← back to search

Pengfei Qi

Ministry of Education of the People's Republic of China · CN
Area of research
Computer Vision and Pattern Recognition · Biomedical Engineering
Research interest
Research topics from publications: IPLNet: a neural network for intensity-polarization imaging in low light; Underwater imaging enhancement based on a polarization filter and histogram attenuation prior. Representative work: Imaging in low light is significant but challenging in many applications. Adding the polarization information into the imaging system compromises the drawbacks of the conventional intensity imaging to some extent. However, generally speaking, the qualities of intensity images and polarization images cannot be compatible due to the characteristic differences in polarimetric operators. In this Letter, we collected, to the best of our knowledge, the first polarimetric imaging dataset in low light and present a specially designed neural network to enhance the image qualities of intensity and polarization simultaneously. Both indoor and outdoor experiments demonstrate the effectiveness and superi Abstract Underwater images always suffer from low contrast and inaccurate colors due to scattering and absorption by particles when the target light propagates through turbid water. In this paper, we first found that a lot of intensity space is occupied by fewer pixels, called ‘tails’, on both sides of the histograms for the red, green and blue channels of the image. Based on this histogram attenuation prior and taking account of the advantage of a polarization filter we proposed an effective polarimetric recovery method to enhance the underwater image quality, which includes a specially designed histogram processing method, named ‘cut-tail histogram stretching’. This processing overcomes th
h-index
citations
0
works
0
NIH funding
primary concept
email

Recent publications

Underwater imaging enhancement based on a polarization filter and histogram attenuation prior
Journal of Physics D Applied Physics 2021cited by 31position: middledoi
IPLNet: a neural network for intensity-polarization imaging in low light
Optics Letters 2020cited by 68position: middledoi

Grants

No grants ingested yet.

Frequent collaborators

Haofeng Hu · Ministry of Education of the People's Republic of China2 papers (2020–2021)Tiegen Liu · Ministry of Education of the People's Republic of China2 papers (2020–2021)Xiaobo Li · Ministry of Education of the People's Republic of China2 papers (2020–2021)Lin Yang · Ministry of Education of the People's Republic of China1 papers (2020–2020)Zhenzhou Cheng · Georgia Institute of Technology1 papers (2021–2021)