As a prerequisite for autonomous driving, scene understanding has attracted extensive research. With the rise of the convolutional neural network (CNN)-based deep learning technique, research on scene understanding has achieved significant progress. This paper aims to provide a comprehensive survey of deep learning-based approaches for scene understanding in autonomous driving. We categorize these works into four work streams, including object detection, full scene semantic segmentation, instance segmentation, and lane line segmentation. We discuss and analyze these works according to their characteristics, advantages and disadvantages, and basic frameworks. We also summarize the benchmark datasets and evaluation criteria used in the research community and make a performance comparison of some of the latest works. Lastly, we summarize the review work and provide a discussion on the future challenges of the research domain.

This study investigates the adsorption mechanism differences among four nitrogenous dyes, sulforhodamine G (SRG), uncharged/deprotonated rhodamine B (RhB), orange II (Or II) and methyl blue (MB) by montmorillonite (MMT). MMT adsorption capacity for cationic MB was three times that of uncharged RhB and anionic SRG, while anionic Or II was not absorbed. Colloidal MMT particles have two types of surfaces, basal and edge, that interact with nitrogenous dyes very differently. The surface acidity of MMT was characterized with the pyridine adsorption method using in-situ diffuse reflectance infrared Fourier transform spectroscopy (in-situ DRIFTS). Adsorption of cationic MB was compared with the adsorption of RhB. In-situ attenuated total reflectance Fourier transform infrared (in-situ ATR-FTIR) spectroscopy indicated that a nitrogen atom on RhB complexes with a metal hydroxyl on an MMT edge through a water bridge. The highly polar edge hydroxyl is important to hydrogen bond formation. Cation ion exchange and washing experiments, as well as studies on the effect of temperature, pH and ionic strength on adsorption further clarified the adsorption mechanism. Our results provide insights into the effects of molecular structure on the adsorption of nitrogenous dyes by clay and the role of edge surfaces in the adsorption process.