Discrepancy measures for selecting optimal combination of parameter values in object-based image analysis

Liu, Yong; Bian, Ling; Meng, Yuhong; Huan-Ping, Wang; Zhang, Shifu; Yang, Yining; Shao, Xiaomin; Wang, Bo

doi:10.1016/j.isprsjprs.2012.01.007

Cited by 128 publications

(113 citation statements)

References 19 publications

Supporting

Mentioning

108

Contrasting

Unclassified

Order By: Relevance

“…In fact, based on the results obtained in this specific work, a good segmentation would require more than 100 ROs. It is relevant that only around 30 ROs per class were used in previous segmentation quality studies [4,20] and that, in this case study, 30 ROs were not enough to guarantee stable results. Figure 3 shows, as already reported in Aguilar et al [11], that the ED2 metric can be characterized by a very good relationship with the visual quality of plastic-covered greenhouses segmentations.…”

Section: Discussionmentioning

confidence: 96%

Section: Discussionmentioning

confidence: 96%

“…Indeed, in previous scientific works, only a reduced number of ROs were used to assess the segmentation accuracy (e.g., in [4,9,11,20], this number was less than 100). The improvement achieved through the use of a large RO input can be demonstrated in the chosen test area.…”

Section: Discussionmentioning

confidence: 99%

“…Scientific literature proposes different methods for assessing the segmentation quality both from unsupervised and supervised approaches (e.g., Drȃguţ et al [3], Liu et al [4]). However, the proposed methods are not always coupled with tools able to automatically compute the described metrics.…”

Section: Introductionmentioning

confidence: 99%

“…However, the proposed methods are not always coupled with tools able to automatically compute the described metrics. To overcome the limited availability of software assessing segmentation accuracy, this paper presents a free of charge command line tool (AssesSeg) that implements a modified version of the supervised discrepancy measure named Euclidean Distance 2 (ED2) proposed by Liu et al [4]. AssesSeg was used to detect the best band combinations for the detection of plastic-covered greenhouses from three multispectral satellite data: Sentinel-2 (S2), Landsat 8 (L8), and WorldView-2 (WV2) images.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

AssesSeg—A Command Line Tool to Quantify Image Segmentation Quality: A Test Carried Out in Southern Spain from Satellite Imagery

Novelli¹,

Aguilar²,

Aguilar³

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

This letter presents the capabilities of a command line tool created to assess the quality of segmented digital images. The executable source code, called AssesSeg, was written in Python 2.7 using open source libraries. AssesSeg (University of Almeria, Almeria, Spain; Politecnico di Bari, Bari, Italy) implements a modified version of the supervised discrepancy measure named Euclidean Distance 2 (ED2) and was tested on different satellite images (Sentinel-2, Landsat 8, and WorldView-2). The segmentation was applied to plastic covered greenhouse detection in the south of Spain (Almería). AssesSeg outputs were utilized to find the best band combinations for the performed segmentations of the images and showed a clear positive correlation between segmentation accuracy and the quantity of available reference data. This demonstrates the importance of a high number of reference data in supervised segmentation accuracy assessment problems.

show abstract

Section: Discussionmentioning

confidence: 96%

Section: Discussionmentioning

confidence: 96%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

AssesSeg—A Command Line Tool to Quantify Image Segmentation Quality: A Test Carried Out in Southern Spain from Satellite Imagery

Novelli¹,

Aguilar²,

Aguilar³

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

show abstract

Remote‐sensing‐derived fractures and shrub patterns to identify groundwater dependence

et al. 2018

View full text Add to dashboard Cite

The identification and location of groundwater‐dependent ecosystems are the first steps in protecting and managing them. Such identifications are challenging where the surface expressions of groundwater are not obvious. This work presents a remote‐sensing‐based approach to infer the groundwater dependence of semiarid shrubs from their association with fractures that facilitate root access to groundwater. As a case study, we used the Ziziphus lotus matorral in south‐east Spain, a priority conservation habitat in the European Union (Habitat 5220*, Directive 92/43/EEC) that is highly threatened by agricultural and urban sprawl. The approach combines object‐based image analysis of high‐resolution orthoimages to map Ziziphus individuals, geomorphometric analysis of a lidar‐derived terrain model to map bedrock fractures, and spatial statistics to assess the association between Ziziphus and fractures. Electrical resistivity tomography was used to validate the identified fractures, and the seasonal dynamics of the normalized difference vegetation index was used to prove that Z. lotus maintained higher greenness during the summer drought and was less coupled with precipitation than the nearby nonphreatophytic vegetation. A majority (61%) of the Ziziphus patches, particularly the smallest ones, occurred within 50 m of faults. This spatial association between phreatophyte shrubs and fractures contributes to the identification of groundwater‐dependent ecosystems. This approach offers several advantages because it is simple, low cost, and non‐destructive. In addition, the differentiation of shrubs into size classes provided insights into the long‐term environmental controls underlying the establishment of Ziziphus individuals. The evidence of groundwater dependence by Z. lotus in Habitat 5220* indicates the need for its urgent protection under the Water Framework Directive.

show abstract

Spatial Data Reduction Through Element-of-Interest (EOI) Extraction

Arundel

Usery

2021

Handbook of Big Geospatial Data

View full text Add to dashboard Cite

Discrepancy measures for selecting optimal combination of parameter values in object-based image analysis

Cited by 128 publications

References 19 publications

AssesSeg—A Command Line Tool to Quantify Image Segmentation Quality: A Test Carried Out in Southern Spain from Satellite Imagery

AssesSeg—A Command Line Tool to Quantify Image Segmentation Quality: A Test Carried Out in Southern Spain from Satellite Imagery

Remote‐sensing‐derived fractures and shrub patterns to identify groundwater dependence

Spatial Data Reduction Through Element-of-Interest (EOI) Extraction

Contact Info

Product

Resources

About