2013 IEEE International Conference on Image Processing 2013
DOI: 10.1109/icip.2013.6738936
|View full text |Cite
|
Sign up to set email alerts
|

A method for counting moving and stationary people by interest point classification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
9
0

Year Published

2016
2016
2021
2021

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 13 publications
(9 citation statements)
references
References 7 publications
0
9
0
Order By: Relevance
“…To name a few, [31] proposed a system based on learning person appearance models, whereas [2] used hierarchical Gaussian Process Latent Variable Models (hGPLVM) for modeling people. Other approaches were based on face detection [10] or interest point classification [20]. In recent years, improvements in technology and the availability of large annotated image datasets such as Imagenet [23] have allowed Deep Neural Networks (DNNs) to become the state-of-the-art solutions for tasks such as object detection [33], segmentation [8] and classification [19] in RGB images.…”
Section: Introduction and State Of The Artmentioning
confidence: 99%
“…To name a few, [31] proposed a system based on learning person appearance models, whereas [2] used hierarchical Gaussian Process Latent Variable Models (hGPLVM) for modeling people. Other approaches were based on face detection [10] or interest point classification [20]. In recent years, improvements in technology and the availability of large annotated image datasets such as Imagenet [23] have allowed Deep Neural Networks (DNNs) to become the state-of-the-art solutions for tasks such as object detection [33], segmentation [8] and classification [19] in RGB images.…”
Section: Introduction and State Of The Artmentioning
confidence: 99%
“…Many studies have used keypoints to find the level of the crowd (number of people) due to their strong inter-dependance [55]- [58]. It is worth noting that although there is a degree of correlation relationship between the level of the crowd and the level of occlusion in a frame, this relationship is not always valid in all scenarios.…”
Section: The Occlusion-level Modelmentioning
confidence: 99%
“…The results of using moving keypoints to find the number of people show that they have a strong relationship [55]- [58]. Many people counting studies have been carried out using FAST, SIFT and SURF points [24], [60].…”
Section: Feature Representation and Selectionmentioning
confidence: 99%
“…Local algorithms count the number of people by partitioning the frame into several regions and one local regression function is trained for each region to count the total number of people in the whole frame. The regions can be cells having regular or irregular sizes [18] or the regions can be foreground blobs and the total number of people is counted by summing the numbers in all regions [43], [65]- [68].…”
Section: Low-level Features Regression Based Algorithmsmentioning
confidence: 99%