Multi-scale dilated convolution of convolutional neural network for crowd counting

Wang, Yanjie; Hu, Shiyu; Wang, Guodong; Chen, Chenglizhao; Pan, Zhenkuan

doi:10.1007/s11042-019-08208-6

Cited by 55 publications

(20 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IRN model uses RRDB (Xintao Wang et al 2018) module to extract image feature information. In order to improve the ability of neural network to extract image features, the feature extraction structure of RRDB is improved on two directions: First of all, we use dilated convolution (Yanjie Wang et al 2020) instead of standard convolution, choose the convolution core size of 3 × 3, and set the dilated rate of 1, 2 and 4 respectively to avoid the gridding effect, as shown in Fig. 2.…”

Section: Dense Residual Blockmentioning

confidence: 99%

Image Super Resolution Reconstruction Based on Improved Invertible Rescaling Net

Chen

2021

Preprint

View full text Add to dashboard Cite

The Invertible Rescaling Net (IRN) is modeling image downscaling and upscaling as a unified task to alleviate the ill-posed problem in the super-resolution task. However, the ability of potential variables of the model embedded high-frequency information is general, which affects the performance of the reconstructed image. In order to improve the ability of embedding high-frequency information and further reduce the complexity of the model, the potential variables and feature extraction of key components of IRN are improved. Attention mechanism and dilated convolution are used to improve the feature extraction block, reduce the parameters of feature extraction block, and allocate more attention to the image details. The high frequency sub-band interpolation method of wavelet domain is used to improve the potential variables, process and save the image edge, and enhance the ability of embedding high frequency information. Experimental results show that compared with IRN model, improved model has less complexity and excellent performance.

show abstract

Section: Dense Residual Blockmentioning

confidence: 99%

Image Super Resolution Reconstruction Based on Improved Invertible Rescaling Net

Chen

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A CNN can be used to estimate crowd density at railway stations [173],to detect intrusions in track areas, such as pedestrians or large livestock via images captured in railway areas [174], to monitor railway construction [152] and for intrusion detection at railway crossings [175]. From the security side, the method been used for detecting violent crowd flows [176], protect the critical infrastructure [177], and identifying tools wielding by attackers such as knives, guns and Explosives [178].…”

Section: Related Work In Railway Systemsmentioning

confidence: 99%

A Deep Learning Approach Towards Railway Safety Risk Assessment

Alawad

Kaewunruen

2020

IEEE Access

View full text Add to dashboard Cite

Railway stations are essential aspects of railway systems, and they play a vital role in public daily life. Various types of AI technology have been utilised in many fields to ensure the safety of people and their assets. In this paper, we propose a novel framework that uses computer vision and pattern recognition to perform risk management in railway systems in which a convolutional neural network (CNN) is applied as a supervised machine learning model to identify risks. However, risk management in railway stations is challenging because stations feature dynamic and complex conditions. Despite extensive efforts by industry associations and researchers to reduce the number of accidents and injuries in this field, such incidents still occur. The proposed model offers a beneficial method for obtaining more accurate motion data, and it detects adverse conditions as soon as possible by capturing fall, slip and trip (FST) events in the stations that represent high-risk outcomes. The framework of the presented method is generalisable to a wide range of locations and to additional types of risks.

show abstract

“…Multi‐scale (Gaussian kernel) technique is a popular tool for image processing, which has been applied in many tasks such as the crowd counting [31], medical image classification [32] and saliency detection in satellite images [8]. During the saliency detection in satellite images, Gaussian smoothing and bilateral filtering are used to detect multi‐scale blobs and generate a blob map from the input image [8].…”

Section: Literature Reviewmentioning

confidence: 99%

Fast visual saliency based on multi‐scale difference of Gaussians fusion in frequency domain

Yang

et al. 2020

IET image process

View full text Add to dashboard Cite

To reduce the computation required in determining the proper scale of salient object, a fast visual saliency based on multi-scale difference of Gaussians fusion in frequency domain (MDF) is proposed. First, based on the phenomenon that the foreground energy is highlighted and densely distributes on certain band of spectrum, the scale coefficients of foreground in an image can be literately approximated on the amplitude spectrum. Next, relying on the linear integration property of Fourier transform, the feature spectrum is obtained through the weighted infinite integral of difference of Gaussian feature maps with respect to the scale of object. Then, the saliency of each channel is obtained from feature spectrum by the inverse Fourier transform and scale filtering. Finally, through the channel integration, the MDF saliency map is obtained. Experiments on Li-Jian data set demonstrate that combined with most appropriate colour space and scale filter, MDF achieves obvious acceleration (5.4 times faster than frequency domain analysis and spatial information) while getting desired accuracy (area under the curve, 0.8814 at Li-Jian data set), which achieves the best accuracy efficiency trade-off.

show abstract

Multi-scale dilated convolution of convolutional neural network for crowd counting

Cited by 55 publications

References 19 publications

Image Super Resolution Reconstruction Based on Improved Invertible Rescaling Net

Image Super Resolution Reconstruction Based on Improved Invertible Rescaling Net

A Deep Learning Approach Towards Railway Safety Risk Assessment

Fast visual saliency based on multi‐scale difference of Gaussians fusion in frequency domain

Contact Info

Product

Resources

About