Photovoltaic panel extraction from very high-resolution aerial imagery using region–line primitive association analysis and template matching

Automated methods to extract buildings from very high resolution (VHR) remote sensing data have many applications in a wide range of fields. Many convolutional neural network (CNN) based methods have been proposed and have achieved significant advances in the building extraction task. In order to refine predictions, a lot of recent approaches fuse features from earlier layers of CNNs to introduce abundant spatial information, which is known as skip connection. However, this strategy of reusing earlier features directly without processing could reduce the performance of the network. To address this problem, we propose a novel fully convolutional network (FCN) that adopts attention based re-weighting to extract buildings from aerial imagery. Specifically, we consider the semantic gap between features from different stages and leverage the attention mechanism to bridge the gap prior to the fusion of features. The inferred attention weights along spatial and channel-wise dimensions make the low level feature maps adaptive to high level feature maps in a target-oriented manner. Experimental results on three publicly available aerial imagery datasets show that the proposed model (RFA-UNet) achieves comparable and improved performance compared to other state-of-the-art models for building extraction.

Download Full-text

Integration of Lidar Data in Topographical Feature Extraction from Very High-Resolution Aerial Imagery

Lecture Notes in Civil Engineering - Proceedings of UASG 2019 ◽

10.1007/978-3-030-37393-1_5 ◽

2020 ◽

pp. 39-44

Author(s):

Kuldeep Chaurasia

Keyword(s):

Feature Extraction ◽

High Resolution ◽

Aerial Imagery ◽

Lidar Data ◽

Topographical Feature ◽

Very High

Download Full-text

Automatic vehicle detection based on automatic histogram-based fuzzy C-means algorithm and perceptual grouping using very high-resolution aerial imagery and road vector data

Journal of Applied Remote Sensing ◽

10.1117/1.jrs.10.015011 ◽

2016 ◽

Vol 10 (1) ◽

pp. 015011 ◽

Cited By ~ 6

Author(s):

Saman Ghaffarian ◽

Ilgin Gökasar

Keyword(s):

High Resolution ◽

Perceptual Grouping ◽

Vehicle Detection ◽

Aerial Imagery ◽

Vector Data ◽

Fuzzy C Means ◽

Very High ◽

Fuzzy C Means Algorithm

Download Full-text

Mapping the Individual Trees in Urban Orchards by Incorporating Volunteered Geographic Information and Very High Resolution Optical Remotely Sensed Data: A Template Matching-Based Approach

Remote Sensing ◽

10.3390/rs10071134 ◽

2018 ◽

Vol 10 (7) ◽

pp. 1134 ◽

Cited By ~ 5

Author(s):

Hossein Vahidi ◽

Brian Klinkenberg ◽

Brian Johnson ◽

L. Moskal ◽

Wanglin Yan

Keyword(s):

High Resolution ◽

Template Matching ◽

False Negative ◽

Volunteered Geographic Information ◽

Remotely Sensed ◽

Geographic Information ◽

Remotely Sensed Data ◽

Individual Tree ◽

Training Samples ◽

Very High

This paper presents a collective sensing approach that integrates imperfect Volunteered Geographic Information (VGI) obtained through Citizen Science (CS) tree mapping projects with very high resolution (VHR) optical remotely sensed data for low-cost, fine-scale, and accurate mapping of trees in urban orchards. To this end, an individual tree crown (ITC) detection technique utilizing template matching (TM) was developed for extracting urban orchard trees from VHR optical imagery. To provide the training samples for the TM algorithm, remotely sensed VGI about trees including the crowdsourced data about ITC locations and their crown diameters was adopted in this study. A data quality assessment of the proposed approach in the study area demonstrated that the detected trees had a very high degree of completeness (92.7%), a high thematic accuracy (false discovery rate (FDR) = 0.090, false negative rate (FNR) = 0.073, and F1 score (F1) = 0.918), and a fair positional accuracy (root mean square error(RMSE) = 1.02 m). Overall, the proposed approach based on the crowdsourced training samples generally demonstrated a promising ITC detection performance in our pilot project.

Download Full-text