Research Progresses and Trends of Power Line Extraction based on Machine Learning

Zou, Kuansheng; Jiang, Zhenbang; Zhou, Qian

doi:10.1109/isceic53685.2021.00051

Cited by 5 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Initial learning rate and input image tensor are (640, 640, 3). In preparation, an Adam optimizer with a cosine hard learning rate is used [6]. To avoid too much error in the first demonstration of data preparation, the center of the model is fixed for the first 50 cycles and the prominent extraction plane is removed without being touched.…”

Section: Test Settingmentioning

confidence: 99%

“…Once any security issues must be settled physically, reaction time will be limited [4]. Result of this are, brilliantly assessment innovation [5][6][7][8] was made by utilizing UAV airborne photography of transmission lines for review, which can spare a part of time and cash whereas moreover having a tall location proficiency when compared to fake methods RCNN [9]. GPU computing control is growing in this enormous information period, and profound learning is continuously appearing to be valuable in numerous computer visioned apps, especially target location employments.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Object Detection in Electricity Cables With Yolo-X Algorithm

2023

IRJMETS

View full text Add to dashboard Cite

Since of the incredible differences of laying and the complicated, changing environment, outsider things can effortlessly connect themselves to transmission line passages. In the event that these outside things are not found and expelled instantly, they can have a serious affect on the capacity of transmission lines to run safely. We offer an upgraded YOLOX approach for identifying outside things in transmission lines in reaction to the issue of destitute precision of remote protest recognizable proof in transmission line picture review.

show abstract

Section: Test Settingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Object Detection in Electricity Cables With Yolo-X Algorithm

2023

IRJMETS

View full text Add to dashboard Cite

show abstract

“…Processes for manual operation and maintenance are also very costly, time-consuming, and challenging to finish on schedule. As a result, by using UAV aerial photography of transmission lines for inspection, intelligent inspection technology [5][6][7][8] was developed, which can save a lot of time and resources while also having a high detection efficiency when compared to artificial techniques. To recognize aerial data, nevertheless, still requires manual judgment.…”

Section: Introductionmentioning

confidence: 99%

Improved YOLOX Foreign Object Detection Algorithm for Transmission Lines

Guo

Chen

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

It is quite simple for foreign objects to attach themselves to transmission line corridors because of the wide variety of laying and the complex, changing environment. If these foreign objects are not found and removed in a timely manner, they can have a significant impact on the transmission lines’ ability to operate safely. Due to the problem of poor accuracy of foreign object identification in transmission line image inspection, we provide an improved YOLOX technique for detection of foreign objects in transmission lines. The method improves the YOLOX target detection network by first using Atrous Spatial Pyramid Pooling to increase sensitivity to foreign objects of different scales, then by embedding Convolutional Block Attention Module to increase model recognition accuracy, and finally by using GIoU loss to further optimize. The testing findings show that the enhanced YOLOX network has a mAP improvement of around 4.24% over the baseline YOLOX network. The target detection SSD, Faster R-CNN, YOLOv5, and YOLOV7 networks have improved less than this. The effectiveness and superiority of the algorithm are proven.

show abstract