A Deep Learning Approach on Building Detection from Unmanned Aerial Vehicle-Based Images in Riverbank Monitoring

Abstract

Buildings along riverbanks are likely to be affected by rising water levels, therefore the acquisition of accurate building information has great importance not only for riverbank environmental protection but also for dealing with emergency cases like flooding. UAV-based photographs are flexible and cloud-free compared to satellite images and can provide very high-resolution images up to centimeter level, while there exist great challenges in quickly and accurately detecting and extracting building from UAV images because there are usually too many details and distortions on UAV images. In this paper, a deep learning (DL)-based approach is proposed for more accurately extracting building information, in which the network architecture, SegNet, is used in the semantic segmentation after the network training on a completely labeled UAV image dataset covering multi-dimension urban settlement appearances along a riverbank area in Chongqing. The experiment results show that an excellent performance has been obtained in the detection of buildings from untrained locations with an average overall accuracy more than 90%. To verify the generality and advantage of the proposed method, the procedure is further evaluated by training and testing with another two open standard datasets which have a variety of building patterns and styles, and the final overall accuracies of building extraction are more than 93% and 95%, respectively.

A Deep Learning Model for Automatic Plastic Mapping Using Unmanned Aerial Vehicle (UAV) Data

“…The FCN is an end-to-end model that maintains a two-dimensional structure of a feature map and uses contextual and location information to predict class labels, reducing the computational cost significantly. Semantic segmentation models based on FCN can be divided into four categories: encoder-decoder structure [23,24], dilated convolutions [34], and spatial pyramid pooling [35], which are described below.…”

Quantifying Below-Water Fluvial Geomorphic Change: The Implications of Refraction Correction, Water Surface Elevations, and Spatially Variable Error

“…As such, it includes a broad range of algorithms, encompassing everything from simple linear regressions to deep learning-based neural networks [52]. The application of AI/ML for geomorphic error thresholding purposes is novel, with existing studies within freshwater settings applying it predominantly for classification of land cover types from image-derived parameters (e.g., [53][54][55][56]) or for the identification of other specific features of interest such as buildings (e.g., [57]) and invasive species (e.g., [58]). As such, our ultimate aim is to create the first high resolution, spatially continuous SfM-derived topographic change models in submerged fluvial environments constrained by spatially variable error estimates.…”

Unsupervised Human Detection with an Embedded Vision System on a Fully Autonomous UAV for Search and Rescue Operations

“…Moreover, the adaption of camera parameters, as well as motion parameters estimation based on the integration of video measurements and data obtained by UAVs, have always to be seriously taken into account [32]. The relentless motivation for image classification tasks based on deep learning and aerial images captured by UAVs has led to an abundance of research including vehicles [24,33,34], aerial vehicles [35,36,37,38,39], roads [40], buildings [41,42], cracks [43], birds [44], cattle [45], and wilt [46] detection. Another remarkable approach for object detection in very high-resolution aerial images has been proposed in [47].…”