Semi-automatic Pedestrian Labeling Based on On-line Boosting for Transfer Learning with Multiple Sources

碩士 === 國立高雄科技大學 === 電腦與通訊工程系 === 107 === Ground truth annotation is crucial in evaluating the performance of pedestrian detection algorithms. Nevertheless, manually annotation is a tedious and time-consuming task. In this work, we propose a pedestrian labeling system based on on-line boosting for tr...

Full description

Bibliographic Details
Main Authors: Xue, Yu-Xiang, 薛宇翔
Other Authors: HUANG,SHIH-SHINH
Format: Others
Language:zh-TW
Published: 2019
Online Access:http://ndltd.ncl.edu.tw/handle/c8n7kx