Human action recognitions in video
In some recent years, local space-time features technique has become an popular method for human action recognition. Many studies have been carried out, with many different types of detectors/descriptors proposed which gave promising result on traditional RGB videos. However, there have been few stu...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/54591 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | In some recent years, local space-time features technique has become an popular method for human action recognition. Many studies have been carried out, with many different types of detectors/descriptors proposed which gave promising result on traditional RGB videos. However, there have been few studies on the usefulness of this technique for action recognition with depth video. In this project, we will evaluate the performance of the Harris 3D detector for both RGB and depth video in a common setup |
|---|