• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권5호
• /
• pp.1856-1869
• /
• 2015

This paper addresses the issues of 3D human activity detection, tracking and recognition from RGB-D video sequences using a feature structured framework. During human tracking and activity recognition, initially, dense depth images are captured using depth camera. In order to track human silhouettes, we considered spatial/temporal continuity, constraints of human motion information and compute centroids of each activity based on chain coding mechanism and centroids point extraction. In body skin joints features, we estimate human body skin color to identify human body parts (i.e., head, hands, and feet) likely to extract joint points information. These joints points are further processed as feature extraction process including distance position features and centroid distance features. Lastly, self-organized maps are used to recognize different activities. Experimental results demonstrate that the proposed method is reliable and efficient in recognizing human poses at different realistic scenes. The proposed system should be applicable to different consumer application systems such as healthcare system, video surveillance system and indoor monitoring systems which track and recognize different activities of multiple users.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권2호
• /
• pp.1118-1133
• /
• 2017

Computer vision-based human activity recognition (HAR) has become very famous these days due to its applications in various fields such as smart home healthcare for elderly people. A video-based activity recognition system basically has many goals such as to react based on people's behavior that allows the systems to proactively assist them with their tasks. A novel approach is proposed in this work for depth video based human activity recognition using joint-based motion features of depth body shapes and Deep Belief Network (DBN). From depth video, different body parts of human activities are segmented first by means of a trained random forest. The motion features representing the magnitude and direction of each joint in next frame are extracted. Finally, the features are applied for training a DBN to be used for recognition later. The proposed HAR approach showed superior performance over conventional approaches on private and public datasets, indicating a prominent approach for practical applications in smartly controlled environments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권3호
• /
• pp.1595-1613
• /
• 2017

The IR camera and laser-based IR projector provide an effective solution for real-time collection of moving targets in RGB-D videos. Different from the traditional RGB videos, the captured depth videos are not affected by the illumination variation. In this paper, we propose a novel feature extraction framework to describe human activities based on the above optical video capturing method, namely spatial-temporal texture features for 3D human activity recognition. Spatial-temporal texture feature with depth information is insensitive to illumination and occlusions, and efficient for fine-motion description. The framework of our proposed algorithm begins with video acquisition based on laser projection, video preprocessing with visual background extraction and obtains spatial-temporal key images. Then, the texture features encoded from key images are used to generate discriminative features for human activity information. The experimental results based on the different databases and practical scenarios demonstrate the effectiveness of our proposed algorithm for the large-scale data sets.

• 한국멀티미디어학회논문지
• /
• 제23권12호
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권3호
• /
• pp.1189-1204
• /
• 2018

Detecting and capturing 3D human structures from the intensity-based image sequences is an inherently arguable problem, which attracted attention of several researchers especially in real-time activity recognition (Real-AR). These Real-AR systems have been significantly enhanced by using depth intensity sensors that gives maximum information, in spite of the fact that conventional Real-AR systems are using RGB video sensors. This study proposed a depth-based routine-logging Real-AR system to identify the daily human activity routines and to make these surroundings an intelligent living space. Our real-time routine-logging Real-AR system is categorized into two categories. The data collection with the use of a depth camera, feature extraction based on joint information and training/recognition of each activity. In-addition, the recognition mechanism locates, and pinpoints the learned activities and induces routine-logs. The evaluation applied on the depth datasets (self-annotated and MSRAction3D datasets) demonstrated that proposed system can achieve better recognition rates and robust as compare to state-of-the-art methods. Our Real-AR should be feasibly accessible and permanently used in behavior monitoring applications, humanoid-robot systems and e-medical therapy systems.

• Journal of Electrical Engineering and Technology
• /
• 제11권6호
• /
• pp.1857-1862
• /
• 2016

Human activity recognition using depth information is an emerging and challenging technology in computer vision due to its considerable attention by many practical applications such as smart home/office system, personal health care and 3D video games. This paper presents a novel framework of 3D human body detection, tracking and recognition from depth video sequences using spatiotemporal features and modified HMM. To detect human silhouette, raw depth data is examined to extract human silhouette by considering spatial continuity and constraints of human motion information. While, frame differentiation is used to track human movements. Features extraction mechanism consists of spatial depth shape features and temporal joints features are used to improve classification performance. Both of these features are fused together to recognize different activities using the modified hidden Markov model (M-HMM). The proposed approach is evaluated on two challenging depth video datasets. Moreover, our system has significant abilities to handle subject's body parts rotation and body parts missing which provide major contributions in human activity recognition.

• ETRI Journal
• /
• 제33권4호
• /
• pp.569-579
• /
• 2011

This paper presents a novel approach for human activity recognition (HAR) using the joint angles from a 3D model of a human body. Unlike conventional approaches in which the joint angles are computed from inverse kinematic analysis of the optical marker positions captured with multiple cameras, our approach utilizes the body joint angles estimated directly from time-series activity images acquired with a single stereo camera by co-registering a 3D body model to the stereo information. The estimated joint-angle features are then mapped into codewords to generate discrete symbols for a hidden Markov model (HMM) of each activity. With these symbols, each activity is trained through the HMM, and later, all the trained HMMs are used for activity recognition. The performance of our joint-angle-based HAR has been compared to that of a conventional binary and depth silhouette-based HAR, producing significantly better results in the recognition rate, especially for the activities that are not discernible with the conventional approaches.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2767-2780
• /
• 2016

Video-based human-activity recognition has become increasingly popular due to the prominent corresponding applications in a variety of fields such as computer vision, image processing, smart-home healthcare, and human-computer interactions. The essential goals of a video-based activity-recognition system include the provision of behavior-based information to enable functionality that proactively assists a person with his/her tasks. The target of this work is the development of a novel approach for human-activity recognition, whereby human-body-joint features that are extracted from depth videos are used. From silhouette images taken at every depth, the direction and magnitude features are first obtained from each connected body-joint pair so that they can be augmented later with motion direction, as well as with the magnitude features of each joint in the next frame. A generalized discriminant analysis (GDA) is applied to make the spatiotemporal features more robust, followed by the feeding of the time-sequence features into a Hidden Markov Model (HMM) for the training of each activity. Lastly, all of the trained-activity HMMs are used for depth-video activity recognition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권2호
• /
• pp.800-816
• /
• 2018

In recent years, video surveillance research has been able to recognize various behaviors of pedestrians and analyze the overall situation of objects by combining image analysis technology and deep learning method. Human Activity Recognition (HAR), which is important issue in video surveillance research, is a field to detect abnormal behavior of pedestrians in CCTV environment. In order to recognize human behavior, it is necessary to detect the human in the image and to estimate the pose from the detected human. In this paper, we propose a novel approach for 2D Human Pose Estimation based on object detection using RGB-D information. By adding depth information to the RGB information that has some limitation in detecting object due to lack of topological information, we can improve the detecting accuracy. Subsequently, the rescaled region of the detected object is applied to ConVol.utional Pose Machines (CPM) which is a sequential prediction structure based on ConVol.utional Neural Network. We utilize CPM to generate belief maps to predict the positions of keypoint representing human body parts and to estimate human pose by detecting 14 key body points. From the experimental results, we can prove that the proposed method detects target objects robustly in occlusion. It is also possible to perform 2D human pose estimation by providing an accurately detected region as an input of the CPM. As for the future work, we will estimate the 3D human pose by mapping the 2D coordinate information on the body part onto the 3D space. Consequently, we can provide useful human behavior information in the research of HAR.

• ETRI Journal
• /
• 제44권2호
• /
• pp.286-299
• /
• 2022

Human activity recognition in real time is a challenging task. Recently, a plethora of studies has been proposed using deep learning architectures. The implementation of these architectures requires the high computing power of the machine and a massive database. However, handcrafted features-based machine learning models need less computing power and very accurate where features are effectively extracted. In this study, we propose a handcrafted model based on three-dimensional sequential skeleton data. The human body skeleton movement over a frame is computed through joint positions in a frame. The joints of these skeletal frames are projected into two-dimensional space, forming a "movement polygon." These polygons are further transformed into a one-dimensional space by computing amplitudes at different angles from the centroid of polygons. The feature vector is formed by the sampling of these amplitudes at different angles. The performance of the algorithm is evaluated using a support vector machine on four public datasets: MSR Action3D, Berkeley MHAD, TST Fall Detection, and NTU-RGB+D, and the highest accuracies achieved on these datasets are 94.13%, 93.34%, 95.7%, and 86.8%, respectively. These accuracies are compared with similar state-of-the-art and show superior performance.