A New Image De-hazing Method for Safety Critical ADAS Applications KPIT Technologies Limited

Format:

Conference/Event

Author/Creator:

Baskaran, Baskaran, author.

Contributor:

Kutty, Krishnan

Senthamilarasu, Vinuchackravarthy

Conference Name:

Symposium on International Automotive Technology 2015 (2015-01-21 : Pune, India)

Language:

English

Physical Description:

1 online resource

Place of Publication:

Warrendale, PA SAE International 2015

Summary:

AbstractDriver safety and Advanced Driver Assistance Systems (ADAS) is gaining lot of importance these days. In some countries, there are strict regulations in place which mandate the use of certain ADAS features in automobiles. However, as the need for these safety critical systems increases, the challenges associated also increase. These challenges can arise due to technology, human factors or due to nature. In countries like India, where one can expect different weather conditions with changing geography, the associated challenges are mainly due to the natural factors like haze, fog, rain and smoke. This poses a challenging problem in terms of visibility for the drivers as well as in vision based ADAS; thereby, leading to many fatal road accidents.In this paper, a novel pre-processing technique, which addresses the interesting problem of enhancing the perceptual visibility of an image that is degraded by atmospheric haze, is proposed. The solution to this problem is presented by combining model (Beer Lambert model) based and non-model based technique of haze removal. The combined hybrid model picks the best haze free image from the series of non-hazy outputs, that are derived based on multiple scattering coefficients of the input hazy image. The idea here is to restore the true color of an image that is affected by the atmospheric haze.In comparison with the state of the art methods that are available in literature, the proposed method is shown to be capable of recovering better haze-free images both in terms of visual perception and quantitative evaluation. The proposed method promises better perceptual understandings and visibility restoration for vision based ADAS under hazy driving conditions

Notes:

Vendor supplied data

Publisher Number:

2015-26-0009

Access Restriction:

Restricted for use by site license