Human activity recognition based on the combined SVM&amp;amp;HMM

Wu, Haitao; Pan, Wei; Xiong, Xingyu; Xu, Shuxiang

doi:10.1109/icinfa.2014.6932656

Cited by 49 publications

(34 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fernandez et al [5] presented an interactive room using Kinect sensors that could infer pointing direction from the user's elbowwrist vector. Wu et al [19] used machine learning to recognize different human activities in daily living environments based on inputs from Kinect sensors. Despite significant recent research and applications of depth cameras such as the Kinect, these devices are generally not suitable for smart lighting applications due to their cost and the privacy issues involved; a high-resolution range image allows significant information to be observed about an occupant.…”

Section: Related Workmentioning

confidence: 99%

Arrays of single pixel time-of-flight sensors for privacy preserving tracking and coarse pose estimation

Bhattacharya

Radke

2016

2016 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

We present a method for real-time person tracking and coarse pose estimation in a smart room using a sparse array of single pixel time-of flight (ToF) sensors mounted in the ceiling of the room. The single pixel sensors are relatively inexpensive compared to commercial ToF cameras and are privacy preserving in that they only return the range to a small set of hit points. The tracking algorithm includes higher level logic about how people move and interact in a room and makes estimates about the locations of people even in the absence of direct measurements. A maximum likelihood classifier based on features extracted from the time series of ToF measurements is used for robust pose classification into sitting, standing and walking states. We use both computer simulation and real-world experiments to show that the algorithms are capable of robust person tracking and pose estimation even with a sensor spacing of 60 cm (i.e., 1 sensor per ceiling tile).

show abstract

Section: Related Workmentioning

confidence: 99%

Arrays of single pixel time-of-flight sensors for privacy preserving tracking and coarse pose estimation

Bhattacharya

Radke

2016

2016 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

show abstract

“…The produced models are then used for human tracking [69]. Similarly [70,71] have used depth silhouette from depth camera images for motion tracking. Preprocessing in our model involves changing the size of the image and color normalization.…”

Section: Scene Recognitionmentioning

confidence: 99%

Application of Deep Convolutional Neural Networks and Smartphone Sensors for Indoor Localization

2019

View full text Add to dashboard Cite

Indoor localization systems are susceptible to higher errors and do not meet the current standards of indoor localization. Moreover, the performance of such approaches is limited by device dependence. The use of Wi-Fi makes the localization process vulnerable to dynamic factors and energy hungry. A multi-sensor fusion based indoor localization approach is proposed to overcome these issues. The proposed approach predicts pedestrians' current location with smartphone sensors data alone. The proposed approach aims at mitigating the impact of device dependency on the localization accuracy and lowering the localization error in the magnetic field based localization systems. We trained a deep learning based convolutional neural network to recognize the indoor scene which helps to lower the localization error. The recognized scene is used to identify a specific floor and narrow the search space. The database built of magnetic field patterns helps to lower the device dependence. A modified K nearest neighbor (mKNN) is presented to calculate the pedestrian's current location. The data from pedestrian dead reckoning further refines this location and an extended Kalman filter is implemented to this end. The performance of the proposed approach is tested with experiments on Galaxy S8 and LG G6 smartphones. The experimental results demonstrate that the proposed approach can achieve an accuracy of 1.04 m at 50 percent, regardless of the smartphone used for localization. The proposed mKNN outperforms K nearest neighbor approach, and mean, variance, and maximum errors are lower than those of KNN. Moreover, the proposed approach does not use Wi-Fi for localization and is more energy efficient than those of Wi-Fi based approaches. Experiments reveal that localization without scene recognition leads to higher errors.

show abstract

“…A Gaussian mixture-based HMM for human daily activity recognition study [52] obtained 84% recall accuracy, whereas using a depth video sensor for indoor activity recognition achieved 90.33% accuracy [53]. In [58], an 89.1% recognition rate was achieved by using a combined support vector machine (SVM) and HMM architecture. Other depth-based studies [55][56][57] reported recognition rates of 91.29%, 78.5%, and 83.9%.…”

Section: Comparison Of Different Classifiersmentioning

confidence: 99%

“…Other depth-based studies [55][56][57] reported recognition rates of 91.29%, 78.5%, and 83.9%. In [58], an 89.1% recognition rate was achieved by using a combined support vector machine (SVM) and HMM architecture. Recognition of human activity has become one of the most popular research topics in the machine learning field.…”

Section: Comparison Of Different Classifiersmentioning

confidence: 99%

Human activity recognition with analysis of angles between skeletal joints using a RGB‐depth sensor

et al. 2019

View full text Add to dashboard Cite

Human activity recognition (HAR) has become effective as a computer vision tool for video surveillance systems. In this paper, a novel biometric system that can detect human activities in 3D space is proposed. In order to implement HAR, joint angles obtained using an RGB-depth sensor are used as features. Because HAR is operated in the time domain, angle information is stored using the sliding kernel method.Haar-wavelet transform (HWT) is applied to preserve the information of the features before reducing the data dimension. Dimension reduction using an averaging algorithm is also applied to decrease the computational cost, which provides faster performance while maintaining high accuracy. Before the classification, a proposed thresholding method with inverse HWT is conducted to extract the final feature set.Finally, the K-nearest neighbor (k-NN) algorithm is used to recognize the activity with respect to the given data. The method compares favorably with the results using other machine learning algorithms. K E Y W O R D Sactivity recognition, dimension reduction, Haar-wavelet transform, K-nearest neighbour, RGB-D sensor | 89 İNCE Et al.

show abstract

Human activity recognition based on the combined SVM&HMM

Cited by 49 publications

References 9 publications

Arrays of single pixel time-of-flight sensors for privacy preserving tracking and coarse pose estimation

Arrays of single pixel time-of-flight sensors for privacy preserving tracking and coarse pose estimation

Application of Deep Convolutional Neural Networks and Smartphone Sensors for Indoor Localization

Human activity recognition with analysis of angles between skeletal joints using a RGB‐depth sensor

Contact Info

Product

Resources

About