• Journal of KIISE
• /
• v.42 no.1
• /
• pp.138-143
• /
• 2015

In this paper we develop a novel human action recognition system based on communication between an ear-mounted Bluetooth camera and an action recognition server to aid scene recognition for the blind. First, if the blind capture an image of a specific location using the ear-mounted camera, the captured image is transmitted to the recognition server using a smartphone that is synchronized with the camera. The recognition server sequentially performs human detection, object detection and action recognition by analyzing human poses. The recognized action information is retransmitted to the smartphone and the user can hear the action information through the text-to-speech (TTS). Experimental results using the proposed system showed a 60.7% action recognition performance on the test data captured in indoor and outdoor environments.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.281-290
• /
• 2015

Human action recognition from a video scene has remained a challenging problem in the area of computer vision and pattern recognition. The development of the low-cost RGB depth camera (RGB-D) allows new opportunities to solve the problem of human action recognition. In this paper, we present a comprehensive review of recent approaches to human action recognition based on depth maps, skeleton joints, and other hybrid approaches. In particular, we focus on the advantages and limitations of the existing approaches and on future directions.

• Journal of Broadcast Engineering
• /
• v.25 no.3
• /
• pp.374-385
• /
• 2020

In this paper, we propose a preprocessing technique to solve the problems of action recognition with Equirectangular Projection (ERP) video. The preprocessing technique proposed in this paper assumes the person object as the subject of action, that is, the Object of Interest (OOI), and the surrounding area of the OOI as the ROI. The preprocessing technique consists of three modules. I) Recognize person object in the image with object recognition model. II) Create a saliency map from the input image. III) Select subject of action using recognized person object and saliency map. The subject boundary box of the selected action is input to the action recognition model in order to improve the action recognition performance. When comparing the performance of the proposed preprocessing method to the action recognition model and the performance of the original ERP image input method, the performance is improved up to 99.6%, and the action is obtained when only the OOI is detected. It can also see the effects of related video summaries.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.10
• /
• pp.2632-2649
• /
• 2012

Most approaches to human action recognition is limited due to the use of simple action datasets under controlled environments or focus on excessively localized features without sufficiently exploring the spatio-temporal information. This paper proposed a framework for recognizing realistic human actions. Specifically, a new action representation is proposed based on computing a rich set of descriptors from keypoint trajectories. To obtain efficient and compact representations for actions, we develop a feature fusion method to combine spatial-temporal local motion descriptors by the movement of the camera which is detected by the distribution of spatio-temporal interest points in the clips. A new topic model called Markov Semantic Model is proposed for semantic feature selection which relies on the different kinds of dependencies between words produced by "syntactic " and "semantic" constraints. The informative features are selected collaboratively based on the different types of dependencies between words produced by short range and long range constraints. Building on the nonlinear SVMs, we validate this proposed hierarchical framework on several realistic action datasets.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.977-985
• /
• 2020

Aiming at the problem of complex feature extraction and low accuracy in human action recognition, this paper proposed a network structure combining batch normalization algorithm with GoogLeNet network model. Applying Batch Normalization idea in the field of image classification to action recognition field, it improved the algorithm by normalizing the network input training sample by mini-batch. For convolutional network, RGB image was the spatial input, and stacked optical flows was the temporal input. Then, it fused the spatio-temporal networks to get the final action recognition result. It trained and evaluated the architecture on the standard video actions benchmarks of UCF101 and HMDB51, which achieved the accuracy of 93.42% and 67.82%. The results show that the improved convolutional neural network has a significant improvement in improving the recognition rate and has obvious advantages in action recognition.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1851-1863
• /
• 2015

– In the paper, to handle the problem of traditional bag-of-features model ignoring the spatial relationship of local features in human action recognition, we proposed a Multiscale Spatial Position Coding under Locality Constraint method. Specifically, to describe this spatial relationship, we proposed a mixed feature combining motion feature and multi-spatial-scale configuration. To utilize temporal information between features, sub spatial-temporal-volumes are built. Next, the pooled features of sub-STVs are obtained via max-pooling method. In classification stage, the Locality-Constrained Group Sparse Representation is adopted to utilize the intrinsic group information of the sub-STV features. The experimental results on the KTH, Weizmann, and UCF sports datasets show that our action recognition system outperforms the classical local ST feature-based recognition systems published recently.

• Journal of Korea Multimedia Society
• /
• v.21 no.4
• /
• pp.478-484
• /
• 2018

The choice of the motion features influences the result of the human action recognition method directly. Many factors often influence the single feature differently, such as appearance of the human body, environment and video camera. So the accuracy of action recognition is restricted. On the bases of studying the representation and recognition of human actions, and giving fully consideration to the advantages and disadvantages of different features, the Dense Trajectories(DT) algorithm is a very classic algorithm in the field of behavior recognition feature extraction, but there are some defects in the use of optical flow images. In this paper, we will use the improved Dense Trajectories(iDT) algorithm to optimize and extract the optical flow features in the movement of human action, then we will combined with Support Vector Machine methods to identify human behavior, and use the image in the KTH database for training and testing.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.3
• /
• pp.209-218
• /
• 2013

Early researches in human action recognition have focused on tracking and classifying articulated body motions. Such methods required accurate segmentation of body parts, which is a sticky task, particularly under realistic imaging conditions. Recent trends of work have become popular towards the use of more and low-level appearance features such as spatio-temporal interest points. Given the great progress in pose estimation over the past few years, redefined views about pose-based approach are needed. This paper addresses the issues of whether it is sufficient to train a classifier only on low-level appearance features in appearance approach and proposes effective pose-based approach with pose estimation for emotional action recognition. In order for these questions to be solved, we compare the performance of pose-based, appearance-based and its combination-based features respectively with respect to scenario of various emotional action recognition. The experiment results show that pose-based features outperform low-level appearance-based approach of features, even when heavily spoiled by noise, suggesting that pose-based approach with pose estimation is beneficial for the emotional action recognition.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.2
• /
• pp.739-748
• /
• 2014

In this paper, we propose pyramid appearance and global structure action descriptors on both RGB and depth motion history images and a model-free method for human action recognition. In proposed algorithm, we firstly construct motion history image for both RGB and depth channels, at the same time, depth information is employed to filter RGB information, after that, different action descriptors are extracted from depth and RGB MHIs to represent these actions, and then multimodality information collaborative representation and recognition model, in which multi-modality information are put into object function naturally, and information fusion and action recognition also be done together, is proposed to classify human actions. To demonstrate the superiority of the proposed method, we evaluate it on MSR Action3D and DHA datasets, the well-known dataset for human action recognition. Large scale experiment shows our descriptors are robust, stable and efficient, when comparing with the-state-of-the-art algorithms, the performances of our descriptors are better than that of them, further, the performance of combined descriptors is much better than just using sole descriptor. What is more, our proposed model outperforms the state-of-the-art methods on both MSR Action3D and DHA datasets.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.878-879
• /
• 2021

Most state-of-the-art CNNs for action recognition are based on a two-stream architecture: RGB frames stream represents the appearance and the optical flow stream interprets the motion of action. However, the cost of optical flow computation is very high and then it increases action recognition latency. We introduce a design strategy for action recognition inspired by a two-stream network and teacher-student architecture. There are two sub-networks in our neural networks, the optical flow sub-network as a teacher and the RGB frames sub-network as a student. In the training stage, we distill the feature from the teacher as a baseline to train student sub-network. In the test stage, we only use the student so that the latency reduces without computing optical flow. Our experiments show that its advantages over two-stream architecture in both speed and performance.