A Method for Electric Vehicle Charging Port Recognition in Complex Environments based on Wavelet Enhancement and Improved Canny Algorithm
Chunya Sun, Shiao Yin, Yanqiu Xiao, Guangzhen Cui, Lei Yao, Jiangtao Ji- Electrical and Electronic Engineering
- Electronic, Optical and Magnetic Materials
Background:
The current method has low detection accuracy for electric vehicle charging ports in complex environments.
background:
The current method has low detection accuracy for electric vehicle charging ports in complex environments.
Objective:
This paper proposes a method for electric vehicle charging port recognition based on wavelet enhancement and an improved canny algorithm.
objective:
This paper proposes a method for electric vehicle charging port recognition based on wavelet enhancement and improved canny algorithm.
Methods:
Firstly, a preprocessing assessment model is proposed to determine whether preprocessing enhancement should be applied. Subsequently, we perform a stretch transformation on the S channel in the HSI color space and apply a discrete wavelet transform to the I channel to restore the brightness and detail features of the target objects in the image. Specifically, in this paper, adaptive median filtering and multi-scale Retinex algorithm are utilized on different frequency components respectively. Finally, the features and parameters of the charging port are detected and extracted through the maximum inter-class variance method, morphological processing, the improved Canny algorithm, and Hough transform fitting.
Results:
This paper conducts comparative experiments on preprocessing enhancement of charging port images in different environments and features detection of charging ports. The hole feature parameters detected by this method are consistent with the actual situation.
Conclusion:
The experiment proves that the method proposed in this paper can meet the requirements of precise identification of charging ports in complex environments.