BacklitNet: A dataset and network for backlit image enhancement

Lv, Xiaoqian; Zhang, Shengping; Liu, Qinglin; Xie, Haozhe; Zhong, Bineng; Zhou, Huiyu

doi:10.1016/j.cviu.2022.103403

Cited by 15 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method demonstrates the compensation ability of event cameras to traditional cameras in badly exposed remote sensing scenes, enhancing the ability to capture more informative remote sensing images, and can further improve the accuracy of subsequent tasks such as remote sensing object detection and tracking. Some similar remote sensing tasks, such as backlit image enhancement [67] and low-light image enhancement [5], can also be addressed with our framework. In addition, event cameras have other important attributes, such as high temporal resolution and low latency, which could be further developed to address challenges in other tasks, such as remote sensing motion deblurring [68], by leveraging our methods.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

ERS-HDRI: Event-Based Remote Sensing HDR Imaging

Li,

Cheng,

Zeng

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

High dynamic range imaging (HDRI) is an essential task in remote sensing, enhancing low dynamic range (LDR) remote sensing images and benefiting downstream tasks, such as object detection and image segmentation. However, conventional frame-based HDRI methods may encounter challenges in real-world scenarios due to the limited information inherent in a single image captured by conventional cameras. In this paper, an event-based remote sensing HDR imaging framework is proposed to address this problem, denoted as ERS-HDRI, which reconstructs the remote sensing HDR image from a single-exposure LDR image and its concurrent event streams. The proposed ERS-HDRI leverages a coarse-to-fine framework, incorporating the event-based dynamic range enhancement (E-DRE) network and the gradient-enhanced HDR reconstruction (G-HDRR) network. Specifically, to efficiently achieve dynamic range fusion from different domains, the E-DRE network is designed to extract the dynamic range features from LDR frames and events and perform intra- and cross-attention operations to adaptively fuse multi-modal data. A denoise network and a dense feature fusion network are then employed for the generation of the coarse, clean HDR image. Then, the G-HDRR network, with its gradient enhancement module and multiscale fusion module, performs structure enforcement on the coarse HDR image and generates a fine informative HDR image. In addition, this work introduces a specialized hybrid imaging system and a novel, real-world event-based remote sensing HDRI dataset that contains aligned remote sensing LDR images, remote sensing HDR images, and concurrent event streams for evaluation. Comprehensive experiments have demonstrated the effectiveness of the proposed method. Specifically, it improves state-of-the-art PSNR by about 30% and the SSIM score by about 9% on the real-world dataset.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

ERS-HDRI: Event-Based Remote Sensing HDR Imaging

Li,

Cheng,

Zeng

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…When the light source is positioned directly across from the camera, a significant portion of the light emanating from it is funneled directly into the camera lens. This leads to highly disparate exposure levels between the shadowy foreground and the well-lit background [ 4 ]. Images captured with a backlit setup exhibit minimal contrast, and the image details are scarcely discernible (as illustrated in Figure 1 ).…”

Section: Introductionmentioning

confidence: 99%

Restoration of UAV-Based Backlit Images for Geological Mapping of a High-Steep Slope

2024

Sensors

View full text Add to dashboard Cite

Unmanned aerial vehicle (UAV)-based geological mapping is significant for understanding the geological structure in the high-steep slopes, but the images obtained in these areas are inevitably influenced by the backlit effect because of the undulating terrain and the viewpoint change of the camera mounted on the UAV. To handle this concern, a novel backlit image restoration method is proposed that takes the real-world application into account and addresses the color distortion issue existing in backlit images captured in high-steep slope scenes. Specifically, there are two main steps in the proposed method, which consist of the backlit removal and the color and detail enhancement. The backlit removal first eliminates the backlit effect using the Retinex strategy, and then the color and detail enhancement step improves the image color and sharpness. The author designs extensive comparison experiments from multiple angles and applies the proposed method to different engineering applications. The experimental results show that the proposed method has potential compared to other main-stream methods both in qualitative visual effects and universal quantitative evaluation metrics. The backlit images processed by the proposed method are significantly improved by the process of feature key point matching, which is very conducive to the fine construction of 3D geological models of the high-steep slope.

show abstract

“…This method tends to produce artifacts not present in the original image. Furthermore, as mentioned in Lv et al's report [22], these segmentation-based methods have long processing times and are unsuitable for high-resolution images.…”

Section: Introductionmentioning

confidence: 99%

Low-Artifact and Fast Backlit Image Enhancement Method Based on Suppression of Lightness Order Error

Akai,

Ueda,

Koga

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Many image enhancement methods have been proposed to improve the visibility of backlit images. Although these methods can effectively improve the visibility of the subject and background compared to standard image enhancement methods, they may result in image quality degradation owing to non-negligible artifacts. In many cases, such artifacts are caused by a significant change in the Lightness Order Error (LOE) between the original and processed images. To address this problem, this paper proposes a low-artifact and fast backlit image enhancement method to effectively improve the visibility of images by suppressing the LOE. The proposed method uses adaptive luminance correction to generate lightnessenhanced images of the dark and bright areas of the backlit image. These images are then fused based on a weight map to calculate the lightness of the output image with a lower LOE. The final output, i.e., the enhanced color image, is obtained by multiplying the input color image by the ratio of the lightness component of the input image to the enhanced lightness component. The experimental results demonstrate the superiority of the proposed method in terms of low artifacts, natural enhancement, and high processing speed based on straightforward processing.INDEX TERMS Backlit image, image enhancement, lightness order error, low-artifact image.

show abstract

BacklitNet: A dataset and network for backlit image enhancement

Cited by 15 publications

References 44 publications

ERS-HDRI: Event-Based Remote Sensing HDR Imaging

ERS-HDRI: Event-Based Remote Sensing HDR Imaging

Restoration of UAV-Based Backlit Images for Geological Mapping of a High-Steep Slope

Low-Artifact and Fast Backlit Image Enhancement Method Based on Suppression of Lightness Order Error

Contact Info

Product

Resources

About