Vehicular Multi-Camera Sensor System for Automated Visual Inspection of Electric Power Distribution Equipment

Park, Jinsun; Shin, Ukcheol; Shim, Gyumin; Joo, Kyungdon; Rameau, François; Kim, Junhyeok; Choi, Dong‐Geol; Kweon, In So

doi:10.1109/iros40897.2019.8968085

Cited by 4 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the help of SLAM, when a robot enters an uncertain or even unknown environment, it can make use of the structured environment information to determine its location on the map; it can also reconstruct its surroundings by only relying on its own sensors. Thus, the robot can move and complete specific tasks in a prior unknown and unstructured environment autonomously [ 4 , 5 ].…”

Section: Introductionmentioning

confidence: 99%

Semantic-Structure-Aware Multi-Level Information Fusion for Robust Global Orientation Optimization of Autonomous Mobile Robots

Xiang

Dian

Zhao

et al. 2023

Sensors

View full text Add to dashboard Cite

Multi-camera-based simultaneous localization and mapping (SLAM) has been widely applied in various mobile robots under uncertain or unknown environments to accomplish tasks autonomously. However, the conventional purely data-driven feature extraction methods cannot utilize the rich semantic information in the environment, which leads to the performance of the SLAM system being susceptible to various interferences. In this work, we present a semantic-aware multi-level information fusion scheme for robust global orientation estimation. Specifically, a visual semantic perception system based on the synthesized surround view image is proposed for the multi-eye surround vision system widely used in mobile robots, which is used to obtain the visual semantic information required for SLAM tasks. The original multi-eye image was first transformed to the synthesized surround view image, and the passable space was extracted with the help of the semantic segmentation network model as a mask for feature extraction; moreover, the hybrid edge information was extracted to effectively eliminate the distorted edges by further using the distortion characteristics of the reverse perspective projection process. Then, the hybrid semantic information was used for robust global orientation estimation; thus, better localization performance was obtained. The experiments on an intelligent vehicle, which was used for automated valet parking both in indoor and outdoor scenes, showed that the proposed hybrid multi-level information fusion method achieved at least a 10-percent improvement in comparison with other edge segmentation methods, the average orientation estimation error being between 1 and 2 degrees, much smaller than other methods, and the trajectory drift value of the proposed method was much smaller than that of other methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Semantic-Structure-Aware Multi-Level Information Fusion for Robust Global Orientation Optimization of Autonomous Mobile Robots

Xiang

Dian

Zhao

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…With the rapid development of modern industry, electrical control equipment plays an increasingly important role in various fields [1][2][3]. However, it may malfunction after longtime operation, leading to decreased equipment performance or even shutdown [4][5][6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

Electrical Control Equipment Patrol Inspection Method Based on High Quality Image Recognition Technology

Wang¹

2023

View full text Add to dashboard Cite

In order to ensure the safe, stable, and efficient operation of electrical control equipment, the patrol inspection and maintenance are especially important. Research on electrical control equipment patrol inspection method based on high quality image recognition technology is of great significance, because the method replaces traditional manual patrol inspection to some extent and reduces labor costs. The existing methods based on lowillumination image recognition technology meet the patrol inspection requirements in lowillumination environment to a certain extent, but they still have certain limitations. Therefore, this research aimed to study the electrical control equipment patrol inspection method based on high quality image recognition technology. Electrical control equipment patrol inspection images were enhanced based on Deep Curve Estimation Network (DCEN) in order to improve the visibility of equipment anomaly features, which helped reduce the misjudgment and misdetection risks during the patrol inspection process. The patrol inspection image set was reconstructed in super resolution, and was combined with clear images to construct a new image set, which improved the patrol inspection efficiency. The electrical control equipment detection process based on YOLO V3 was elaborated. The experimental results verified that the proposed method and constructed model in this study were effective.

show abstract

Hierarchical lossless coding of light fields with improved random access

Santos

Thomaz

Assunção

et al. 2022

Signal Processing: Image Communication

View full text Add to dashboard Cite

Vehicular Multi-Camera Sensor System for Automated Visual Inspection of Electric Power Distribution Equipment

Cited by 4 publications

References 21 publications

Semantic-Structure-Aware Multi-Level Information Fusion for Robust Global Orientation Optimization of Autonomous Mobile Robots

Semantic-Structure-Aware Multi-Level Information Fusion for Robust Global Orientation Optimization of Autonomous Mobile Robots

Electrical Control Equipment Patrol Inspection Method Based on High Quality Image Recognition Technology

Hierarchical lossless coding of light fields with improved random access

Contact Info

Product

Resources

About