Human posture classification for intelligent visual surveillance systems

2008 ◽  
Author(s):  
Haroun Rababaah ◽  
Amir Shirkhodaie
Keyword(s):  
Visual Surveillance ◽  
Surveillance Systems ◽  
Human Posture ◽  
Posture Classification

Learning Algorithms for Anomaly Detection from Images

Biometrics ◽  
2017 ◽  
pp. 281-308
Author(s):  
Tarem Ahmed ◽  
Al-Sakib Khan Pathan ◽  
Supriyo Shafkat Ahmed
Keyword(s):  
Human Security ◽  
Visual Surveillance ◽  
Automated System ◽  
Surveillance Systems ◽  
Human Beings ◽  
Security Officer ◽  
Security Officers ◽  
Large Numbers ◽  
Quantitative Performance ◽  
Present World

Visual surveillance networks are installed in many sensitive places in the present world. Human security officers are required to continuously stare at large numbers of monitors simultaneously, and for lengths of time at a stretch. Constant alert vigilance for hours on end is difficult to maintain for human beings. It is thus important to remove the onus of detecting unwanted activity from the human security officer to an automated system. While many researchers have proposed solutions to this problem in the recent past, significant gaps remain in existing knowledge. Most existing algorithms involve high complexities. No quantitative performance analysis is provided by most researchers. Most commercial systems require expensive equipment. This work proposes algorithms where the complexities are independent of time, making the algorithms naturally suited to online use. In addition, the proposed methods have been shown to work with the simplest surveillance systems that may already be publicly deployed. Furthermore, direct quantitative performance comparisons are provided.

PCA–Based Human Posture Classification

2012 ◽  
Author(s):  
Nooritawati Md Tahir ◽  
Aini Hussain ◽  
Salina Abdul Samad ◽  
Hafizah Husain
Keyword(s):  
Neural Network ◽  
Principal Component Analysis ◽  
Artificial Neural Network ◽  
Multilayer Perceptron ◽  
Principal Component ◽  
Optimal Choice ◽  
Correct Classification ◽  
Human Posture ◽  
Posture Classification

Kertas kerja ini membentangkan suatu mekanisme untuk pengelasan susuk tubuh manusia berdasarkan kombinasi pelbagai jelmaan ruang eigen yang dinamakan sebagai eigenposture dan Multilayer Perceptron (MLP) sebagai pengelas. Penjelmaan komponen utama telah digunakan untuk menyari sifat pada bayang-bayang bentuk badan manusia. Gabungan sarian sifat ini digunakan untuk pengelasan susuk tubuh manusia sebagai berdiri atau sebaliknya berasaskan bentuk badan yang diperoleh selepas proses peruasan. Uji kaji telah dijalankan dengan mengubah bilangan vektor eigen yang dijadikan perwakilan untuk tujuan pengelasan. Keputusan yang diperoleh menunjukkan gabungan eigenposture kedua dan keempat memberi keputusan pengelasan bentuk badan manusia yang agak baik iaitu 98% dan boleh dijadikan sebagai pilihan optimal masukan bagi tujuan pengelasan menggunakan bilangan input minima. Kata kunci: Analisa komponen utama, vektor eigen, pengelasan, rangkaian neural tiruan, susuk tubuh manusia This paper outlines a mechanism for human body posture classification based on various combination of eigenspace transform, which we named as eigenposture, and using Multilayer Perceptron (MLP) as classifier. We apply principal component transformation to extract the features from human shape silhouettes. Combinations of the extracted features were used to classify the posture of standing and non-standing based on the human shape obtained from the segmentation process. We experiment by using various combinations of eigenvectors as input representations for classification purpose. Results showed that the second and fourth eigenpostures combination gives reasonably good result with 98% correct classification of human posture and can be adopted as the optimal choice of input for classification using a minimal combination. Key words: Principal component analysis (PCA), eigenvectors, classification, artificial neural network, human posture

ANALYSIS OF HUMAN WALKING TRAJECTORIES FOR SURVEILLANCE

2004 ◽  
Vol 01 (02) ◽  
pp. 169-189
Author(s):  
KA KEUNG LEE ◽  
YANGSHENG XU
Keyword(s):  
Real Time ◽  
Similarity Measure ◽  
Real Life ◽  
Visual Surveillance ◽  
Longest Common Subsequence ◽  
Human Walking ◽  
Support Vector ◽  
Surveillance Systems ◽  
Boundary Values ◽  
Variable Boundary

Surveillance of public places has become a worldwide concern in recent years. The ability to identify abnormal human behaviors in real-time is fundamental to the success of intelligent surveillance systems. The recognition of abnormal and suspicious human walking patterns is an important step towards the achievement of this goal. In this research, we develop an intelligent visual surveillance system that can classify normal and abnormal human walking trajectories in outdoor environments by learning from demonstration. The system takes into account both the local and global characteristics of the observed trajectories and is able to identify their normality in real-time. By utilizing support vector learning and a similarity measure based on hidden Markov models, the developed system has produced satisfactory results on real-life data during testing. Moreover, we utilize the approach of longest common subsequence (LCSS) in determining the similarity between different types of walking trajectories. In order to establish the position and speed boundaries required for the similarity measure, we compare the performance of a number of approaches, including fixed boundary values, variable boundary values, learning boundary by support vector regression, and learning boundary by cascade neural networks.

scholarly journals Improving TDWZ Correlation Noise Estimation: A Deep Learning based Approach

2020 ◽  
Author(s):  
Vũ Hữu Tiến ◽  
Thao Nguyen Thi Huong ◽  
San Vu Van ◽  
Xiem HoangVan
Keyword(s):  
Deep Learning ◽  
Activation Function ◽  
Vital Role ◽  
Visual Surveillance ◽  
Noise Model ◽  
Perceptual Quality ◽  
Surveillance Systems ◽  
Compression Performance ◽  
Laplacian Distribution ◽  
Correlation Noise

Transform domain Wyner-Ziv video coding (TDWZ) has shown its benefits in compressing video applications with limited resources such as visual surveillance systems, remote sensing and wireless sensor networks. In TDWZ, the correlation noise model (CNM) plays a vital role since it directly affects to the number of bits needed to send from the encoder and thus the overall TDWZ compression performance. To achieve CNM with high accurate for TDWZ, we propose in this paper a novel CNM estimation approach in which the CNM with Laplacian distribution is adaptively estimated based on a deep learning (DL) mechanism. The proposed DL based CNM includes two hidden layers and a linear activation function to adaptively update the Laplacian parameter. Experimental results showed that the proposed TDWZ codec significantly outperforms the relevant benchmarks, notably by around 35% bitrate saving when compared to the DISCOVER codec and around 22% bitrate saving when compared to the HEVC Intra benchmark while providing a similar perceptual quality.

Sign in / Sign up

Export Citation Format

Share Document