scholarly journals Redesigned Skip-Network for Crowd Counting with Dilated Convolution and Backward Connection

2020 ◽  
Vol 6 (5) ◽  
pp. 28
Author(s):  
Sorn Sooksatra ◽  
Toshiaki Kondo ◽  
Pished Bunnun ◽  
Atsuo Yoshitaka
Keyword(s):  
Mean Squared Error ◽  
Absolute Error ◽  
Experimental Result ◽  
Crowd Counting ◽  
Low Level ◽  
Dilated Convolution ◽  
Counting Error ◽  
Crowd Density ◽  
High Level ◽  
High Level Feature

Crowd counting is a challenging task dealing with the variation of an object scale and a crowd density. Existing works have emphasized on skip connections by integrating shallower layers with deeper layers, where each layer extracts features in a different object scale and crowd density. However, only high-level features are emphasized while ignoring low-level features. This paper proposes an estimation network by passing high-level features to shallow layers and emphasizing its low-level feature. Since an estimation network is a hierarchical network, a high-level feature is also emphasized by an improved low-level feature. Our estimation network consists of two identical networks for extracting a high-level feature and estimating the final result. To preserve semantic information, dilated convolution is employed without resizing the feature map. Our method was tested in three datasets for counting humans and vehicles in a crowd image. The counting performance is evaluated by mean absolute error and root mean squared error indicating the accuracy and robustness of an estimation network, respectively. The experimental result shows that our network outperforms other related works in a high crowd density and is effective for reducing over-counting error in the overall case.

scholarly journals Multiscale Aggregate Networks with Dense Connections for Crowd Counting

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Pengfei Li ◽  
Min Zhang ◽  
Jian Wan ◽  
Ming Jiang
Keyword(s):  
Mean Squared Error ◽  
Absolute Error ◽  
Image Features ◽  
Convolutional Network ◽  
Crowd Counting ◽  
Squared Error ◽  
Crowd Density ◽  
Density Maps ◽  
Density Map ◽  
Map Decoder

The most advanced method for crowd counting uses a fully convolutional network that extracts image features and then generates a crowd density map. However, this process often encounters multiscale and contextual loss problems. To address these problems, we propose a multiscale aggregation network (MANet) that includes a feature extraction encoder (FEE) and a density map decoder (DMD). The FEE uses a cascaded scale pyramid network to extract multiscale features and obtains contextual features through dense connections. The DMD uses deconvolution and fusion operations to generate features containing detailed information. These features can be further converted into high-quality density maps to accurately calculate the number of people in a crowd. An empirical comparison using four mainstream datasets (ShanghaiTech, WorldExpo’10, UCF_CC_50, and SmartCity) shows that the proposed method is more effective in terms of the mean absolute error and mean squared error. The source code is available at https://github.com/lpfworld/MANet.

scholarly journals A High-Density Crowd Counting Method Based on Convolutional Feature Fusion

2018 ◽  
Vol 8 (12) ◽  
pp. 2367 ◽  
Author(s):  
Hongling Luo ◽  
Jun Sang ◽  
Weiqun Wu ◽  
Hong Xiang ◽  
Zhili Xiang ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Feature Fusion ◽  
High Density ◽  
Counting Problem ◽  
Crowd Counting ◽  
Low Level ◽  
Density Map ◽  
High Level

In recent years, the trampling events due to overcrowding have occurred frequently, which leads to the demand for crowd counting under a high-density environment. At present, there are few studies on monitoring crowds in a large-scale crowded environment, while there exists technology drawbacks and a lack of mature systems. Aiming to solve the crowd counting problem with high-density under complex environments, a feature fusion-based deep convolutional neural network method FF-CNN (Feature Fusion of Convolutional Neural Network) was proposed in this paper. The proposed FF-CNN mapped the crowd image to its crowd density map, and then obtained the head count by integration. The geometry adaptive kernels were adopted to generate high-quality density maps which were used as ground truths for network training. The deconvolution technique was used to achieve the fusion of high-level and low-level features to get richer features, and two loss functions, i.e., density map loss and absolute count loss, were used for joint optimization. In order to increase the sample diversity, the original images were cropped with a random cropping method for each iteration. The experimental results of FF-CNN on the ShanghaiTech public dataset showed that the fusion of low-level and high-level features can extract richer features to improve the precision of density map estimation, and further improve the accuracy of crowd counting.

scholarly journals Shallow Feature Based Dense Attention Network for Crowd Counting

2020 ◽  
Vol 34 (07) ◽  
pp. 11765-11772 ◽  
Author(s):  
Yunqi Miao ◽  
Zijia Lin ◽  
Guiguang Ding ◽  
Jungong Han
Keyword(s):  
Absolute Error ◽  
Image Features ◽  
Feature Maps ◽  
Attention Network ◽  
Crowd Counting ◽  
Attention Model ◽  
Crowd Density ◽  
Benchmark Datasets ◽  
Feature Based ◽  
The Impact

While the performance of crowd counting via deep learning has been improved dramatically in the recent years, it remains an ingrained problem due to cluttered backgrounds and varying scales of people within an image. In this paper, we propose a Shallow feature based Dense Attention Network (SDANet) for crowd counting from still images, which diminishes the impact of backgrounds via involving a shallow feature based attention model, and meanwhile, captures multi-scale information via densely connecting hierarchical image features. Specifically, inspired by the observation that backgrounds and human crowds generally have noticeably different responses in shallow features, we decide to build our attention model upon shallow-feature maps, which results in accurate background-pixel detection. Moreover, considering that the most representative features of people across different scales can appear in different layers of a feature extraction network, to better keep them all, we propose to densely connect hierarchical image features of different layers and subsequently encode them for estimating crowd density. Experimental results on three benchmark datasets clearly demonstrate the superiority of SDANet when dealing with different scenarios. Particularly, on the challenging UCF_CC_50 dataset, our method outperforms other existing methods by a large margin, as is evident from a remarkable 11.9% Mean Absolute Error (MAE) drop of our SDANet.

scholarly journals Linear Attribute Projection and Performance Assessment for Signifying the Absenteeism at Work using Machine Learning

2019 ◽  
Vol 8 (3) ◽  
pp. 1262-1267
Keyword(s):  
Machine Learning ◽  
Performance Metrics ◽  
Mean Squared Error ◽  
Working Hours ◽  
Absolute Error ◽  
Machine Learning Algorithms ◽  
Working Environment ◽  
Experimental Result ◽  
Technological Advancement ◽  
Development Environment

In recent times, with the technological advancement the industry and organization are transforming all their inflow and outflow operations into digital identity. At the outset, the name of the organization is also in the hands of the employee. One of the major needs of the employee in the working environment is to avail leave or vacation based on their family circumstances. Based on the health condition and need of the employee, the organization must extend their leave for the satisfaction of the employee. The performance of the employee is also predicted based on the working days in the organization. With this view, this paper attempts to analyze the performance of the employee and the number of working hours by using machine learning algorithms. The Absenteeism at work dataset from UCI machine learning Repository is used for prediction analysis. The prediction of absent hours is achieved in three ways. Firstly, the correlation between each of the dataset attributes are found and depicted as a histogram. Secondly, the top most high correlated features are identified which are directly fitted to the regression models like Linear regression, SRD regression, RANSAC regression, Ridge regression, Huber regression, ARD Regression, Passive Aggressive Regression and Theilson Regression. Thirdly, the Performance analysis is done by analyzing the performance metrics like Mean Squared Error, Mean Absolute Error, R2 Score, Explained Variance Score and Mean Squared Log Error. The implementation is done by python in Anaconda Spyder Navigator Integrated Development Environment. Experimental Result shows that the Passive Aggressive Regression have achieved the effective prediction of number of absent hours with minimum MSE of 0.04, MAE of 0.16, EVS of 0.03, MSLE of 0.32 and reasonable R2 Score of 0.89.

scholarly journals Crowd Counting Based on Multiresolution Density Map and Parallel Dilated Convolution

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Jingfan Tang ◽  
Meijia Zhou ◽  
Pengfei Li ◽  
Min Zhang ◽  
Ming Jiang
Keyword(s):  
Receptive Field ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Crowd Counting ◽  
Dilated Convolution ◽  
Perspective Distortion ◽  
Contact Information ◽  
Crowd Density ◽  
Density Maps ◽  
Density Map

The current crowd counting tasks rely on a fully convolutional network to generate a density map that can achieve good performance. However, due to the crowd occlusion and perspective distortion in the image, the directly generated density map usually neglects the scale information and spatial contact information. To solve it, we proposed MDPDNet (Multiresolution Density maps and Parallel Dilated convolutions’ Network) to reduce the influence of occlusion and distortion on crowd estimation. This network is composed of two modules: (1) the parallel dilated convolution module (PDM) that combines three dilated convolutions in parallel to obtain the deep features on the larger receptive field with fewer parameters while reducing the loss of multiscale information; (2) the multiresolution density map module (MDM) that contains three-branch networks for extracting spatial contact information on three different low-resolution density maps as the feature input of the final crowd density map. Experiments show that MDPDNet achieved excellent results on three mainstream datasets (ShanghaiTech, UCF_CC_50, and UCF-QNRF).

Review of CBIR Related with Low Level and High Level Features

2016 ◽  
Vol 7 (1) ◽  
pp. 27-40 ◽  
Author(s):  
Tamil Kodi ◽  
G. Rosline Nesa Kumari ◽  
S. Maruthu Perumal
Keyword(s):  
Image Retrieval ◽  
User Interaction ◽  
Standard Analysis ◽  
Query Image ◽  
Low Level ◽  
Comprehensive Comparison ◽  
High Level ◽  
High Level Feature ◽  
Good Manner

The method of retrieving pictures from the massive image info is termed as content based mostly image retrieval (CBIR). CBIR is that the standard analysis space of interest. CBIR paves the approach of user interaction with giant info by satisfying their queries within the sort of pictures. This paper discusses the recital of a CBIR system that is in and of itself repressed by the options adopted to symbolize the pictures within the record and conjointly study the approaches of a spread of ways that deals with the extraction of options supported low and high level options of images with the query image provided. The most contribution of this work could be a comprehensive comparison between the low level and high level feature approaches to CBIR.To retrieve the pictures in a good manner this paper provides associate platform for victimization the ways which can able to specialize in each low level and high level options and created clarification regarding high level options will retrieve images a lot of relevant to the query image provided.

Affective emotion classification using feature vector of image based on visual concepts

2020 ◽  
pp. 002072092093683
Author(s):  
D Tamil Priya ◽  
J Divya Udayan
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Recognition Performance ◽  
Learning Model ◽  
Experimental Result ◽  
Emotion Classification ◽  
Low Level ◽  
Visual Concepts ◽  
Deep Learning Network ◽  
High Level

Nowadays, deep learning technique becomes the most popular fast-growing machine learning method in an Artificial Neural Network. The Convolution Neural Network (CNN) is one of the deep learning architecture that has been applied in the field of image analysis and image classification. In this paper, we proposed a novel emotion learning model with a deep learning network. The aim of the learning model is to reduce the affective gap, that extracts the objects and background features of an image semantically, such as high-level and low-level features. These extracted features accompanied with few others and it is more effective in emotion prediction model based on visual concepts of image, that leads to better emotion recognition performance. For training and testing, the experiment is conducted on IAPS (International Affective Picture System) dataset, the Artistic Photos, and the Emotion-Image dataset. An experimental result shows that the proposed model combines visual-content and low-level features of the image that provides promising results for Affective Emotion Classification task.

scholarly journals Predictive modeling of COVID-19 New Confirmed Cases in Algeria using Artificial Neural Network

2021 ◽  
Author(s):  
Messaoud Djeddou ◽  
Ibrahim A Hameed ◽  
Aouatef Hellal ◽  
Abolfazel Nejatian
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Mean Squared Error ◽  
Pearson Correlation ◽  
Absolute Error ◽  
Taylor Diagram ◽  
Ann Models ◽  
Artificial Neural ◽  
Predicted Values ◽  
High Level

This study investigates the potential of a simple artificial neural network for the prediction of COVID-19 New Confirmed Cases in Algeria (CNCC). Four different ANN models were built (GRNN, RBFNN, ELM, and MLP). The performance of the predictive models is evaluated based on four numerical parameters, namely root mean squared error (RMSE), mean absolute error (MAE), Nash-Sutcliffe efficiency (NSE), and Pearson correlation coefficient (R). Taylor diagram was also used to examine the similarities and differences between the observed and predicted values obtained from the proposed models. The results showed the potential of the multi-layer perceptron neural network (MLPNN) which exhibited a high level of accuracy in comparison to the other models.

Teknik Data Mining Dalam Clustering Produksi Susu Segar Di Indonesia Dengan Algoritma K-Means

2019 ◽  
Vol 1 (1) ◽  
pp. 31-39
Author(s):  
Ilham Safitra Damanik ◽  
Sundari Retno Andani ◽  
Dedi Sehendro
Keyword(s):  
Data Mining ◽  
Milk Production ◽  
Clustering Algorithm ◽  
Clustering Method ◽  
Data Mining Techniques ◽  
Low Level ◽  
Fresh Milk ◽  
Nutritional Needs ◽  
High Level ◽  
Level Cluster

Milk is an important intake to meet nutritional needs. Both consumed by children, and adults. Indonesia has many producers of fresh milk, but it is not sufficient for national milk needs. Data mining is a science in the field of computers that is widely used in research. one of the data mining techniques is Clustering. Clustering is a method by grouping data. The Clustering method will be more optimal if you use a lot of data. Data to be used are provincial data in Indonesia from 2000 to 2017 obtained from the Central Statistics Agency. The results of this study are in Clusters based on 2 milk-producing groups, namely high-dairy producers and low-milk producing regions. From 27 data on fresh milk production in Indonesia, two high-level provinces can be obtained, namely: West Java and East Java. And 25 others were added in 7 provinces which did not follow the calculation of the K-Means Clustering Algorithm, including in the low level cluster.

Determinants of Abuse of the Bodies of the Dead

2019 ◽  
pp. 71-77
Author(s):  
Margarita Khomyakova
Keyword(s):  
Low Income ◽  
Criminal Code ◽  
Value Judgments ◽  
Legal Norms ◽  
Low Level ◽  
Medical Institutions ◽  
Specific Object ◽  
The Subject ◽  
The Dead ◽  
High Level

The author analyzes definitions of the concepts of determinants of crime given by various scientists and offers her definition. In this study, determinants of crime are understood as a set of its causes, the circumstances that contribute committing them, as well as the dynamics of crime. It is noted that the Russian legislator in Article 244 of the Criminal Code defines the object of this criminal assault as public morality. Despite the use of evaluative concepts both in the disposition of this norm and in determining the specific object of a given crime, the position of criminologists is unequivocal: crimes of this kind are immoral and are in irreconcilable conflict with generally accepted moral and legal norms. In the paper, some views are considered with regard to making value judgments which could hardly apply to legal norms. According to the author, the reasons for abuse of the bodies of the dead include economic problems of the subject of a crime, a low level of culture and legal awareness; this list is not exhaustive. The main circumstances that contribute committing abuse of the bodies of the dead and their burial places are the following: low income and unemployment, low level of criminological prevention, poor maintenance and protection of medical institutions and cemeteries due to underperformance of state and municipal bodies. The list of circumstances is also open-ended. Due to some factors, including a high level of latency, it is not possible to reflect the dynamics of such crimes objectively. At the same time, identification of the determinants of abuse of the bodies of the dead will reduce the number of such crimes.

Sign in / Sign up

Export Citation Format

Share Document