Intelligent video defogging technology based on covariance and perceptron
| Autor: | Yanfan Xiong, Jianming Guo, Qing Liu, Longli Li |
|---|---|
| Rok vydání: | 2011 |
| Předmět: |
Channel (digital image)
business.industry Covariance matrix Computer science Frame (networking) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Covariance Perceptron Object detection symbols.namesake Transmission (telecommunications) Feature (computer vision) symbols Computer vision Artificial intelligence business Gaussian process |
| Zdroj: | ICNC |
| DOI: | 10.1109/icnc.2011.6021916 |
| Popis: | As the algorithm of video defogging must meet real-time requirement, a new method is proposed, it uses the covariance matrix of multi-feature combination to describe image features, and combines with perceptron model to intelligently detect foggy scenes. Because the backgrounds of industrial video images generally change slowly, Gaussian mixture modeling is used to get foregrounds. The transmission of dark channel prior is updated according to the foreground. Then each frame is restored directly according to the newer transmission. The defogging algorithm greatly reduces the running time. It achieves the purpose of video defogging. Experimental results show that the algorithm has a high accuracy on detecting foggy scenes. The algorithm of video defogging proposed can meet the industrial real-time requirements and ensure spatial and temporal consistency of video. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|