Application of oblique photogrammetry technique in geological hazard identification and decision management

With the continuous development of the oblique photography technique, it has been used more and more widely in the field of geological disasters. It can quickly obtain the three-dimensional(3D) real scene model of dangerous mountainous areas under the premise of ensuring the safety of personnel while restoring the real geographic information as much as possible. However, geological disaster areas are often accompanied by many adverse factors such as cliffs and dense vegetation. Based on this, the paper introduced the flight line design of oblique photogrammetry, analyzed the multi-platform data fusion processing, studied the multi-period data dynamic evaluation technology and proposed the application methods of data acquisition, early warning, disaster assessment and decision management suitable for geological disaster identification through the analysis of actual cases, which will help geologists to plan and control geological work more scientifically and rationally, improve work efficiency and reduce the potential personnel safety hazards in the process of geological survey, to offer technical support to the application of oblique photogrammetry in geological disaster identification and decision making and provide the scientific basis for personal and property safety protection and later-stage geological disaster management in disaster areas.

Broad Federated Meta-Learning of Damaged Objects in Aerial Videos

We advanced an emerging federated learning technology in city intelligentization for tackling a real challenge-to learn damaged objects in aerial videos.Ameta-learning system was integrated with the fuzzy broad learning system to further develop the theory of federated learning.Both the mixed picture set of aerial video segmentation and the 3D-reconstructed mixed-reality data were employed in the performance of the broad federated meta-learning system.The study results indicated that the object classification accuracy is up to 90%and the average time cost in damage detection is only 0.277 s.Consequently,the broad federated meta-learning system is efficient and effective in detecting damaged objects in aerial videos.

3D Model Construction and Ecological Environment Investigation on a Regional Scale Using UAV Remote Sensing

The acquisition of digital regional-scale information and ecological environmental data has high requirements for structural texture,spatial res-olution,and multiple parameter categories,which is challenging to achieve using satellite remote sensing.Considering the convenient,facilitative,and flexible characteristics of UAV(unmanned air vehicle)remote sensing tech-nology,this study selects a campus as a typical research area and uses the Pegasus D2000 equipped with a D-MSPC2000 multi-spectral camera and a CAM3000 aerial camera to acquire oblique images and multi-spectral data.Using professional software,including Context Capture,ENVI,and ArcGIS,a 3D(three-dimensional)campus model,a digital orthophoto map,and multi-spectral remote sensing map drawing are realized,and the geometric accuracy of typical feature selection is evaluated.Based on a quantitative remote sensing model,the campus ecological environment assessment is performed from the perspectives of vegetation and water body.The results presented in this study could be of great significance to the scientific management and sustainable development of regional natural resources.

Automatic identifcation of building structure types using unmanned aerial vehicle oblique images and deep learning considering facade prior knowledge

Building structural type information is the foundation for seismic risk assessment and management since it reflects the behavior of buildings under seismic load.However,in earthquake-prone regions,most of this information is out-of-date or nonexistent.This paper proposes a deep learning-based method for automatically identifying building structural types from unmanned aerial vehicle(UAV)oblique images.The method consists of four steps:(1)collect facades of buildings with different structural types by web crawler technology as a sample set;(2)construct a convolutional neural network with a facade prior knowledge attention branch and train the model using the sample set;(3)extract building facades from UAV oblique images based on the georeferencing results of feature points as the test set;(4)identify building structural types by inputting the test set into the trained model.Three cases have been selected to verify the feasibility and applicability of the method.The average recall rate of 85%and the average F1 score of 83%have been achieved in areas with regular building distribution.This method integrates multidisciplinary knowledge to provide a solution for rapid collection of building vulnerability information,and expands the role of oblique photography data in urban management and disaster prevention planning.

Geomorphological monitoring of a highly dynamic estuary using oblique aerial photographs

Bad weather in many countries limits the use of optical satellite imageries in spatial and temporal monitoring of the environment.In this paper,a series of lowaltitude oblique aerial photos taken on daily,weekly and monthly intervals were used to monitor the geomorphological changes in the upper part of the Mersey Estuary,northwestern England.This low-altitude aerial photo methodology reveals itself to be a satisfying compromise between cost,accuracy and difficulty of implementation.It offered a large amount of information on a spatial and temporal scale aiding in the understanding of channel mobility.This was an important consideration in the sitting and installation of new bridge pier foundations.This series of oblique aerial photos was used in a dynamic model to determine the migration of the ebb channel and was effective in identifying the main route of flow.Few uncertainties were encountered and the level of accuracy achieved in resolving these uncertainties in the images was in the range from 40 cm to a maximum of 1.7 m.This was compared with historical navigation charts and showed good correlation.Further applications are required to improve the quality of the data output from these images and the development of the technique.