(VRSS-2), will be done through Gram-Schmidt (GS) pan-sharpening method.

Fusion images and vegetation indices (VIs) were used as input to following Seg-

Net based semantic segmentation. Our main contributions can be summarized

as: this is probably the first attempt conducted to explore the combination of

VRSS-2 and GE imagery, through a data fusion process for crop detection; a

SegNet-based semantic segmentation model is proposed for crop type detection,

capable of adapting to fusing data sets in which the results proved that this ap-

proach provide better performance than that of the traditional classification

methods; a self-designed preparation of data sets and semantic segmentation

network have been employed to provide a per pixel labelling of the input data;

finally, two different data sets from VRSS-2 and GE, those are obtained abso-

lutely free of cost, have been employed with several pre-processing and

post-processing strategies, designed and combined with Segnet architecture, that

has increased the overall accuracy.

J. Pena et al.

DOI:

10.4236/jcc.2019.77006 55 Journal of Computer and Communications

2. Materials and Methods

2.1. Study Area

The study area is located in the north-central region of Venezuela, Aragua State,

Palo Negro Sector-Venezuela. The most important agricultural production is

concentrated in this area and the main crops produced are banana, pasture, pa-

paya and coco. Banana and pasture production have greater importance in the

study area, because they represent 65% of the economy of that region of Vene-

zuela. In recent years their production and thereby, the source of employment

have been declined considerably. Reasonably, the state has taken steps to identify

and quantify the possible reasons and overcome the problems. ‘Bare land’ comes

into this issue as one of the solutions to increase their production using that

lands which are in plenty. In this study, different training zones and testing zone

are used.

2.2. Data Sets Construction

The design of the training dataset is the key to the performance of a good CNN

classification model, and the construction of dataset is described below. All three

datasets used in this research are contained the RGB image set from VRSS-2

image, Google earth mapping, and data fusion images which are composed of

the multispectral bands including RGB bands, Near-infrared (NIR), and norma-

lized difference vegetation index (NDVI).

2.2.1. VRSS-2 Image

VRSS-2 was launched on October 09, 2017, and owned by the Bolivarian Agency

for Space Activities (ABAE). It contains two different cameras, High Resolution

Camera (panchromatic and multispectral sensors) and Infrared Camera. VRSS-2

data has a total of 10 bands including a panchromatic band (band 1) which has 1

meter of spatial resolution, nine multispectral bands (band 2 - 10) which has the

spatial resolution in 3 meter (band 2 - 5), 30 m (band 6 - 8) and 60m (band 9 -

10) respectively. However, in this research, only five bands are selected (bands 1

- 5).

The radiometric calibration procedure is first applied to selected VRSS-2 im-

ages to generate a consistent output images. To obtain the high-quality fusion

data, it is important to apply the data corrections for various lighting conditions

such as overcast skies and partial cloud coverage. To correct for this aspect, we

utilize sunlight sensors measuring the sun’s orientation and sun irradiance, as

shown in

Figure 1.

The obtained data are stored as quantized and calibrated Digital Numbers

(DN). The DN are converted to surface reflectance value using the Equation (1)

with coefficients provided in metadata file and ABAE.

(

)

( )

/ cos

TOA

sum s

Ld E

ρπ θ

= ×× ×

(1)

where,

TOA

is surface reflectance of the earth at the top of the atmosphere,

apparent radiance at the top of the atmosphere in Watt/m

/stereo-radian/

剩余11页未读，继续阅读

weixin_38576392

粉丝: 7
资源: 896

会员权益专享

论文研究 - 基于语义分割的作物检测遥感数据融合

评论0

会员权益专享

最新资源

论文研究 - 基于语义分割的作物检测遥感数据融合

评论0

基于通信、导航、遥感相融合的发展思路，提出在应用领域的一体化解决方案

基于改进神经网络的农作物产量预测方法

介绍语义分割，要介绍概念、来源、现在的应用情况

作物模型与数据同化的研究有哪些创新

写一个农业遥感发展的研究综述论文

landsat 8地表温度反演免费软件-北大遥感所

无人机遥感图像中的小麦病害检测python

请思考遥感解译数据应用于金融投资领域的其他方面的场景，简述其中两例，并给出原因。

遥感作物蒸散发模型有哪些

苹果叶片病害检测论文

用python编写从遥感影像提取作物长势信息的代码

基于yolov5的苹果叶片病害检测论文摘要

作物模型与数据同化怎么结合

作物模型同化方向的创新点

城市水足迹研究对作物水足迹有什么借鉴意义

基于于ZigBee的智慧农业环境采集系统 国内外研究现状详细介绍

6月份公益课.rar

会员权益专享

最新资源

基于于ZigBee的智慧农业环境采集系统国内外研究现状详细介绍