Image Haze Removal Using Depth-Based Cluster and Self-Adaptive Parameters
| Autor: | Wenyou Huang, Xiangmin Xu, Chunmei Qing, Hu Yiwei |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Haze
Computer science business.industry Attenuation ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 0211 other engineering and technologies 02 engineering and technology Image segmentation Transmission (telecommunications) Depth map Attenuation coefficient Histogram 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Computer vision Artificial intelligence business 021101 geological & geomatics engineering |
| Zdroj: | iThings/GreenCom/CPSCom/SmartData |
| DOI: | 10.1109/ithings-greencom-cpscom-smartdata.2017.163 |
| Popis: | Removing haze from a single image is a very challenging problem. In this paper, we propose a new method for dehazing from a single image utilizing cluster segmentation. By using K-means to cluster the depth map and segment into several parts, we obtain several regions with different ranges of depth. Then we present to estimate the flexible attenuation coefficient based on intensity for each regions in order to improve the transmission accuracy. Finally, we modify the transmission by setting several boundaries for different regions to avoid oversaturation. Experimental results on various haze images demonstrate that the proposed algorithm is capable of recovering clear and natural haze-free images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|