Video-based range estimation for automotive applications: Performance analysis and specification

我和我的合作者进行的研究是在计算机视觉的一般领域，试图赋予机器视觉。从理论的角度来看，这是一项重要的努力，因为它涉及复杂信息处理的基本问题，并且可能产生影响我们对自然系统（例如人类）中视觉信息处理的理解的结果。从实用的角度来看，能看东西的机器有潜力以一种比目前更自然、更有用的方式与人类互动。这项特别提案所包含的研究代表了加拿大学术界（约克大学）和工业界（加拿大通用汽车公司）之间的合作努力。它涉及严格表征基于视频摄像机的计算机视觉技术的性能，用于估计从移动车辆到环境物体的相对3D距离和方向。避免碰撞、障碍物检测和停车需要与环境物体的距离和方向。与视觉在人类感知中的作用类似，基于视频的汽车传感预计将在寻求围绕车辆建立类似人类的感知方面发挥关键作用；当前提案中提出的性能规范将是实现这一潜力的关键。这项研究在三个重要方面为加拿大做出了贡献。首先，它将通过在下一代汽车上整合基于视频的传感技术来实现先进的汽车技术，从而提高加拿大汽车供应链的竞争力。其次，通过对3D距离和方向估计技术的严格性能评估，它将更广泛地推进计算机视觉学科，从而为将此类方法纳入视觉机器铺平道路；这使得加拿大能够在一个关键的科学和技术领域成功竞争。第三，它为学生提供了在调查、计算机视觉以及更普遍的计算机科学与工程等重要领域的实践经验和技能。学生们将继续从事科学、技术、教学和其他领域的职业，并从参与研究中获得丰富的经验。

The research that my collaborators and I carry out is in the general area of computer vision, the attempt to endow machines with a sense of sight. From a theoretical point of view this is an important endeavor as it bears on fundamental issues in complex information processing, and may yield results that bear on our understanding of visual information processing in natural systems (e.g., humans), as well. From a practical point of view, machines that can see have the potential to interact with humans in a much more natural and useful fashion than is currently the case. The research encompassed in this particular proposal represents a collaborative effort between Canadian academia (York University) and industry (General Motors of Canada). It is concerned with rigorously characterizing the performance of video camera-based computer vision technology for estimation of relative 3D distance and direction to environmental objects from a moving vehicle. Distance and direction to environmental objects are required for collision avoidance, obstacle detection and parking. Analogous to the role of vision in human perception, video-based sensing in automobiles is anticipated to play a key role in the quest to build a human-like perception around vehicles; performance specification, as set forth in the current proposal, will be key to realizing this potential. This research contributes to Canada in three important ways. First, it will enable advanced automotive technology via incorporation of video-based sensing on next generation vehicles and thereby enhance the competitiveness of the Canadian automotive supply chain. Second, it more generally will advance the discipline of computer vision through rigorous performance evaluation of 3D distance and orientation estimation techniques and thereby pave the way for incorporation of such methods in vision machines; this allows Canada to compete successfully in a critical area of science and technology. Third, it provides students with hands on experience and skills in vital areas of investigation, computer vision and, more generally, computer science and engineering. Students go on to make careers in science, technology, teaching and elsewhere, taking with them the enrichment of having been involved in research.