A Survey of Scene Understanding by Event Reasoning in Autonomous Driving

Realizing autonomy is a hot research topic for automatic vehicles in recent years. For a long time, most of the efforts to this goal concentrate on understanding the scenes surrounding the ego-vehicle（autonomous vehicle itself）. By completing lowlevel vision tasks, such as detection, tracking and segmentation of the surrounding traffic participants, e.g., pedestrian, cyclists and vehicles, the scenes can be interpreted. However, for an autonomous vehicle, low-level vision tasks are largely insufficient to give help to comprehensive scene understanding. What are and how about the past, the on-going and the future of the scene participants？ This deep question actually steers the vehicles towards truly full automation, just like human beings. Based on this thoughtfulness, this paper attempts to investigate the interpretation of traffic scene in autonomous driving from an event reasoning view. To reach this goal, we study the most relevant literatures and the state-of-the-arts on scene representation, event detection and intention prediction in autonomous driving. In addition, we also discuss the open challenges and problems in this field and endeavor to provide possible solutions.

Dynamic background modeling using tensor representation and ant colony optimization

Background modeling and subtraction is a fundamental problem in video analysis. Many algorithms have been developed to date, but there are still some challenges in complex environments, especially dynamic scenes in which backgrounds are themselves moving, such as rippling water and swaying trees. In this paper, a novel background modeling method is proposed for dynamic scenes by combining both tensor representation and swarm intelligence. We maintain several video patches, which are naturally represented as higher order tensors,to represent the patterns of background, and utilize tensor low-rank approximation to capture the dynamic nature. Furthermore, we introduce an ant colony algorithm to improve the performance. Experimental results show that the proposed method is robust and adaptive in dynamic environments, and moving objects can be perfectly separated from the complex dynamic background.

State of the Art on Deep Learning-enhanced Rendering Methods

Photorealistic rendering of the virtual world is an important and classic problem in the field of computer graphics.With the development of GPU hardware and continuous research on computer graphics,representing and rendering virtual scenes has become easier and more efficient.However,there are still unresolved challenges in efficiently rendering global illumination effects.At the same time,machine learning and computer vision provide real-world image analysis and synthesis methods,which can be exploited by computer graphics rendering pipelines.Deep learning-enhanced rendering combines techniques from deep learning and computer vision into the traditional graphics rendering pipeline to enhance existing rasterization or Monte Carlo integration renderers.This state-of-the-art report summarizes recent studies of deep learning-enhanced rendering in the computer graphics community.Specifically,we focus on works of renderers represented using neural networks,whether the scene is represented by neural networks or traditional scene files.These works are either for general scenes or specific scenes,which are differentiated by the need to retrain the network for new scenes.