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...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/77315 |
| _version_ | 1811683569298309120 |
|---|---|
| author | Chew, Keng Siang |
| author2 | Alex Kot Chichung |
| author_facet | Alex Kot Chichung Chew, Keng Siang |
| author_sort | Chew, Keng Siang |
| collection | NTU |
| description | 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. |
| first_indexed | 2024-10-01T04:14:49Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/77315 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:14:49Z |
| publishDate | 2019 |
| record_format | dspace |
| spelling | ntu-10356/773152023-07-07T16:05:05Z Training convolutional neural networks for human re-identification (B) Chew, Keng Siang Alex Kot Chichung School of Electrical and Electronic Engineering Rapid-Rich Object Search (ROSE) Lab DRNTU::Engineering::Electrical and electronic engineering 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. Bachelor of Engineering (Electrical and Electronic Engineering) 2019-05-27T02:17:16Z 2019-05-27T02:17:16Z 2019 Final Year Project (FYP) http://hdl.handle.net/10356/77315 en Nanyang Technological University 54 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering Chew, Keng Siang Training convolutional neural networks for human re-identification (B) |
| title | Training convolutional neural networks for human re-identification (B) |
| title_full | Training convolutional neural networks for human re-identification (B) |
| title_fullStr | Training convolutional neural networks for human re-identification (B) |
| title_full_unstemmed | Training convolutional neural networks for human re-identification (B) |
| title_short | Training convolutional neural networks for human re-identification (B) |
| title_sort | training convolutional neural networks for human re identification b |
| topic | DRNTU::Engineering::Electrical and electronic engineering |
| url | http://hdl.handle.net/10356/77315 |
| work_keys_str_mv | AT chewkengsiang trainingconvolutionalneuralnetworksforhumanreidentificationb |