Comparison of Pixel-Based and Object-Based Classification Using Parameters and Non-Parameters Approach For the Pattern Consistency of Multi Scale Landcover

Abstract

ABSTRACT:Information extraction from remote sensing data especially land cover can be obtained by digital classification. In practical some people are more comfortable using visual interpretation to retrieve land cover information. However, it is highly influenced by subjectivity and knowledge of interpreter, also takes time in the process. Digital classification can be done in several ways, depend on the defined mapping approach and assumptions on data distribution. The study compared several classifiers method for some data type at the same location. The data used Landsat 8 satellite imagery, SPOT 6 and Orthophotos. In practical, the data used to produce land cover map in 1:50,000 map scale for Landsat, 1:25,000 map scale for SPOT and 1:5,000 map scale for Orthophotos, but using visual interpretation to retrieve information. Maximum likelihood Classifiers (MLC) which use pixel-based and parameters approach applied to such data, and also Artificial Neural Network classifiers which use pixel-based and non-parameters approach applied too. Moreover, this study applied object-based classifiers to the data. The classification system implemented is land cover classification on Indonesia topographic map. The classification applied to data source, which is expected to recognize the pattern and to assess consistency of the land cover map produced by each data. Furthermore, the study analyse benefits and limitations the use of methods.

Assessing land cover change in Namibia's Kavango East region: a multi-date object approach

“…Object-based image analysis uses spectral and spatial information to assign pixels into objects based on characteristics such as tone, size, shape, texture, patterns and the association between objects to assign a class. Object-based image analysis has been reported to be more accurate compared to pixel-based approaches (Esetlili et al, 2018;Jawak et al, 2018;Juniati and Arrofigoh, 2017). However, this depends on various factors such as the nature of the landscape, classification scheme, satellite sensor type and algorithms used to perform the actual analysis.…”

Mapping Urban Trees Within Cadastral Parcels Using an Object-Based Convolutional Neural Network

“…There are two different approaches for image analysis namely pixel-wise and object-based (Castillejo-González et al, 2009;Lei et al, 2016;Lu, Weng, 2007). Pixel-wise image analysis method classifies each individual pixel to their most probable thematic class (Castillejo-González et al, 2009;Juniati, Arrofiqoh, 2017;Li et al, 2014;Weih, Riggan, 2010). Whereas, object-based image analysis first segments the image and classifies those individual segments to most appropriate thematic classes considering on spatial, spectral, geometrical and textural attributes (Blaschke, 2010;Weih, Riggan, 2010).…”

Farm Area Segmentation in Satellite Images Using DeepLabv3+ Neural Networks

“…In many cases software and computational tools such as ERDAS and Khoros 2.2 were used [17]. eCognition and ArcGIS softwares are recent examples in this case [8,21]; Traditional hand-crafted feature extraction and discrimination techniques for object classification in remote sensing was reviewed in [22]. When using low resolution images such as Landsat 8, appropriate choice of training samples, segmentation parameters and modelling strategy is important.…”

“…When using low resolution images such as Landsat 8, appropriate choice of training samples, segmentation parameters and modelling strategy is important. That is a challenge in using software-based strategies and limit their accuracy [21]. An example in this case is selection of a suitable segmentation scale to avoid over and under segmentation in Object Based Image Analysis OBIA.…”

“…An example in this case is selection of a suitable segmentation scale to avoid over and under segmentation in Object Based Image Analysis OBIA. Although there are several reports of superior performance on different landscapes, due to the segmentation scale issue and lower resolution, OBIA is not very ideal for Landsat data [21].…”