A scene invariant convolutional neural network for visual crowd counting using fast-lane and sample selective methods
Convolutional neural network (CNN) based crowd counting aims to estimate the number of pedestrians from the image. Existing research usually follow the training-testing protocol within a single dataset and the accuracy drops when conducting cross-dataset evaluation. Density map prediction methodolog...
Saved in:
Main Author: | Teoh, Shen Khang |
---|---|
Format: | Final Year Project / Dissertation / Thesis |
Published: |
2023
|
Subjects: | |
Online Access: | http://eprints.utar.edu.my/5945/1/1606100_Teoh_Shen_Khang.pdf http://eprints.utar.edu.my/5945/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Editing techniques: analysis on action scenes in road action films in Malaysia
by: Rosli Sareya, et al.
Published: (2014) -
3D Intrinsic scene characteristics extraction framework for a single image
by: Akbar, Habibullah
Published: (2016) -
Ekspresi emosi dalam pengkaryaan seni visual
by: Japery, Ibai
Published: (2016) -
The Research on the effectiveness of visual in the manual guide of digital camera
by: Wong, Vincent Thian Fook
Published: (2007) -
Seni Ekspresi Jalinan Melalui Seni Fotografi Makro Dalam Konteks Visual
by: Mohd Nasri, Mohd Safir
Published: (2017)