本文为美国俄亥俄州立大学（作者：Erik Petersen Schilling）的学士论文，共41页。

分心驾驶是美国许多事故中的常见因素。汽车制造商正试图采用技术来提高驾驶员对道路的感知认识。虽然诸如车道偏离警告、盲点监视器和自适应巡航控制等系统是有效的，但几乎没有第三方技术，而且基本上没有开源技术。本文所描述的系统使用了一个健壮、廉价且精确的车辆检测系统，该系统是可扩展的，允许他方对系统进行升级改进。系统在分层过程中检测关键车辆特性，每一层要求每个区域通过更精细的特征准则来剪除一组假设的车辆区域。车道检测也可用于减少车辆检测时间。测试表明，该系统的准确率为82%，召回率为76%。

Distracted driving is a common factor inmany accidents in the United States. Car manufacturers are trying to implementtechnologies to increase a driver’s awareness of the road. While systems suchas lane departure warnings, blind spot monitors, and adaptive cruise controlare effective, there are few third party technologies and essentially none thatare open source. The system described in this thesis uses a robust, cheap, andaccurate vehicle detection system that is extendable, allowing for otherparties to contribute to the system. The system detects key vehiclecharacteristics in a tiered process. Each tier prunes the set of hypothesizedvehicle regions by requiring each region pass more refined characteristiccriteria. Lane detection is also leveraged to reduce vehicle detection time.Testing shows that the system has a precision of 82% and a recall of 76%.

1 引言

2 文献回顾

3 系统设计回顾

4 系统实现

5 实验评估

更多精彩文章请关注公众号：