Generation and rendering of interactive ground vegetation for real-time testing and validation of computer vision algorithms

Abstract

During the development process of new algorithms for computer vision applications, testing and evaluation in real outdoor environments is time-consuming and often difficult to realize. Thus, the use of artificial testing environments is a flexible and cost-efficient alternative. As a result, the development of new techniques for simulating natural, dynamic environments is essential for real-time virtual reality applications, which are commonly known as Virtual Testbeds. Since the first basic usage of Virtual Testbeds several years ago, the image quality of virtual environments has almost reached a level close to photorealism even in real-time due to new rendering approaches and increasing processing power of current graphics hardware. Because of that, Virtual Testbeds can recently be applied in application areas like computer vision, that strongly rely on realistic scene representations. The realistic rendering of natural outdoor scenes has become increasingly important in many application areas, but computer simulated scenes often differ considerably from real-world environments, especially regarding interactive ground vegetation. In this article, we introduce a novel ground vegetation rendering approach, that is capable of generating large scenes with realistic appearance and excellent performance. Our approach features wind animation, as well as object-to-grass interaction and delivers realistically appearing grass and shrubs at all distances and from all viewing angles. This greatly improves immersion, as well as acceptance, especially in virtual training applications. Nevertheless, the rendered results also fulfill important requirements for the computer vision aspect, like plausible geometry representation of the vegetation, as well as its consistence during the entire simulation. Feature detection and matching algorithms are applied to our approach in localization scenarios of mobile robots in natural outdoor environments. We will show how the quality of computer vision algorithms is influenced by highly detailed, dynamic environments, like observed in unstructured, real-world outdoor scenes with wind and object-to-vegetation interaction.