Detection and Enumeration of Trees using Cartosat2 High Resolution Satellite Imagery

A modular CNN-based building detector for remote sensing images

“…In the last few decades, the image sensors attached to satellites have evolved in a way that nowadays allows the capture of high-resolution multi-spectral satellite images, [1,2,3,4]. As a result, land cover classification became a widely-studied field providing also solutions on the detection and classification of buildings and other struc- [5,6] a) sociology, for the monitoring the dynamic processes that occur in a complex urban environment, b) citizen welfare, for city planning, c) city protection, for the analysis and assessment of the impact of fire, flood and natural disasters in an urban environment, d) illegal construction for detecting illegal building activity and e) navigation, for the development and constant update of accurate urban maps that can be employed for navigation purposes.…”

“…Applying the cosine-based dissimilarity measure to a pair of vectors x i and x j is equivalent to transforming the feature vectors to their Euler representation z i and z j , where z i = iαπx i and subsequently employ the l 2 -norm function. With the use of a few trigonometric identities and the substitution θ i = απx i , the proof is presented in Eq (4)…”

Framework for Tree Crown Delineation from Panchromatic Images

“…Remaining parameters, such as height and size of tree crown can also be easily delineated. While most of the existing studies only concentrated on tree crown delineation, and existing authors used regular algorithms [11,12] in image processing. In the same time period, grey scale analysis was applied on high resolution satellite imagery and to estimate tree crown area and the template matching techniques were introduced for extraction of tree crown delineation of the given model.…”