Crowd management becomes a global concern due to increased population in urban areas.Better management of pedestrians leads to improved use of public places.Behavior of pedestrian’s is a major factor of crowd managem...Crowd management becomes a global concern due to increased population in urban areas.Better management of pedestrians leads to improved use of public places.Behavior of pedestrian’s is a major factor of crowd management in public places.There are multiple applications available in this area but the challenge is open due to complexity of crowd and depends on the environment.In this paper,we have proposed a new method for pedestrian’s behavior detection.Kalman filter has been used to detect pedestrian’s usingmovement based approach.Next,we have performed occlusion detection and removal using region shrinking method to isolate occluded humans.Human verification is performed on each human silhouette and wavelet analysis and particle gradient motion are extracted for each silhouettes.Gray Wolf Optimizer(GWO)has been utilized to optimize feature set and then behavior classification has been performed using the Extreme Gradient(XG)Boost classifier.Performance has been evaluated using pedestrian’s data from avenue and UBI-Fight datasets,where both have different environment.The mean achieved accuracies are 91.3%and 85.14%over the Avenue and UBI-Fight datasets,respectively.These results are more accurate as compared to other existing methods.展开更多
With the dramatic increase in video surveillance applications and public safety measures,the need for an accurate and effective system for abnormal/sus-picious activity classification also increases.Although it has mul...With the dramatic increase in video surveillance applications and public safety measures,the need for an accurate and effective system for abnormal/sus-picious activity classification also increases.Although it has multiple applications,the problem is very challenging.In this paper,a novel approach for detecting nor-mal/abnormal activity has been proposed.We used the Gaussian Mixture Model(GMM)and Kalmanfilter to detect and track the objects,respectively.After that,we performed shadow removal to segment an object and its shadow.After object segmentation we performed occlusion detection method to detect occlusion between multiple human silhouettes and we implemented a novel method for region shrinking to isolate occluded humans.Fuzzy c-mean is utilized to verify human silhouettes and motion based features including velocity and opticalflow are extracted for each identified silhouettes.Gray Wolf Optimizer(GWO)is used to optimize feature set followed by abnormal event classification that is performed using the XG-Boost classifier.This system is applicable in any surveillance appli-cation used for event detection or anomaly detection.Performance of proposed system is evaluated using University of Minnesota(UMN)dataset and UBI(Uni-versity of Beira Interior)-Fight dataset,each having different type of anomaly.The mean accuracy for the UMN and UBI-Fight datasets is 90.14%and 76.9%respec-tively.These results are more accurate as compared to other existing methods.展开更多
Our lives are significantly impacted by social media platforms such as Facebook, Twitter, Instagram, LinkedIn, and others. People are actively participating in it the world over. However, it also has to deal with the ...Our lives are significantly impacted by social media platforms such as Facebook, Twitter, Instagram, LinkedIn, and others. People are actively participating in it the world over. However, it also has to deal with the issue of bogus profiles. False accounts are frequently created by humans, bots, or computers. They are used to disseminate rumors and engage in illicit activities like identity theft and phishing. So, in this project, the author’ll talk about a detection model that uses a variety of machine learning techniques to distinguish between fake and real Twitter profiles based on attributes like follower and friend counts, status updates, and more. The author used the dataset of Twitter profiles, separating real accounts into TFP and E13 and false accounts into INT, TWT, and FSF. Here, the author discusses LSTM, XG Boost, Random Forest, and Neural Networks. The key characteristics are chosen to assess a social media profile’s authenticity. Hyperparameters and the architecture are also covered. Finally, results are produced after training the models. The output is therefore 0 for genuine profiles and 1 for false profiles. When a phony profile is discovered, it can be disabled or destroyed so that cyber security problems can be prevented. Python and the necessary libraries, such as Sklearn, Numpy, and Pandas, are used for implementation. At the end of this study, the author will come to the conclusion that XG Boost is the best machine learning technique for finding fake profiles.展开更多
基金partially supported by the Taif University Researchers Supporting Project number(TURSP-2020/115),Taif University,Taif,Saudi Arabiasupported by the MSIT(Ministry of Science and ICT),Korea,under the ITRC(Information Technology Research Center)support program(IITP-2023-2018-0-01426)supervised by the IITP(Institute for Information&Communications Technology Planning&Evaluation).
文摘Crowd management becomes a global concern due to increased population in urban areas.Better management of pedestrians leads to improved use of public places.Behavior of pedestrian’s is a major factor of crowd management in public places.There are multiple applications available in this area but the challenge is open due to complexity of crowd and depends on the environment.In this paper,we have proposed a new method for pedestrian’s behavior detection.Kalman filter has been used to detect pedestrian’s usingmovement based approach.Next,we have performed occlusion detection and removal using region shrinking method to isolate occluded humans.Human verification is performed on each human silhouette and wavelet analysis and particle gradient motion are extracted for each silhouettes.Gray Wolf Optimizer(GWO)has been utilized to optimize feature set and then behavior classification has been performed using the Extreme Gradient(XG)Boost classifier.Performance has been evaluated using pedestrian’s data from avenue and UBI-Fight datasets,where both have different environment.The mean achieved accuracies are 91.3%and 85.14%over the Avenue and UBI-Fight datasets,respectively.These results are more accurate as compared to other existing methods.
基金The authors acknowledge the Deanship of Scientific Research at King Faisal University for the financial support under Nasher Track(Grant No.NA000239)this research was supported by a Grant(2021R1F1A1063634)of the Basic Science Research Program through the National Research Foundation(NRF)funded by the Ministry of Education,Republic of Korea.
文摘With the dramatic increase in video surveillance applications and public safety measures,the need for an accurate and effective system for abnormal/sus-picious activity classification also increases.Although it has multiple applications,the problem is very challenging.In this paper,a novel approach for detecting nor-mal/abnormal activity has been proposed.We used the Gaussian Mixture Model(GMM)and Kalmanfilter to detect and track the objects,respectively.After that,we performed shadow removal to segment an object and its shadow.After object segmentation we performed occlusion detection method to detect occlusion between multiple human silhouettes and we implemented a novel method for region shrinking to isolate occluded humans.Fuzzy c-mean is utilized to verify human silhouettes and motion based features including velocity and opticalflow are extracted for each identified silhouettes.Gray Wolf Optimizer(GWO)is used to optimize feature set followed by abnormal event classification that is performed using the XG-Boost classifier.This system is applicable in any surveillance appli-cation used for event detection or anomaly detection.Performance of proposed system is evaluated using University of Minnesota(UMN)dataset and UBI(Uni-versity of Beira Interior)-Fight dataset,each having different type of anomaly.The mean accuracy for the UMN and UBI-Fight datasets is 90.14%and 76.9%respec-tively.These results are more accurate as compared to other existing methods.
文摘以不同自然老化时间的红花种子为材料,采用X射线成像技术检测种子的饱满度,并测定种子发芽率;利用多光谱成像系统采集不同自然老化时间种子的inverse jet图像和不同光谱特征,再用XG-Boost模型进行验证。结果表明,随着自然老化时间的延长,红花种子发芽率显著降低,种子平均反射率与发芽率正相关;筛选出20多个光谱特征与发芽率相关,其中Reflectance Ratio Bands Mean贡献率最高。研究表明,基于光谱成像技术的不同自然老化时间红花种子活力检测研究,筛选出与种子活力相关联参数,实现了红花种子活力的快速无损检测。
文摘Our lives are significantly impacted by social media platforms such as Facebook, Twitter, Instagram, LinkedIn, and others. People are actively participating in it the world over. However, it also has to deal with the issue of bogus profiles. False accounts are frequently created by humans, bots, or computers. They are used to disseminate rumors and engage in illicit activities like identity theft and phishing. So, in this project, the author’ll talk about a detection model that uses a variety of machine learning techniques to distinguish between fake and real Twitter profiles based on attributes like follower and friend counts, status updates, and more. The author used the dataset of Twitter profiles, separating real accounts into TFP and E13 and false accounts into INT, TWT, and FSF. Here, the author discusses LSTM, XG Boost, Random Forest, and Neural Networks. The key characteristics are chosen to assess a social media profile’s authenticity. Hyperparameters and the architecture are also covered. Finally, results are produced after training the models. The output is therefore 0 for genuine profiles and 1 for false profiles. When a phony profile is discovered, it can be disabled or destroyed so that cyber security problems can be prevented. Python and the necessary libraries, such as Sklearn, Numpy, and Pandas, are used for implementation. At the end of this study, the author will come to the conclusion that XG Boost is the best machine learning technique for finding fake profiles.
