Saliency detection in human crowd images of different density levels using attention mechanism

Nguyen, Minh Tri; Siritanawan, Prarinya; Kotani, Kazuhiko

doi:10.1016/j.image.2020.115976

Cited by 8 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen et al [ 16 ] argued that ResNet is essentially DenseNet with shared connections, and ResNet implicitly has residual path reuse features, and dense connections that can be mined for new features, based on this joint perspective dual-channel network (DPN) were proposed, by sharing same features of network through dual-path structure; high accuracy is achieved with flexibility, small models, less computation, and low resources. Nguyen et al [ 26 ] proposed MSDENSE-DAT to predict regions in crowd scenes that attract human attention, designed two-branch homography network based on DenseNet201 to extract multiscale features, extracted as many features as possible from original size and half-size images, and cascaded two-branch features along channel axis, and also designed self-attention blocks to emphasize interfeature correlation; MSDENSE-DAT extracts the best features with low density in the crowd.…”

Section: Development Of Densenetmentioning

confidence: 99%

Dense Convolutional Network and Its Application in Medical Image Analysis

Tao

XinYu

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

Dense convolutional network (DenseNet) is a hot topic in deep learning research in recent years, which has good applications in medical image analysis. In this paper, DenseNet is summarized from the following aspects. First, the basic principle of DenseNet is introduced; second, the development of DenseNet is summarized and analyzed from five aspects: broaden DenseNet structure, lightweight DenseNet structure, dense unit, dense connection mode, and attention mechanism; finally, the application research of DenseNet in the field of medical image analysis is summarized from three aspects: pattern recognition, image segmentation, and object detection. The network structures of DenseNet are systematically summarized in this paper, which has certain positive significance for the research and development of DenseNet.

show abstract

Section: Development Of Densenetmentioning

confidence: 99%

Dense Convolutional Network and Its Application in Medical Image Analysis

Tao

XinYu

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…e first step of the method is also to collect the raw image dataset, and then, the collected raw images are detected and identified using an existing network model of convolutional neural networks with high accuracy, where the dataset is trained using the existing VOC2012 dataset. e convolutional neural network algorithm is used to frame out the pedestrians in the image and calculate their confidence level, the confidence interval of this system is set to be greater than 50%, but most of the framed pedestrian targets in the image have a confidence level of less than 50%, so there is severe occlusion between these targets and they are unidentifiable, but in reality, the targets are present, so the accuracy of this solution is not high [34][35][36][37][38][39][40]. However, when combined with the actual situation and the observation of multiple images, it is easy to see that there is a minimal occlusion in the pedestrian head region, so this paper uses head recognition to detect pedestrians.…”

Section: Classification Of Density Of People and System Flowmentioning

confidence: 99%

A Crowd Density Detection Algorithm for Tourist Attractions Based on Monitoring Video Dynamic Information Analysis

2020

Complexity

View full text Add to dashboard Cite

In this paper, we analyze and calculate the crowd density in a tourist area utilizing video surveillance dynamic information analysis and divide the crowd counting and density estimation task into three stages. In this paper, novel scale perception module and inverse scale perception module are designed to further facilitate the mining of multiscale information by the counting model; the main function of the third stage is to generate the population distribution density map, which mainly consists of three columns of void convolution with different void rates and generates the final population distribution density map using the feature maps of different branch regressions. Also, the algorithm uses jump connections between the top convolution and the bottom void convolution layers to reduce the risk of network gradient disappearance and gradient explosion and optimizes the network parameters using an intermediate supervision strategy. The hierarchical density estimator uses a hierarchical strategy to mine semantic features and multiscale information in a coarse-to-fine manner, and this is used to solve the problem of scale variation and perspective distortion. Also, considering that the background noise affects the quality of the generated density map, the soft attention mechanism is integrated into the model to stretch the distance between the foreground and background to further improve the quality of the density map. Also, inspired by multitask learning, this paper embeds an auxiliary count classifier in the count model to perform the count classification auxiliary task and to increase the model’s ability to express semantic information. Numerous experimental results demonstrate the effectiveness and feasibility of the proposed algorithm in solving the problems of scale variation and perspective distortion.

show abstract