Training convolutional neural networks for human re-identification (B)
Human re-identification has become a popular research topic due to advancements in neural network research and progression in IoT technology, Furthermore, with increasing importance for public security, human re-identification is critical to the security firms and governments. The objective of the...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/77315 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | Human re-identification has become a popular research topic due to advancements in neural network research and progression in IoT technology, Furthermore, with increasing importance for public security, human re-identification is critical to the security firms and governments.
The objective of the project is to develop a dataset of images from real-world based security cameras and implement the latest neural models to the dataset to evaluate their performance and comparing them with available public datasets.
SoftMax and triplet loss models will be implemented to evaluate the results, as well as the implementation of data augmentation method for further evaluation and comparison of the datasets. |
|---|