2022
DOI: 10.3233/jifs-220503
|View full text |Cite
|
Sign up to set email alerts
|

Activity detection and counting people using Mask-RCNN with bidirectional ConvLSTM

Abstract: Image Incorporation concerns, including background confusion, uneven population distribution, and variations in scale and familiarity, can make group counting difficult. Pre-existing information and multi-level contextual representations are required to handle these problems effectively with deep neural networks and Mask-RCNN. Numerous studies on crowd counting use density maps without segmentation, which treat a group of individuals as a single entity. This article offers a hybrid method for crowd counting th… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
2

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(3 citation statements)
references
References 30 publications
0
3
0
Order By: Relevance
“…Our architecture expands the architecture described by interpreting image data in both directions using a Convolutional LSTM (ConvLSTM). 20 We hypothesize that accessing both previous and future information from an existing state enables the BiConvLSTM [21][22][23][24][25][26] to comprehend the meaning of the existing input, resulting in improved categorizing on non-homogenous and voluminous datasets. It demonstrates our networks' effectiveness in conducting experimentation on three standard datasets.…”
Section: Proposed Systemmentioning
confidence: 99%
See 1 more Smart Citation
“…Our architecture expands the architecture described by interpreting image data in both directions using a Convolutional LSTM (ConvLSTM). 20 We hypothesize that accessing both previous and future information from an existing state enables the BiConvLSTM [21][22][23][24][25][26] to comprehend the meaning of the existing input, resulting in improved categorizing on non-homogenous and voluminous datasets. It demonstrates our networks' effectiveness in conducting experimentation on three standard datasets.…”
Section: Proposed Systemmentioning
confidence: 99%
“…And finally, this interpretation is fed into a classifier that determines whether or not the image/video includes abuse. Our architecture expands the architecture described by interpreting image data in both directions using a Convolutional LSTM (ConvLSTM) 20 . We hypothesize that accessing both previous and future information from an existing state enables the BiConvLSTM 21–26 to comprehend the meaning of the existing input, resulting in improved categorizing on non‐homogenous and voluminous datasets.…”
Section: Proposed Systemmentioning
confidence: 99%
“…RNNs, LSTMs, gated recurrent units (GRUs) are designed to process sequential data, making them suitable for time series analysis, while combined with CNNs could improve the accuracy and granularity of local population projections. For example, convolutional long short-term memory networks (ConvLSTMs) have already been used to process time series of remote sensing images [81,63,131] and bear potential for applications on population projections.…”
Section: Ethical Considerationsmentioning
confidence: 99%