Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Zizhu Fan et al.
Summary: This paper comprehensively reviews the recent research advancement on crowd counting and density estimation, including background introduction, summary of traditional methods, review of methods based on convolutional neural network models, reporting and discussion of experimental results, and outlook on future directions.
Article
Engineering, Civil
Rongyong Zhao et al.
Summary: This paper proposes a novel model for crowd stability analysis using images from a real-time video surveillance system. By enhancing the accuracy of human head recognition for crowd counting and density estimation, a four-column convolutional neural network (4C-CNN) is developed. This model calculates crowd density in different areas with image rectification against perspective distortion, and utilizes a stability criterion for quantitative computation dynamically. Additionally, experiments demonstrate that this improved CNN model outperforms typical multi-column CNN models for crowd counting, and the effectiveness of the crowd stability analysis model is validated at Shanghai Hongqiao Railway Station.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Chemistry, Multidisciplinary
Fadwa Alrowais et al.
Summary: This paper proposes a Metaheuristics with Deep Transfer Learning Enabled Intelligent Crowd Density Detection and Classification (MDTL-ICDDC) model for video surveillance systems. The MDTL-ICDDC model primarily leverages a Salp Swarm Algorithm (SSA) for feature extraction, a weighted extreme learning machine (WELM) for crowd density and classification, and the krill swarm algorithm (KSA) for parameter optimization. Experimental results show that the MDTL-ICDDC system outperforms other models in terms of performance.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Shuo Wang et al.
Summary: Crowd stampedes and incidents pose critical threats to public security. Real-time crowd density estimation can help monitor crowd movements and support timely evacuation strategies. This study proposes a lightweight Convolutional Neural Networks (CNN) model to enhance the performance of the crowd monitoring system through algorithm optimization.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Weiheng Liu et al.
Summary: This research proposes a method that combines surveillance video streams and transportation schedule information to predict future crowd density in transportation buildings. By utilizing temporal convolution layers and pooling techniques, the method is able to extract effective prediction features from dual-modal information, leading to more accurate prediction results.
2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
(2022)
Proceedings Paper
Computer Science, Information Systems
Gurkan Solmaz et al.
Summary: This paper presents a new adaptive machine learning system, CountMeIn, which addresses the problem of crowd estimation using polynomial regression and neural networks. The system maintains high accuracy for a longer duration without the need for cameras. Experimental results show that CountMeIn achieves significant error reductions compared to state-of-the-art methods in both minutely and hourly crowd estimations.
2022 IEEE INTERNATIONAL CONFERENCE ON PERVASIVE COMPUTING AND COMMUNICATIONS (PERCOM)
(2022)
Article
Computer Science, Information Systems
Adal Alashban et al.
Summary: Crowd density estimation is an important topic in computer vision with widespread applications. This paper proposes a Single-Convolutional Neural Network with Three Layers (S-CNN3) model for crowd management and conducts a comparative study on density counting. The proposed model achieves high effectiveness and efficiency in crowd density estimation.
Article
Computer Science, Hardware & Architecture
Xiuwen Fu et al.
Summary: The paper introduces a model called REST, which constructs a scale-free topology through a two-stage process to address the lack of fault tolerance and energy efficiency in wireless sensor networks.
Article
Computer Science, Interdisciplinary Applications
Alem Fitwi et al.
Summary: This paper introduces a novel solution called E-SEC, which utilizes a single edge camera to estimate the interpersonal distance between individuals, area occupied by a dynamic crowd, and density. By combining human detection technology and algorithms, E-SEC can monitor social distancing of a crowd in real-time, as well as dynamically determine the size of the area occupied by the crowd and the crowd density.
Article
Computer Science, Information Systems
David Garcia-Retuerta et al.
Summary: A smart city utilizes innovative technologies to improve city operations and enhance the quality of life for its citizens by optimizing resources through data collection, management, and analysis, as well as leveraging IoT and AI for efficient city management.
Article
Robotics
Hiroaki Minoura et al.
Summary: This work introduces a new forecasting task called crowd density forecasting, utilizing patch-based density forecasting networks to directly predict crowd density maps of future frames. Experimental results demonstrate the effectiveness of this method in dealing with diverse and complex crowd density dynamics observed when input videos involve a variable number of crowds moving independently.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Computer Science, Interdisciplinary Applications
Laith Abualigah et al.
Summary: This paper introduces a novel population-based optimization method, AO, inspired by the behaviors of eagles during hunting. Through a series of experiments, the superior performance of AO in finding optimal solutions for various problems is demonstrated and compared with other meta-heuristic methods.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Engineering, Civil
Xinghao Ding et al.
Summary: Crowd counting is crucial in intelligent transportation systems, but challenges like occlusion, perspective distortion, and complex backgrounds make it difficult to achieve accuracy. This study introduces a novel CNN model and a new evaluation method for measuring density map accuracy, outperforming existing methods. Evaluation on cross-scene datasets shows promising performance of the proposed method.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Automation & Control Systems
Xiaoyong Tang et al.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2020)
Article
Computer Science, Hardware & Architecture
Xiuwen Fu et al.
Article
Medicine, Research & Experimental
Ferhat Ucar et al.
MEDICAL HYPOTHESES
(2020)
Article
Remote Sensing
Ali Almagbile
GEO-SPATIAL INFORMATION SCIENCE
(2019)
Review
Computer Science, Theory & Methods
G. Sreenu et al.
JOURNAL OF BIG DATA
(2019)
Article
Automation & Control Systems
Bingyin Zhou et al.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2018)
Article
Energy & Fuels
Huiting Zheng et al.
Article
Physics, Multidisciplinary
Panchi Li et al.
INTERNATIONAL JOURNAL OF THEORETICAL PHYSICS
(2017)
