ABSTRACT
The quality correction of transmission line images is of great significance for power system monitoring and maintenance. The purpose of this study is to propose an automatic quality correction algorithm based on saliency model to improve the clarity and visibility of transmission line images. We combine modern computer vision technology with saliency analysis, and propose an innovative method, which can automatically detect and correct the quality problems in transmission line images. In this paper, an automatic quality correction algorithm for transmission line images based on the salient deep features of pseudo-reference images is proposed. The algorithm mainly consists of three parts, namely, pseudo reference image generation network, deep feature extraction network and quality regression network. The experimental results show that the quality prediction of this algorithm accords with human quality perception, and the prediction score is in good agreement with human subjective quality evaluation. The algorithm can automatically detect the salient regions in the image and adjust the correction parameters according to the characteristics of these regions. This adaptability enables our algorithm to process transmission line images under different lighting conditions, thus improving its universality. The successful application of this algorithm will hopefully improve the operation and maintenance of the power system, thus achieving a more sustainable power supply.
- Chongyi Li, Jun Guo, Chunle Guo, Runmin Cong, and Jiachang Gong. 2017. A hybrid method for underwater image correction. Pattern Recognition Letters 94, (July 2017), 62–67. DOI: https://doi.org/10.1016/j.patrec.2017.05.023.Google ScholarDigital Library
- Mohammad Kazem Moghimi and Farahnaz Mohanna. 2020. Real-time underwater image resolution enhancement using super-resolution with deep convolutional neural networks. Journal of Real-time Image Processing 18, 5 (October 2020), 1653–1667. DOI: https://doi.org/10.1007/s11554-020-01024-4.Google ScholarDigital Library
- Qi-Chong Tian and Laurent D. Cohen. 2018. A variational-based fusion model for non-uniform illumination image enhancement via contrast optimization and color correction. Signal Processing 153, (December 2018), 210–220. DOI: https://doi.org/10.1016/j.sigpro.2018.07.022.Google ScholarCross Ref
- Wan-Chin Kim, Yong-Shik Park, Sung-Dae Kim, and Jiseok Kim. 2017. Compensation of image noise induced by difference in optical characteristics of array-LED chips of LED print head. Science China Technological Sciences 60, (2017), 1819-1830.Google ScholarCross Ref
- Yongqing Guo, Wei Chen, and Shiwei Jing. 2020. An image compressed sensing algorithm based on adaptive nonlinear network*. Chinese Physics B 29, 5 (May 2020), 054203. DOI: https://doi.org/10.1088/1674-1056/ab7b4e.Google ScholarCross Ref
- Chao Chen, Liyan Wang, Zili Zhang, Long-Wen Chang, Huixin Chen, and Jianyu Chen. 2021. Construction and application of quality evaluation index system for remote-sensing image fusion. Journal of Applied Remote Sensing 16, 01 (August 2021). DOI: https://doi.org/10.1117/1.jrs.16.012006.Google ScholarCross Ref
- Jijun Li, H. Suxia, and Linfa Peng. 2020. Analysis and evaluation of tomographic gamma scanning image reconstruction algorithm. Kerntechnik 85, 6 (June 2020), 452–460. DOI: https://doi.org/10.3139/124.190046.Google ScholarCross Ref
- Ming Yin, Puhong Duan, Wei Liu, and Xiangyu Liang. 2017. A novel infrared and visible image fusion algorithm based on shift-invariant dual-tree complex shearlet transform and sparse representation. Neurocomputing 226, (February 2017), 182–191. DOI: https://doi.org/10.1016/j.neucom.2016.11.051.Google ScholarDigital Library
- Hyeonju Kim, Junho Lee, and Joon Yoon. 2022. A phantom study on usefulness of modifying image parameters to reduce radiation exposure and maintain image quality in chest HRCT. Clinical Imaging 86, (2022), 89-93.Google ScholarCross Ref
- Zhou Fang, Xinrong Wang, Wei Ji, Meng Xu, Yinan Zhang, Yan Li, and Longfei Li. 2021. Geometric Calibration and Image Quality Assessment of High-Resolution Dual-Camera Satellite. Journal of Beijing Institute of Technology 30, 2 (2021), 125-138.Google Scholar
- Peng Li, Piao Zai-Lin, and Jianwei Wang. 2009. Optimal route searching for the design of rural power transmission line based on improved ant colony algorithms. Transactions of the Chinese Society of Agricultural Engineering 25, 11 (January 2009), 232–235. Retrieved from https://www.cabdirect.org/cabdirect/abstract/20103065717Google Scholar
- Macmillan Simfukwe, Bo Peng, and Tianrui Li. 2019. Fusion of measures for image segmentation evaluation. International Journal of Computational Intelligence Systems 12, 1 (January 2019), 379. DOI: https://doi.org/10.2991/ijcis.2019.125905654.Google ScholarCross Ref
Index Terms
- Automatic Quality Correction Algorithm Design for Transmission Line Images Based on the Saliency Model
Recommendations
Saliency integration driven by similar images
Highlights- We propose a saliency integration approach driven by similar images.
- We utilize ...
AbstractThis paper proposes a saliency integration approach via the use of similar images to elevate saliency detection performance. Given the input image, a group of similar images are first retrieved, and meanwhile, the corresponding ...
Adaptive saliency fusion based on quality assessment
A variety of saliency models based on different schemes and methods have been proposed in the recent years, and the performance of these models often vary with images and complement each other. Therefore it is a natural idea whether we can elevate ...
A weighted full-reference image quality assessment based on visual saliency
A full reference image quality assessment based saliency map is proposed.Human visual system is taken account into image quality assessment.The pixels of an image make different contributions in image quality assessment. In full reference image quality ...
Comments