Forest land occupation detection in high spatial resolution remote sensing based on spatiotemporal waveband set construction and object-oriented approach

doi:10.13466/j.cnki.lczyyj.2025.05.012

Abstract

Abstract:

To enhance the automation level and efficiency of forest resource monitoring,we adopted spatiotemporal waveband set construction to meet the requirements of high spatial resolution,large scale,mixed temporal phases,and multi-source data.Object-oriented multi-scale clustering segmentation was employed to conduct change detection in forest-occupied areas.Taking Fengxiang District in Shaanxi Province as an example,data band screening and waveband set construction for two periods(2020 and 2021)were carried out using three types of remote sensing image data:Gaofen-1,Gaofen-6,and Ziyuan-3.Through multi-scale region-growing clustering,pixel-level images were aggregated into object units.At the object level,a threshold was set using the joint features of spectral digital numbers and NDVI to achieve automatic detection of forest-occupied areas.The results show that the spatiotemporal waveband set construction and multi-scale object-oriented segmentation method can effectively separate changed areas from unchanged areas.The automatic detection accuracy of occupied forest land was 82.9%.75.3% of the automatic detection plot contour and the actual occupied land contour were evaluated as "high",and the edge extraction accuracy and detection efficiency had significant advantages.Compared with the mainstream post-classification detection methods based on pixels or object-oriented approaches,this method effectively simplifies the operation process by using high-dimensional segmentation that combines space and time,and can be applied to detect changes in forest-occupied land plots,assisting visual interpretation,thereby improving the detection efficiency of behavior that damages forest resources.

Key words: occupied forest, change detection, object-oriented, waveband set construction, multi-scale segmentation

CLC Number:

S771.8
TP79

LIU Xiaoshuang, JIA Yili, ZHAO Yibing. Forest land occupation detection in high spatial resolution remote sensing based on spatiotemporal waveband set construction and object-oriented approach[J]. Forest and Grassland Resources Research, 2025, (5): 105-113.

Figures/Tables 9

Tab.1

Fig.1

Tab.2

Tab.3

Fig.2

Tab.4

Tab.5

Tab.6

Tab.7

References 36

[1]	张煜星, 王雪军, 黄国胜, 等. 森林面积多阶遥感监测方法[J]. 林业科学, 2017, 53(7):94-104.
[2]	吴田军, 胡晓东, 夏列钢, 等. 基于对象级分类的土地覆盖动态变化及趋势分析[J]. 遥感技术与应用, 2014, 29(4):600-606. doi: 10.11873/j.issn.1004-0323.2014.4.0600
[3]	林欣怡, 汪小钦, 汤紫霞, 等. 基于面向对象CNN和RF的不同空间分辨率遥感影像农业大棚提取研究[J]. 遥感技术与应用, 2024, 39(2):315-327. doi: 10.11873/j.issn.1004-0323.2024.2.0315
[4]	刘宣广, 李蒙蒙, 汪小钦, 等. 基于面向对象孪生神经网络的高分辨率遥感影像建筑物变化检测[J]. 遥感学报, 2024, 28(2):437-454.
[5]	ZHOU Huiping, JIANG Hong, HUANG Qinghua. Landscape and water quality change detection in urban wetland:A post-classification comparison method with IKONOS data[J]. Procedia Environmental Sciences, 2011, 10:1726-1731. doi: 10.1016/j.proenv.2011.09.271
[6]	ARDILA J P, BIJKER W, TOLPEKIN V A, et al. Multitemporal change detection of urban trees using localized region-based active contours in VHR images[J]. Remote Sensing of Environment, 2012, 124:413-426. doi: 10.1016/j.rse.2012.05.027
[7]	SANTOSH C, KRISHNAIAH C, PRAVEEN G D. Land use/land cover and change detection in chikodi taluk,belagavi district,karnataka using object based image classification[J]. International Journal of Engineering and Advanced Technology(IJEAT), 2019, 9(1):1522-1527.
[8]	王彩艳, 王瑷玲, 王介勇, 等. 基于面向对象的海岸带土地利用信息提取研究[J]. 自然资源学报, 2014, 29(9):1589-1597. doi: 10.11849/zrzyxb.2014.09.013
[9]	ROBERTSON L D, KING D J. Comparison of pixeland object-based classification in land cover change mapping[J]. International Journal of Remote Sensing, 2011, 32(6):1505-1529. doi: 10.1080/01431160903571791
[10]	WU Qiong, ZHONG Ruofei, ZHAO Wenji, et al. A comparison of pixel-based decision tree and objectbased Support Vector Machine methods for land-cover classification based on aerial images and airborne lidar data[J]. International Journal of Remote Sensing, 2017, 38(23):7176-7195. doi: 10.1080/01431161.2017.1371864
[11]	吴金胜, 刘红利, 张锦水. 无人机遥感影像面向对象分类方法估算市域水稻面积[J]. 农业工程学报, 2018, 34(1):70-77.
[12]	周小成, 庄海东, 陈铭潮, 等. 面向小班对象的森林资源变化遥感监测方法:以福建省厦门市为例[J]. 资源科学, 2013, 35(8):1710-1718.
[13]	杨振兴, 文哲, 张贵, 等. 基于Sentinel-2A数据的森林覆盖变化研究[J]. 中南林业科技大学学报, 2020, 40(8):53-62.
[14]	王崇阳, 田昕. 基于GF-1 PMS数据的森林覆盖变化检测[J]. 遥感技术与应用, 2021, 36(1):208-216. doi: 10.11873/j.issn.1004-0323.2021.1.0208
[15]	MORGAN J L, GERGEL S E. Quantifying historic landscape heterogeneity from aerial photographs using object-based analysis[J]. Landscape Ecology, 2010, 25(7):985-998. doi: 10.1007/s10980-010-9474-1
[16]	HURSKAINEN P, ADHIKARI H, SILJANDER M, et al. Auxiliary datasets improve accuracy of object-based land use/land cover classification in heterogeneous savanna landscapes[J]. Remote Sensing of Environment, 2019, 233:1726-1731.
[17]	林津, 洪宇, 林志玮, 等. 福建泉州湾河口湿地时空动态及其驱动机理[J]. 北京林业大学学报, 2021, 43(6):75-82.
[18]	汪红, 刘兴明, 赵传燕, 等. 基于面向对象的RF算法白水江自然保护区土地利用及景观格局时空演变特征分析[J]. 兰州大学学报(自然科学版), 2021, 57(4):427-436.
[19]	QIN Yao, NIU Zhi, CHEN Feng. Object-based land cover change detection for cross-sensor images[J]. International Journal of Remote Sensing, 2013, 34(19):6723-6737. doi: 10.1080/01431161.2013.805282
[20]	PLATT R V, OGRA M V, BADOLA R, et al. Conservation-induced resettlement as a driver of land cover change in India:An object-based trend analysis[J]. Applied Geography, 2016, 69:75-86. doi: 10.1016/j.apgeog.2016.02.006
[21]	OLMANSON L G, BAUER M E. Land cover classification of the Lake of the Woods/Rainy River Basin by object-based image analysis of landsat and lidar data[J]. Lake and Reservoir Management, 2017, 33(4):335-346. doi: 10.1080/10402381.2017.1373171
[22]	王宁, 陈方, 于博. 基于形态学开运算的面向对象滑坡提取方法研究[J]. 遥感技术与应用, 2018, 33(3):520-529. doi: 10.11873/j.issn.1004-0323.2018.3.0520
[23]	李强, 张景发, 罗毅, 等. 2017年“8.8”九寨沟地震滑坡自动识别与空间分布特征[J]. 遥感学报, 2019, 23(4):785-795.
[24]	SONG Qian, ZHOU Qingbo, WU Wenbin, et al. Mapping regional cropping patterns by using GF-1 WFV sensor data[J]. Journal of Integrative Agriculture, 2017, 16(2):337-347. doi: 10.1016/S2095-3119(16)61392-8
[25]	DORNIK A, DRAGUT L, URDEA P. Classification of soil types using geographic object-based image analysis and random forests[J]. Pedosphere, 2018, 28(6):913-925. doi: 10.1016/S1002-0160(17)60377-1
[26]	李方方, 刘正军, 徐强强, 等. 面向对象随机森林方法在湿地植被分类的应用[J]. 遥感信息, 2018, 33(1):111-116.
[27]	张正健, 李爱农, 雷光斌, 等. 基于多尺度分割和决策树算法的山区遥感影像变化检测方法:以四川攀西地区为例[J]. 生态学报, 2014, 34(24):7222-7232.
[28]	MAO Xuegang, HOU Jiyu. Object-based forest gaps classification using airborne LiDAR data[J]. Journal of Forestry Research, 2019, 30(2):617-627. doi: 10.1007/s11676-018-0652-3
[29]	陈雪, 马建文, 戴芹. 基于贝叶斯网络分类的遥感影像变化检测[J]. 遥感学报, 2005, 9(6):667-672.
[30]	李亮, 舒宁, 王凯, 等. 融合多特征的遥感影像变化检测方法[J]. 测绘学报, 2014, 43(9):945-953. doi: 10.13485/j.cnki.11-2089.2014.0138
[31]	贾永红, 谢志伟, 吕臻, 等. 一种新的遥感影像变化检测方法[J]. 武汉大学学报(信息科学版), 2016, 41(8):1001-1006.
[32]	刘巨峰, 刘勇, 蒋月, 等. 集成基于对象影像分析与贝叶斯软融合的土地覆被变化检测[J]. 兰州大学学报(自然科学版), 2020, 56(2):196-204.
[33]	逄锦娇, 孙睿, 王汶. 高分辨率影像配准误差对土地覆盖分类和变化检测的影响[J]. 遥感技术与应用, 2014, 29(3):498-505. doi: 10.11873/j.issn.1004-0323.2014.3.0498
[34]	杨超, 邬国锋, 李清泉, 等. 植被遥感分类方法研究进展[J]. 地理与地理信息科学, 2018, 34(4):24-32.
[35]	连喜红, 祁元, 王宏伟, 等. 基于面向对象的青海湖环湖区居民地信息自动化提取[J]. 遥感技术与应用, 2020, 35(4):775-785. doi: 10.11873/j.issn.1004-0323.2020.4.0775
[36]	陆海霞, 刘勇, 张寅丹, 等. 集成机器学习与面向地理对象影像分类的大区域林地信息提取及其泛化能力探讨[J]. 兰州大学学报(自然科学版), 2020, 56(3):363-370.

年份	数据源	全色分辨率/m	多光谱分辨率/m	轨道号	获取日期
2020	高分一号	2.0	8.0	E107.1 N34.6	2020-07-30
				E107.1 N34.6	2020-07-30
				E107.1 N34.7	2020-07-25
				E107.7 N34.1	2020-07-23
	资源三号	2.1	5.8	041711_019138	2020-07-14
	资源三号	2.1	5.8	041711_019139	2020-07-14
2021	高分一号	2.0	8.0	E106.9N34.7	2021-06-05
	高分六号	2.0	8.0	E107.8N34.3	2021-06-24
	资源三号	2.1	5.8	022305_020138	2021-06-05
	资源三号	2.1	5.8	022305_020139	2021-06-05

波段编号	年份	波段名称	波长/nm
Band1	2020	近红外(Near-infrared)	770~890
Band2	2020	红(Red)	630~690
Band3	2020	绿(Green)	520~590
Band4	2021	近红外(Near-infrared)	770~890
Band5	2021	红(Red)	630~690
Band6	2021	绿(Green)	520~590

评价指标	评价标准	评价结果/个		评价结论
评价指标	评价标准	是	否	评价结论
欠分割	$\frac{{L}_{\mathrm{C}\mathrm{H}}}{L}$<1 记为“是”,反之记为“否”。	0	13	合格
过分割	$\frac{{\overline{S}}_{\mathrm{F}\mathrm{W}\mathrm{N}}}{\frac{}{\overline{S}}}$<80% 记为“是”,反之记为“否”。	0	13	合格

检测方法	检测结果	对照组		评价结果
检测方法	检测结果	检出	未检出	生产者精度(检出率)	遗漏率
自动检测	检出	97	34	82.9%	17.1%
自动检测	未检出	20		82.9%	17.1%

综合评价	评价等级
综合评价	高	较高	一般	低
标准	[90%,100%]	[80%,90%)	[60%,80%)	[0,60%)
个数	51	22	11	13
占比/%	52.6	22.7	11.3	13.4