On the Objectivity of the Objective Function—Problems with Unsupervised Segmentation Evaluation Based on Global Score and a Possible Remedy

Böck, Sebastian; Immitzer, Markus; Atzberger, Clement

doi:10.3390/rs9080769

Cited by 35 publications

(36 citation statements)

References 34 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A multiresolution local variance strategy has inherent instability and depends on the spatial resolution of the imagery and the a priori knowledge. Segmentation evaluation metrics, such as a modification of the Global Score, should be tested with this method to make the segmentation reproducible and less subjective [60]. Third, it is well known that using multi-source data can improve crop classification accuracy, as different information can capture crop characteristics from alternative perspectives.…”

Section: Discussionmentioning

confidence: 99%

In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest

Song

Zhou

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

Producing accurate crop maps during the current growing season is essential for effective agricultural monitoring. Substantial efforts have been made to study regional crop distribution from year to year, but less attention is paid to the dynamics of composition and spatial extent of crops within a season. Understanding how crops are distributed at the early developing stages allows for the timely adjustment of crop planting structure as well as agricultural decision making and management. To address this knowledge gap, this study presents an approach integrating object-based image analysis with random forest (RF) for mapping in-season crop types based on multi-temporal GaoFen satellite data with a spatial resolution of 16 meters. A multiresolution local variance strategy was used to create crop objects, and then object-based spectral/textural features and vegetation indices were extracted from those objects. The RF classifier was employed to identify different crop types at four crop growth seasons by integrating available features. The crop classification performance of different seasons was assessed by calculating F-score values. Results show that crop maps derived using seasonal features achieved an overall accuracy of more than 87%. Compared to the use of spectral features, a feature combination of in-season textures and multi-temporal spectral and vegetation indices performs best when classifying crop types. Spectral and temporal information is more important than texture features for crop mapping. However, texture can be essential information when there is insufficient spectral and temporal information (e.g., crop identification in the early spring). These results indicate that an object-based image analysis combined with random forest has considerable potential for in-season crop mapping using high spatial resolution imagery.

show abstract

Section: Discussionmentioning

confidence: 99%

In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest

Song

Zhou

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Recent research revealed that the overall goodness measure resulting from this USPO approach is highly dependent on the range of parameter considered during the optimization procedure 26 . Therefore, we performed some empirical tests to find parameters generating clearly over-segmented and under-segmented results.…”

Section: Segmentation and Unsupervised Segmentation Parameter Optimizmentioning

confidence: 99%

A local segmentation parameter optimization approach for mapping heterogeneous urban environments using VHR imagery

Grippa

Georganos

Vanhuysse

et al. 2017

Remote Sensing Technologies and Applications in Urban Environments II

View full text Add to dashboard Cite

Mapping large heterogeneous urban areas using object-based image analysis (OBIA) remains challenging, especially with respect to the segmentation process. This could be explained both by the complex arrangement of heterogeneous land-cover classes and by the high diversity of urban patterns which can be encountered throughout the scene. In this context, using a single segmentation parameter to obtain satisfying segmentation results for the whole scene can be impossible. Nonetheless, it is possible to subdivide the whole city into smaller local zones, rather homogeneous according to their urban pattern. These zones can then be used to optimize the segmentation parameter locally, instead of using the whole image or a single representative spatial subset. This paper assesses the contribution of a local approach for the optimization of segmentation parameter compared to a global approach. Ouagadougou, located in sub-Saharan Africa, is used as case studies. First, the whole scene is segmented using a single globally optimized segmentation parameter. Second, the city is subdivided into 283 local zones, homogeneous in terms of building size and building density. Each local zone is then segmented using a locally optimized segmentation parameter. Unsupervised segmentation parameter optimization (USPO), relying on an optimization function which tends to maximize both intra-object homogeneity and inter-object heterogeneity, is used to select the segmentation parameter automatically for both approaches. Finally, a land-use/land-cover classification is performed using the Random Forest (RF) classifier. The results reveal that the local approach outperforms the global one, especially by limiting confusions between buildings and their bare-soil neighbors.

show abstract

“…However, due to the normalization procedure, the values of GS and consequently, its optimum value, are sensitive to the range of candidate segmentations, as pointed out by Böck et al [31]. When the normalization of MI and WV is computed using the value of the finest and coarsest segmentations as minima and maxima (i.e., 0 and 1), a shift in these scales may also cause a shift in the optimum GS value.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, for adequate results to be produced, the selection of an appropriate range of candidate segmentations might require substantial testing time to be found and moreover, still fall under the curse of subjectivity. In response, Böck et al [31] proposed to do the normalization using fixed minimum and maximum threshold values of MI and WV. In such manner, the optimal value identified by the GS would be the same regardless of the candidate segmentations considered.…”

Section: Introductionmentioning

confidence: 99%

“…In such manner, the optimal value identified by the GS would be the same regardless of the candidate segmentations considered. Their selected ranges corresponded to the extreme values of the MI/WV metrics, and although Böck et al [31] demonstrated that this approach resulted in the GS score remaining stable (i.e., always identifying the same segmentation as "optimal"), it is still unknown if the suggested solution provides segmentation results of adequate quality as they did not evaluate their results with segmentation or classification metrics . In this paper, we demonstrate the limitations of the fixed threshold (FT) approach, both in a theoretical and applied manner, and propose an alternative scheme that focuses on selecting appropriate ranges for the segmentation parameters prior to the normalization rather than employing absolute values a priori.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Normalization in Unsupervised Segmentation Parameter Optimization: A Solution Based on Local Regression Trend Analysis

et al. 2018

View full text Add to dashboard Cite

In object-based image analysis (OBIA), the appropriate parametrization of segmentation algorithms is crucial for obtaining satisfactory image classification results. One of the ways this can be done is by unsupervised segmentation parameter optimization (USPO). A popular USPO method does this through the optimization of a "global score" (GS), which minimizes intrasegment heterogeneity and maximizes intersegment heterogeneity. However, the calculated GS values are sensitive to the minimum and maximum ranges of the candidate segmentations. Previous research proposed the use of fixed minimum/maximum threshold values for the intrasegment/intersegment heterogeneity measures to deal with the sensitivity of user-defined ranges, but the performance of this approach has not been investigated in detail. In the context of a remote sensing very-high-resolution urban application, we show the limitations of the fixed threshold approach, both in a theoretical and applied manner, and instead propose a novel solution to identify the range of candidate segmentations using local regression trend analysis. We found that the proposed approach showed significant improvements over the use of fixed minimum/maximum values, is less subjective than user-defined threshold values and, thus, can be of merit for a fully automated procedure and big data applications.

show abstract

On the Objectivity of the Objective Function—Problems with Unsupervised Segmentation Evaluation Based on Global Score and a Possible Remedy

Cited by 35 publications

References 34 publications

In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest

In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest

A local segmentation parameter optimization approach for mapping heterogeneous urban environments using VHR imagery

Normalization in Unsupervised Segmentation Parameter Optimization: A Solution Based on Local Regression Trend Analysis

Contact Info

Product

Resources

About