Human Complex Activity Recognition With Sensor Data Using Multiple Features

Huan, Ruohong; Jiang, Chengxi; Ge, Luoqi; Shu, Jia; Zhan, Ziwei; Chen, Peng; Chi, Kaikai; Liang, Ronghua

doi:10.1109/jsen.2021.3130913

Cited by 18 publications

(17 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average accuracy of R-CNN on the Pascal VOC 2012 test set reached 53.3%, and the algorithm has since inspired many deep learning-based target detection algorithms. Depending on the data source, action classification methods can be further classified into RGB video-based action classification, depth image-based action classification, and skeletal data-based action classification [ 8 ]. Compared with RGB video and depth images, skeletal data is compact, smaller, and easier to extract concise motion features, so motion classification algorithms based on 3D skeletal data are faster and more efficient.…”

Section: Related Workmentioning

confidence: 99%

Behaviour Detection and Recognition of College Basketball Players Based on Multimodal Sequence Matching and Deep Neural Networks

Zhang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

This study fuses multimodal sequence matching with a deep neural network algorithm for college basketball player behavior detection and recognition to conduct in-depth research and analysis, analyzing the basic components of basketball technical action videos by studying the practical application of technical actions in professional games and teaching videos from self-published authors of short video platforms. The characteristics of the dataset are also analyzed through literature research related to the basketball action dataset. On the established basketball technical action dataset, combined with the SSD target detection algorithm, the video images with cropping of human motion regions to reduce the size of image frames, generating a basketball technical action dataset based on cropped frames, reduces the amount of network training and improves the efficiency of subsequent action recognition training. In this study, by analyzing the characteristics of basic camera motion, a univariate global motion model is proposed to introduce a quadratic term to accurately express the shaking transformation, while the horizontal and vertical motion are independently represented to reduce the model complexity. Comparative experimental results show that the proposed model achieves a good balance between complexity and accuracy of global motion representation. It is suitable for global motion modeling in behavior recognition applications, laying the foundation for global and local motion estimation. On this basis, the visual feature change pattern of the key area of the scene (basketball area) is combined with the group behavior recognition based on motion patterns and the success-failure classification based on key visual information to achieve basketball semantic event recognition. The experimental results at NCAA show that the fusion of global and local motion patterns can effectively improve group behavior recognition performance. The semantic event recognition algorithm combining motion patterns and video key visual information achieves the best performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Behaviour Detection and Recognition of College Basketball Players Based on Multimodal Sequence Matching and Deep Neural Networks

Zhang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The authors reported that their approach outperformed other feature sets and classifiers in terms of accuracy. Huan et al [9] tackle the problem of complex human activity recognition. They proposed a framework to extract multilayer features from accelerometer, gyroscope and magnetometer signals.…”

Section: Related Workmentioning

confidence: 99%

“…These wearable sensors can be Inertial Measurement Units (IMU), pressure sensors and global positioning system (GPS) sensors [2]. Applications that can be done with sensor-based approaches are fitness and motion tracking, daily activity monitoring, virtual reality and medical rehabilitation [9]. Sensor based approaches can be considered as two types: Multi sensor based and single sensor-based systems.…”

Section: Introductionmentioning

confidence: 99%

“…Human activities can be considered as a combination of simple and complex activities [9]. Simple activities are defined by actions that repeats itself and possess a single body pose.…”

Section: Introductionmentioning

confidence: 99%

“…For example, eating a meal can be considered as a complex activity because it involves sitting and can contain several different hand motions while eating a meal. Example complex activities are cleaning, cooking, writing and eating [9]. These activities usually have high level semantic characteristics that truly represent daily life of the user.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Complex Human Activity Recognition Using a Local Weighted Approach

Asuroglu

2022

IEEE Access

View full text Add to dashboard Cite

Due to the life expectancy increase, there will be a workforce shortage in elderly care sector in forthcoming years. Ambient Assisted Living (AAL) systems can cope with this issue. A subset of AAL, Human activity recognition (HAR) provides an efficient way to tackle this issue. It can help with evaluating general health and welfare of elderly by automatically tracking their activities. Lifelogging and home diary applications will reduce the load on physicians and caregivers. On the other hand, complex activities play a vital role as they have high level semantic characteristics that truly represent daily life of the user. The main objective is to track these high-level semantic motions with low-cost single sensor systems with efficient machine learning frameworks. To achieve this objective, a framework is proposed to predict complex human activities from a single sensor using a machine learning approach. Time and frequency features are extracted from PAAL ADL Accelerometry Dataset and fed to Locally Weighted Random Forest (LWRF) machine learning algorithm. This algorithm is a hybrid structure that utilizes local weighting by introducing neighboring samples on Random Forest tree building phases. Proposed approach achieved 91% accuracy for HAR and 91.3% for gender recognition, outperforming other machine learning algorithms and previous study on the same dataset. This is the first study that utilize a local weighted approach for accelerometer signal domain. For prospective application, proposed framework can be embedded in lifelogging and home diary applications in home environments to track mental status of elderlies.

show abstract