A New Multi-level Hazy Image and Video Dataset for Benchmark of Dehazing Methods

Creative Commons License

Çetinkaya B., Çimtay Y., Günay F. N., Yılmaz G.

4th International Conference on Image Processing and Capsule Networks, ICIPCN 2023, Bangkok, Tayland, 10 - 11 Ağustos 2023, cilt.798 LNNS, ss.269-280 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 798 LNNS
  • Doi Numarası: 10.1007/978-981-99-7093-3_18
  • Basıldığı Şehir: Bangkok
  • Basıldığı Ülke: Tayland
  • Sayfa Sayıları: ss.269-280
  • Anahtar Kelimeler: Hazy imagery, Image enhancement, Poor visibility, Reconstruction of images
  • TED Üniversitesi Adresli: Evet

Özet

The changing level of haze is one of the main factors which affects the success of the proposed dehazing methods. However, there is a lack of controlled multi-level hazy dataset in the literature. Therefore, in this study, a new multi-level hazy color image dataset is presented. Color video data is captured for two real scenes with a controlled level of haze. The distance of the scene objects from the camera, haze level, and ground truth (clear image) is available so that different dehazing methods and models can be benchmarked. In this study, the dehazing performance of five different dehazing methods/models is compared on the dataset based on SSIM, PSNR, VSI, and DISTS image quality metrics. Results show that traditional methods can generalize the dehazing problem better than many deep learning-based methods. The performance of deep models depends mostly on the scene and is generally poor on cross-dataset dehazing.