Obstacle detection by fusing image and depth information

• Main Author: Liu, Yufeng
• Other Authors: Wen Changyun
• Format: Final Year Project
• Language: English
• Published: 2018
• Subjects: DRNTU::Engineering
• Online Access: http://hdl.handle.net/10356/74514
• Institution: Nanyang Technological University

With the rapid development of technology, applications of object detection become more and more important. The need for robustness and accuracy of object detection is increased as well. The goal of this project is to provide the proper object detection algorithm by using both fusing image and depth information, showing that the robustness and accuracy of object detection will be improved when both RGB and depth information are applied. The object detector that combines Histogram of Oriented Gradient (HOG) with efficient Liner SVM classifiers is presented in this project. It achieves prominent performance on the object RGB-D dataset. Based on the results, it could be said that the object detector provides better performance when both RGB-D information are applied.