scholarly journals Robust detection of small and dense objects in images from autonomous aerial vehicles

2021 ◽  
Author(s):  
Joo Chan Lee ◽  
JeongYeop Yoo ◽  
Yongwoo Kim ◽  
SungTae Moon ◽  
Jong Hwan Ko
Author(s):  
Christopher M. Aasted ◽  
Sunwook Lim ◽  
Rahmat A. Shoureshi

In order to optimize the use of fault tolerant controllers for unmanned or autonomous aerial vehicles, a health diagnostics system is being developed. To autonomously determine the effect of damage on global vehicle health, a feature-based neural-symbolic network is utilized to infer vehicle health using historical data. Our current system is able to accurately characterize the extent of vehicle damage with 99.2% accuracy when tested on prior incident data. Based on the results of this work, neural-symbolic networks appear to be a useful tool for diagnosis of global vehicle health based on features of subsystem diagnostic information.


2020 ◽  
Vol 10 (17) ◽  
pp. 5948 ◽  
Author(s):  
Alberto Fernández ◽  
Rubén Usamentiaga ◽  
Pedro de Arquer ◽  
Miguel Ángel Fernández ◽  
D. Fernández ◽  
...  

The efficiency and profitability of photovoltaic (PV) plants are highly controlled by their operation and maintenance (O&M) procedures. Today, the effective diagnosis of any possible fault of PV plants remains a technical and economic challenge, especially when dealing with large-scale PV plants. Currently, PV plant monitoring is carried out by either electrical performance measurements or image processing. The first approach presents limited fault detection ability, it is costly and time-consuming, and it is incapable of fast identification of the physical location of the fault. In the second approach, Infrared Thermography (IRT) imaging has been used for the characterization of PV module failures, but their setup and processing are rather complex and an experienced technician is required. The use of Unmanned Aerial Vehicles (UAVs) for IRT imaging of PV plants for health status monitoring of PV modules has been identified as a cost-effective approach that offers 10–-15 fold lower inspection times than conventional techniques. However, previous works have not performed a comprehensive approach in the context of automated UAV inspection using IRT. This work provides a fully automated approach for the: (a) detection, (b) classification, and (c) geopositioning of the thermal defects in the PV modules. The system has been tested on a real PV plant in Spain. The obtained results indicate that an autonomous solution can be implemented for a full characterization of the thermal defects.


Sign in / Sign up

Export Citation Format

Share Document