Recognition of Transmission Line Related Bird Species Based on Image Feature Extraction and Support Vector Machine

Qiu, Zhibin; Zhu, Xuan; Shi, Dazhai; Kuang, Yanjun

doi:10.1109/ichve49031.2020.9279508

Cited by 9 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some researchers have focused on environmental factors that may lead to component degradation and failure. This has included detection of activities of birds on OHL towers [15], [16], detection of icing [17]- [21], and measurement of vegetation encroachment [22]. Others have addressed the detection of components that have failed or that require immediate maintenance work.…”

Section: B Previous Work On Automated Monitoringmentioning

confidence: 99%

Aerial Image Analysis Using Deep Learning for Electrical Overhead Line Network Asset Management

Odo

McKenna²,

Flynn

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Electricity networks are critical infrastructure, delivering vital energy services. Due to the significant number, variety and distribution of electrical network overhead line assets, energy network operators spend millions annually on inspection and maintenance programmes. Currently, inspection involves acquiring and manually analysing aerial images. This is labour intensive and subjective. Along with costs associated with helicopter or drone operations, data analysis represents a significant financial burden to network operators. We propose an approach to automating assessment of the condition of electrical towers. Importantly, we train machine learning tower classifiers without using condition labels for individual components of interest. Instead, learning is supervised using only condition labels for towers in their entirety. This enables us to use a real-world industry dataset without needing costly additional human labelling of thousands of individual components. Our prototype first detects instances of components in multiple images of each tower, using Mask R-CNN or RetinaNet. It then predicts tower condition ratings using one of two approaches: (i) component instance classifiers trained using class labels transferred from towers to each of their detected component instances, or (ii) multiple instance learning classifiers based on bags of detected instances. Instance or bag class predictions are aggregated to obtain tower condition ratings. Evaluation used a dataset with representative tower images and associated condition ratings covering a range of component types, scenes, environmental conditions, and viewpoints. We report experiments investigating classification of towers based on the condition of their multiple insulator and U-bolt components. Automated visual detection and analysis of U-bolts has not been previously reported. We demonstrate that tower condition classifiers can be trained effectively without labelling the condition of individual components.

show abstract

Section: B Previous Work On Automated Monitoringmentioning

confidence: 99%

Aerial Image Analysis Using Deep Learning for Electrical Overhead Line Network Asset Management

Odo

McKenna²,

Flynn

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Related study is important because it helps understand learners' requirements and learning status more precisely by analyzing their learning behavior and micro-expressions in detail [9][10][11]. Dual stream convolutional networks can efficiently process time series data and precisely identify learner behavior patterns, whereas migration learning can assist systems in fast adapting to new learner groups [12][13][14]. In addition, GCNNs are an effective tool for deciphering and examining learner micro-expressions due to their advantages in processing non-Euclidean data structures.…”

Section: Introductionmentioning

confidence: 99%

Personalized Learning Pathway Generation for Online Education Through Image Recognition

Yan,

Wang,

Wei

et al. 2023

View full text Add to dashboard Cite

The development of online education has driven a profound transformation in the teaching mode of vocational education, with the generation of personalized learning paths as one of the key factors in improving the learning effectiveness of learners. However, current online learning platforms still face a series of challenges in personalized teaching practices. Especially in terms of accurately capturing and understanding learner behavior and emotions, existing systems have not fully met the personalized learning needs of learners. This study aims to explore a novel mechanism for generating personalized learning paths for learners through image recognition technology. Firstly, by combining migration learning and dual stream convolutional networks, this study proposes a recognition method that can adapt to the behavioral characteristics of different groups of learners. Secondly, using graph convolutional neural networks (GCNNs) for deep recognition of learner micro-expressions to accurately capture the learner's emotional state, making the generation of learning paths more detailed and adaptable. This study addresses the shortcomings of existing systems in processing multimodal data integration and real-time feedback dynamic adaptation, and improves the accuracy and practicality of personalized learning path generation for learners. The research results not only promote the progress of personalized learning path generation in online education for learners technically, but also provide learners with a more customized learning experience.

show abstract

Bird Species Identification Based on Images Using Residual Network

Potluri

Vinnakota

Prativada

et al. 2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Recognition of Transmission Line Related Bird Species Based on Image Feature Extraction and Support Vector Machine

Cited by 9 publications

References 12 publications

Aerial Image Analysis Using Deep Learning for Electrical Overhead Line Network Asset Management

Aerial Image Analysis Using Deep Learning for Electrical Overhead Line Network Asset Management

Personalized Learning Pathway Generation for Online Education Through Image Recognition

Bird Species Identification Based on Images Using Residual Network

Contact Info

Product

Resources

About