基于迁移学习的行人检测方法研究-计算机应用技术专业论文.docxVIP

优秀毕业论文 精品参考文献资料 研究生优秀毕业论文 Abstract Abstract 硕士学位论文 Abstra ct Pedestrian detection is the core of the application of intelligent rmnitoring systems， intelligent transportation systerm and intelligent vehicle systems．The goal of the study of pedestrian detection methods based on transfer learning,is to improve the detection performance of the classifier by making use of transfer leaming． This paper seperates the study of pedestrian detection based on transfer learning into two parts：the first one is sample selection strategy,and the second one is san印le faltering algorit hm． This paper also proposed a pedestrian detection model based on transfer learning．The main research of sanple selection strategy,is to select samples for the training sample sets．Its goal is to enhance the detection perfommace of classifier．Sample filtering algorithm is mainly in the field of research methods to obtain the target sample丘Dm the detection results，SO that to continm acquiring right new sample in the target field． This paper studies the sample selection strategy based on determined positive and detern-hned negative samples．The main research study on two sample selection strategies：the first One is adding samples directly and the last is adding san甲les relies on a filtered set based on the orig证al classifier．Wah the research．，a conclusion is draw that the strategy which adding samples reties on a filtered set based on the original classifier is a relatively viable strategy at Caltech pedestrian database with a proper sample-grouping condition． This paper also studied sample faltering algorithm for transfer learning based on perdestrian size model．According calrlera imaging characteristics，this paper proposed pedestrian size model to meet the needs of specific scenarios captured by Car camer