Abstract
Haze is the most frequently encountered weather condition on the road, and it accounts for a considerable number of car crashes occurring every year. Accordingly, image dehazing has garnered strong interest in recent decades. However, although various algorithms have been developed, a robust dehazing method that can operate reliably in different haze conditions is still in great demand. Therefore, this paper presents a method to adapt a dehazing system to various haze conditions. Under this approach, the proposed method discriminates haze conditions based on the haze density estimate. The discrimination result is then leveraged to form a piece-wise linear weight to modify the depth estimator. Consequently, the proposed method can effectively handle arbitrary input images regardless of their haze condition. This paper also presents a corresponding real-time hardware implementation to facilitate the integration into existing embedded systems. Finally, a comparative assessment against benchmark designs demonstrates the efficacy of the proposed dehazing method and its hardware counterpart.
Highlights
High-level object recognition systems, which operate in outdoor environments, are subject to weather conditions
This paper presented a robust image dehazing algorithm that could deliver satisfactory performance in various haze conditions
This robustness is a result of adopting the haze density estimate to modify the scene depth estimator
Summary
High-level object recognition systems, which operate in outdoor environments, are subject to weather conditions. According to a comprehensive investigation of Pei et al [1], performance reduces proportionally to the haze thickness; rendering image dehazing essential. In this context, image dehazing should be located near the camera to pre-process the image data to improve visibility. Deep dehazing models often yield state-of-the-art performance at expensive computational and manufacturing costs This limitation hinders the practical application in real-world embedded systems, where the aforementioned factors are critical. This paper presents a corresponding FPGA implementation to facilitate the application in real-world embedded systems. An elegant solution to form a piece-wise linear weight from the haze density estimate to improve the robustness of a dehazing algorithm, and a real-time high-performance hardware accelerator that can handle DCI 4K images at.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
