ICESat waveform-based land-cover classification using a curve matching approach

Zhou, Yuhong; Qiu, Fang; Aldosari, Ali; Alfarhan, Mohammed

doi:10.1080/01431161.2014.990648

Cited by 12 publications

(10 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To detect anomalous signals from these data, an effective analyzing method is needed. Thus, we integrate ideas from the ground object spectrum [29] and construct the frequencyintensity curve (Figure 4 as an example) to represent the electromagnetic radiation condition at different sampling points. Such a method lays a foundation for future anomaly detection of the electromagnetic environment.…”

Section: Construction Of Electromagnetic Anomaly Detection Methodsmentioning

confidence: 99%

Detecting Electromagnetic Geographical Environment Changes Based on the Frequency‐Intensity Curve

et al. 2021

View full text Add to dashboard Cite

Electromagnetic geographic environment is closely related to human life. With continuous popularization of public infrastructures and daily electronic instruments, such as electric power communication systems and household appliances, electromagnetic radiation sources have increased sharply in the geographic environment, which leads to increasingly serious electromagnetic radiation pollution. Thus, it is significant to monitor, evaluate, and analyze the electromagnetic radiation condition and explore its changing law in the environment. However, the traditional monitoring method can only detect anomalies within certain frequencies in the fixed stations. To fill this gap, this research first develops a vehicle-mounted electromagnetic environment monitoring system to collect both spatial positioning data and electromagnetic data of the whole frequency range. The acquired data are then used to construct the location-based frequency-intensity curve to reflect the variation of electromagnetic radiation at different frequency ranges. On this basis, a curve similarity measurement method is introduced to analyze the similarity of different curves, which is effective to diagnose time-varying sources from both global and local perspectives. This research provides a real-time mobile monitoring method, which is significant to know the dynamic variation of local electromagnetic environment and promotes subsequent comprehensive geographic analyses.

show abstract

Section: Construction Of Electromagnetic Anomaly Detection Methodsmentioning

confidence: 99%

Detecting Electromagnetic Geographical Environment Changes Based on the Frequency‐Intensity Curve

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Few studies on land cover classification have been carried out in the past decade. These studies used decision tree approach (Duong et al 2006), curve matching method (Zhou et al 2015) and machine learning techniques (Liu et al 2015) to classify land cover types with an overall accuracy of around 73-87 %. Liu et al (2015) also used multi-sensor (ICESat/GLAS and Landsat Thematic Mapper (TM)/Enhanced TM Plus (ETM?))…”

Section: Introductionmentioning

confidence: 99%

Land Cover Classification Using ICESat/GLAS Full Waveform Data

Ghosh¹,

Nandy²,

Patra³

et al. 2016

J Indian Soc Remote Sens

View full text Add to dashboard Cite

In the present study, parameters derived from Ice, Cloud, and land Elevation Satellite/Geoscience Laser Altimeter System (GLAS) full waveform were used for land cover classification in western part of Doon valley, Uttarakhand, India. Three parameters, viz, height, front slope angle (afslope) and canopy return ratio (rCanopy) were extracted from the returned full waveform signals. k-means (KM), partitioning around medoids (PAM), and fuzzy c-means (FCM) with different cluster sizes were used for classifying the land cover types with the help of GLASderived parameters. Among the clustering methods, KM performed the best. The overall accuracy (89.41 %) of all methods were quite significant with cluster size three i.e. with three classes forest, mango orchard and other class including agriculture, barren/fallow land, settlement, dry river bed, etc. The accuracy of the PAM (60 %) and the FCM (68.4 %) decreased drastically at four clusters with the separation of agriculture from barren/fallow land. The accuracy of the PAM and the FCM further decreased with increase in the number of clusters whereas KM showed reliable results for all clusters. KM with five clusters was able to distinguish five different land covers, viz, forest, mango orchard, agriculture and barren/fallow land and other class including settlement, dry river bed, etc. with an overall classification accuracy of 72.93 %. The study presents a method for classifying land cover types using GLAS full waveform data.

show abstract

“…S PACEBORNE remote sensing has an ability to observe the Earth almost all the time, thus helping to derive more information about the land cover at the global scale. This technology can overcome the disadvantages of traditional field surveying, such as high costs in the time and labor, many hard-to-reach areas, and dependence of subjective judgment [1]. One method of remote sensing is passive optical imagery, which could collect multispectral, hyperspectral, and high-resolution images.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, additional features (e.g., metrics in distance) specified by the users can also be extracted from the full-waveform. Land cover classification using data extracted from these remote sensing methods can be utilized by geographers and ecologists to monitor, assess, and understand the ongoing process that drives the geographical changes and identify strategies for sustainable development [1], [13].…”

Section: Introductionmentioning

confidence: 99%

Classification of Laser Footprint Based on Random Forest in Mountainous Area Using GLAS Full-Waveform Features

Liu

Wang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Full-waveform spaceborne laser altimeter can provide more characteristic parameters of the laser footprint and rich vertical structure information on the target surface. This technology has the potential for land-cover classification, especially in hard-to-reach mountain areas. Classifying the land types based on the returned waveform can provide a convenient way for the online classification needs and assess the quality of footprint used as the ground control point in photogrammetry. This article presents a random forest (RF) classification using geoscience laser altimeter system waveform, in the west-central Yunnan Province, China. First, an improved threshold wavelet is performed to denoise the waveform, and then Gaussian decomposition is used to extract the typical characteristic features of footprint. Second, an RF algorithm is implemented to clarify the footprints into five types: flat, building, terrace, forest, and mountain. Finally, quantitative analysis is conducted with producer's accuracy (PA), user's accuracy (UA), overall accuracy (OA), precision, recall rate, F1-score, and kappa coefficient to compare the performance of RF with other classifiers, including linear support vector machine (linear-SVM), radial basis function SVM (RBF-SVM), logistic regression (LR), K-nearest neighbor (KNN), and naive Bayes (NB). The results show that all the six methods can accurately classify the flat land with 100.00% PA and UA. The RF also has the best performances in other four land types, with PA and UA of 98.14% and 100.00%, 97.24% and 95.49%, 98.64% and 96.03%, and 94.64% and 100.00%, respectively. The OA, precision, recall, F1-score, and kappa coefficient for the RF are 97.95%,

show abstract

ICESat waveform-based land-cover classification using a curve matching approach

Cited by 12 publications

References 44 publications

Detecting Electromagnetic Geographical Environment Changes Based on the Frequency‐Intensity Curve

Detecting Electromagnetic Geographical Environment Changes Based on the Frequency‐Intensity Curve

Land Cover Classification Using ICESat/GLAS Full Waveform Data

Classification of Laser Footprint Based on Random Forest in Mountainous Area Using GLAS Full-Waveform Features

Contact Info

Product

Resources

About