IMPACT OF SEGMENTATION PARAMETERS ON THE CLASSIFICATION OF VHR IMAGES ACQUIRED BY RPAS
- 1Institute for Advanced Studies - IEAv, São José dos Campos-SP, Brazil
- 2Aeronautics Institute of Technology - ITA, São José dos Campos-SP, Brazil
- 3National Institute for Space Research - INPE, São José dos Campos-SP, Brazil
- 4Federal Institute of Education, Science and Technology of South of Minas Gerais - IFSULDEMINAS, Inconfidentes-MG, Brazil
Keywords: Image Classification, Segmentation Parameters, RPA, Very High Resolution Images
Abstract. RPAs (Remotely Piloted Aircrafts) have been used in many Remote Sensing applications, featuring high-quality imaging sensors. In some situations, the images are interpreted in an automated fashion using object-oriented classification. In this case, the first step is segmentation. However, the setting of segmentation parameters such as scale, shape, and compactness may yield too many different segmentations, thus it is necessary to understand the influence of those parameters on the final output. This paper compares 24 segmentation parameter sets by taking into account classification scores. The results indicate that the segmentation parameters exert influence on both classification accuracy and processing time.