Multi-Attention DenseNet: A Scattering Medium Imaging Optimization Framework for Visual Data Pre-Processing of Autonomous Driving Systems

The vision system is important for almost all kinds of autonomous driving systems. However, visual data interfered by scattering media, such as smoke, haze, water, and other non-uniform media will be degraded seriously, showing the characteristics of detail loss, poor contrast, low visibility, or color distortion. These characteristics can significantly interfere with the reliability of autonomous driving systems. In real environments the image degradation mechanism is complex, and the estimation of degradation parameters is difficult. This issue remains to be solved. In this study, we employed dense blocks as the framework and introduced the attention mechanism to our model from four dimensions: Multi-scale Attention, Channel Attention, Structure Attention, and ROI (region of interest) Attention. With the help of the training data provided by the weakly supervised model, the proposed method achieved excellent performance in the task of scattering medium imaging optimization in different scenes. Comparative experiments show that the proposed method is robust, and is superior to other state-of-the-art methods in image dehazing, and underwater image enhancement tasks. It is of great significance to improve the reliability of autonomous driving systems in underwater and severe weather environments.

Automated summary

The vision system plays a crucial role in autonomous driving systems, but the presence of scattering media can seriously degrade visual data and affect the reliability of the systems. This study proposes a method that employs dense blocks and attention mechanism to achieve excellent performance in scattering medium imaging optimization, using training data from a weakly supervised model.