ABSTRACT
There are millions of ammeters working in China and daily manual inspection of their status consumes immense manpower and material resources. Besides, manual inspection is inevitably affected by factors such as the levels of evaluation skills and tiredness. To solve the problem, we propose an ammeter safety status assessment method and construct a software system for the ammeter inspection task, which encapsulates smart detection and evaluation algorithms for ammeter and its parts into an app and website. The use of this system has greatly reduced the workload of ammeter inspection tasks and unify the standards for defect judgment. Meanwhile, raw data and its analysis results are kept in the system and can be reused to improve the system further. The system has been deployed in the electric power system of Hangzhou and creates millions of economic values.
- Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]. 2005.Google ScholarDigital Library
- Felzenszwalb P F, Girshick R B, McAllester D, Object detection with discriminatively trained part-based models[J]. IEEE transactions on pattern analysis and machine intelligence, 2009, 32(9): 1627-1645.Google Scholar
- Girshick R, Donahue J, Darrell T, Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 580-587.Google Scholar
- Uijlings J R R, Van De Sande K E A, Gevers T, Selective search for object recognition[J]. International journal of computer vision, 2013, 104(2): 154-171.Google Scholar
- Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C]//Advances in neural information processing systems. 2012: 1097-1105.Google Scholar
- Suykens J A K, Vandewalle J. Least squares support vector machine classifiers[J]. Neural processing letters, 1999, 9(3): 293-300.Google Scholar
- Girshick R. Fast r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2015: 1440-1448.Google Scholar
- Ren S, He K, Girshick R, Faster r-cnn: Towards real-time object detection with region proposal networks[C]//Advances in neural information processing systems. 2015: 91-99.Google Scholar
- Redmon J, Divvala S, Girshick R, You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788.Google Scholar
- Redmon J, Farhadi A. Yolov3: An incremental improvement[J]. arXiv preprint arXiv:1804.02767, 2018.Google Scholar
- Redmon J, Farhadi A. YOLO9000: better, faster, stronger[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 7263-7271.Google Scholar
- Howard A G, Zhu M, Chen B, Mobilenets: Efficient convolutional neural networks for mobile vision applications[J]. arXiv preprint arXiv:1704.04861, 2017.Google Scholar
Recommendations
Task-directed software inspection
Special issue: Applications of statistics in software engineeringSoftware inspection is recognized as an effective verification technique. Despite this fact, the use of inspection is surprisingly low. This paper describes a new inspection technique, called task-directed inspection (TDI), and a light-weight process, ...
Task-directed software inspection technique: an experiment and case study
CASCON '00: Proceedings of the 2000 conference of the Centre for Advanced Studies on Collaborative researchResearch in software inspection has led to the development of inspection techniques focused on providing structure and guidance to the individual inspector, with the goal of improving effectiveness. This paper defines and investigates a new inspection ...
A Low-Cost and Scalable Personalized Thermal Comfort Estimation System in Indoor Environments
CPHS21: Proceedings of the First International Workshop on Cyber-Physical-Human System Design and ImplementationIn commercial buildings, occupant thermal comfort is a key factor that must be optimized to provide a comfortable and productive work environment. However, current methods largely estimate thermal comfort based on preset models which do not incorporate ...
Comments