Scholarlink

<p>In the field of video surveillance, effective image enhancement is pivotal for extracting valuable information from challenging visual environments. Enhancing images from video surveillance scenes is challenging due to varying lighting conditions ranging from bright daylight to low-light or nighttime settings. Noise, artifacts and distortions in video frames further degrade quality, while real-time processing requirements add complexity. To overcome these issues, this research focuses on developing a specialized neural network tailored for enhancing images captured in video surveillance scenarios. The primary objective is to significantly boost the visual quality of surveillance video frames. To achieve both accuracy and efficiency, Convolutional Neural Network (CNN) based on ResNet-152, is specifically designed for enhancing images in video surveillance settings. The research aims to enhance adaptability to varying lighting conditions, weather patterns and scene complexities. Uniform frame sampling (UFS) ensures simplicity in implementation and computational efficiency by consistently extracting frames at regular intervals. To further enhance the performance of the ResNet-152 CNN, an Adaptive Spiral Flying Sparrow Search Algorithm (ASFSSA) is employed. Experimental outcomes reveal that the proposed system outperforms traditional approaches, achieving impressive metrics like accuracy of 98%, recall of 95%, precision of 95.7%, F1-score of 98%, specificity of 96%, sensitivity of 97.8% and a peak signal-to-noise ratio of 35%. Additionally, the structural similarity index measure, root mean square error and mean average error of the proposed technique are reported at 0.09%, 4% and 3.02% respectively, showcasing improvements over current methods.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Resnet 152 convolutional adaptive spiral flying sparrow search neural network for image enhancement of video surveillance scene

  • 期刊论文

  • 发表日期：

    2025年1月17日

查看全文
  • J. Angel Ida Chellam,
  • P. Malliga,
  • Mathankumar Manoharan,
  • M. Ramkumar

摘要

In the field of video surveillance, effective image enhancement is pivotal for extracting valuable information from challenging visual environments. Enhancing images from video surveillance scenes is challenging due to varying lighting conditions ranging from bright daylight to low-light or nighttime settings. Noise, artifacts and distortions in video frames further degrade quality, while real-time processing requirements add complexity. To overcome these issues, this research focuses on developing a specialized neural network tailored for enhancing images captured in video surveillance scenarios. The primary objective is to significantly boost the visual quality of surveillance video frames. To achieve both accuracy and efficiency, Convolutional Neural Network (CNN) based on ResNet-152, is specifically designed for enhancing images in video surveillance settings. The research aims to enhance adaptability to varying lighting conditions, weather patterns and scene complexities. Uniform frame sampling (UFS) ensures simplicity in implementation and computational efficiency by consistently extracting frames at regular intervals. To further enhance the performance of the ResNet-152 CNN, an Adaptive Spiral Flying Sparrow Search Algorithm (ASFSSA) is employed. Experimental outcomes reveal that the proposed system outperforms traditional approaches, achieving impressive metrics like accuracy of 98%, recall of 95%, precision of 95.7%, F1-score of 98%, specificity of 96%, sensitivity of 97.8% and a peak signal-to-noise ratio of 35%. Additionally, the structural similarity index measure, root mean square error and mean average error of the proposed technique are reported at 0.09%, 4% and 3.02% respectively, showcasing improvements over current methods.