Abstract
High-quality training samples are essential for accurate land cover classification. Due to the difficulties in collecting a large number of training samples, it is of great significance to collect a high-quality sample dataset with a limited sample size but effective sample distribution. In this paper, we proposed an object-oriented sampling approach by segmenting image blocks expanded from systematically distributed seeds (object-oriented sampling approach) and carried out a rigorous comparison of seven sampling strategies, including random sampling, systematic sampling, stratified sampling (stratified sampling with the strata of land cover classes based on classification product, Latin hypercube sampling, and spatial Latin hypercube sampling), object-oriented sampling, and manual sampling, to explore the impact of training sample distribution on the accuracy of land cover classification when the samples are limited. Five study areas from different climate zones were selected along the China–Mongolia border. Our research identified the proposed object-oriented sampling approach as the first-choice sampling strategy in collecting training samples. This approach improved the diversity and completeness of the training sample set. Stratified sampling with strata defined by the combination of different attributes and stratified sampling with the strata of land cover classes had their limitations, and they performed well in specific situations when we have enough prior knowledge or high-accuracy product. Manual sampling was greatly influenced by the experience of interpreters. All these sampling strategies mentioned above outperformed random sampling and systematic sampling in this study. The results indicate that the sampling strategies of training datasets do have great impacts on the land cover classification accuracies when the sample size is limited. This paper will provide guidance for efficient training sample collection to increase classification accuracies.
Highlights
We used seven training sample distribution strategies: random sampling, systematic sampling, stratified sampling, object-oriented sampling, and manual sampling
The performances of stratified sampling with the strata of land cover classes based on classification product were different in each study area
We focused on the spatial distribution of training samples of land cover and proposed an object-oriented sampling approach by segmenting image blocks expanded from systematically distributed seeds
Summary
In supervised land cover classification, training samples, classifiers, and auxiliary data are the main factors that affect classification accuracy [6]. The representativeness of training samples has a significant impact on the supervised land cover classification [12,15,16]. To obtain better classification results with fewer but informative labeled samples, active learning was widely used in land cover classification using remotely sensed images [22,23]. It is of great significance to develop a reasonable distribution method of training samples suitable for multi regions in land cover classification. Two specific objectives include (1) proposing an object-oriented sampling approach by segmenting image blocks expanded from systematically distributed seeds, and (2) in terms of classification accuracy and sample diversity, quantitatively comparing the proposed method with traditional probability sampling, stratified sampling, and manual sampling
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
