主题报告： Vehicle Model Recognition based on Deep Network
报告专家：韩国全北国立大学Hyo Jong Lee教授
报告时间：6月20日（周二）下午14:50
报告地点：教学楼D211
主讲人介绍：
Hyo Jong Lee教授本科，硕士与博士均毕业于美国犹他大学，取得了气象学专业与计算机专业双博士学位，自1991年起在韩国全北国立大学拥有26年的教学经验，期间担任系主任以及高级图像与信息技术中心主任。与此同时，李教授曾以访问教授在英国布里斯托尔大学从事研究工作，并长期（7年）在美国加州大学兼职工作，拥有非常高的全英文教学水平。另一方面，李教授在图像处理，模式识别与并行计算中有丰富的科研经验，总共发表70多篇高水平期刊论文，120多篇会议论文。李教授承担过韩国国家研究基金(NRF)，韩国科技部(MSIP),韩国产学研项目等十多项科研课题。
讲座内容简介：
In recent years, vehicle recognition has become an important application in intelligent traffic monitoring and other vehicle management. Vehicle analysis is an essential component in many intelligent applications, such as automatic toll collection, driver assistance systems, self-guided vehicles, intelligent parking systems, and traffic statistics (vehicle count, speed, and flow). In this talk our method, which extract vehicle information from the moving vehicles like their make, model and type, is presented. We address the detection of moving vehicles and recognition problems using Deep Neural Networks (DNNs) approach. A large scale vehicle dataset (~300,000) was collected and labelled from the street cameras, The accuracy of our algorithm is 96.3% and it achieves promising results on our actual data.
