A night semantic segmentation method based on low-illumination enhancement and edge optimization

By combining a low-light enhancement and inpainting network based on Retinex theory and local contrast enhancement with an improved semantic segmentation network, the performance degradation problem of the nighttime semantic segmentation model in low-light environments is solved, achieving improved image clarity and edge structure preservation, and enhancing the accuracy and robustness of nighttime segmentation.

CN121962610BActive Publication Date: 2026-07-21GUIZHOU UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
GUIZHOU UNIV
Filing Date
2026-01-23
Publication Date
2026-07-21

AI Technical Summary

Technical Problem

Existing nighttime semantic segmentation models exhibit significant performance degradation in low-light environments, struggling to adapt to changes in illumination, exposure imbalances, and edge degradation. This leads to uneven changes in object appearance and structural texture, increasing the difficulty of boundary recognition. Furthermore, existing enhancement methods are prone to introducing blurring or over-smoothing and lack end-to-end optimization.

Method used

We employ a low-light enhancement and inpainting network based on Retinex theory, local contrast enhancement, and adaptive feature fusion. This network is combined with an improved semantic segmentation network and a channel attention module. End-to-end training is performed by jointly optimizing the loss function through multiple tasks, thus achieving deep coupling between image enhancement and segmentation tasks.

Benefits of technology

It effectively improves the clarity and edge structure preservation of nighttime images, enhances the robustness and segmentation accuracy of the model in low-light environments, and performs particularly well in boundary recognition and small target recognition, with adaptive capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121962610B_ABST
    Figure CN121962610B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of semantic segmentation, and particularly relates to a night semantic segmentation method based on low-illumination enhancement and edge optimization, method steps are as follows: an image is input into a low-light enhancement repair network based on Retinex theory, local contrast enhancement and adaptive feature fusion, an intermediate image after noise reduction and enhancement processing is obtained, the intermediate image is input into a semantic segmentation network to obtain a class distribution map of each pixel; the class distribution map of each pixel is input into a discriminator embedded with a channel attention module, a generator composed of the low-light enhancement repair network and the semantic segmentation network is optimized through a multi-task joint optimization loss function; a night image to be measured and segmented is input into the optimized generator, and a segmentation result is output. By using the above method, the low-light enhancement repair network combines the local contrast enhancement and the channel feature fusion mechanism, the overall brightness of the image is improved, the image details and edge structure are retained, and the model perception ability and robustness are improved.
Need to check novelty before this filing date? Find Prior Art