• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3668-3684
• /
• 2021

Video action recognition is widely used in video surveillance, behavior detection, human-computer interaction, medically assisted diagnosis and motion analysis. However, video action recognition can be disturbed by many factors, such as background, illumination and so on. Two-stream convolutional neural network uses the video spatial and temporal models to train separately, and performs fusion at the output end. The multi segment Two-Stream convolutional neural network model trains temporal and spatial information from the video to extract their feature and fuse them, then determine the category of video action. Google Xception model and the transfer learning is adopted in this paper, and the Xception model which trained on ImageNet is used as the initial weight. It greatly overcomes the problem of model underfitting caused by insufficient video behavior dataset, and it can effectively reduce the influence of various factors in the video. This way also greatly improves the accuracy and reduces the training time. What's more, to make up for the shortage of dataset, the kinetics400 dataset was used for pre-training, which greatly improved the accuracy of the model. In this applied research, through continuous efforts, the expected goal is basically achieved, and according to the study and research, the design of the original dual-flow model is improved.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.399-410
• /
• 2021

Aiming at the problem that complex external variables in natural scenes have a greater impact on facial expression recognition results, a facial expression recognition method based on two-stream convolutional neural network is proposed. The model introduces exponentially enhanced shared input weights before each level of convolution input, and uses soft attention mechanism modules on the space-time features of the combination of static and dynamic streams. This enables the network to autonomously find areas that are more relevant to the expression category and pay more attention to these areas. Through these means, the information of irrelevant interference areas is suppressed. In order to solve the problem of poor local robustness caused by lighting and expression changes, this paper also performs lighting preprocessing with the lighting preprocessing chain algorithm to eliminate most of the lighting effects. Experimental results on AFEW6.0 and Multi-PIE datasets show that the recognition rates of this method are 95.05% and 61.40%, respectively, which are better than other comparison methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권5호
• /
• pp.2253-2272
• /
• 2018

We propose a deep learning method for multi-focus image fusion. Unlike most existing pixel-level fusion methods, either in spatial domain or in transform domain, our method directly learns an end-to-end fully convolutional two-stream network. The framework maps a pair of different focus images to a clean version, with a chain of convolutional layers, fusion layer and deconvolutional layers. Our deep fusion model has advantages of efficiency and robustness, yet demonstrates state-of-art fusion quality. We explore different parameter settings to achieve trade-offs between performance and speed. Moreover, the experiment results on our training dataset show that our network can achieve good performance with subjective visual perception and objective assessment metrics.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• 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.

• 한국차세대컴퓨팅학회논문지
• /
• 제14권6호
• /
• pp.66-74
• /
• 2018

최근 가상환경에서 몰입감을 늘리고 자유로운 상호작용을 제공하기 위한 손 제스처 인식에 대한 연구가 활발히 진행되고 있다. 그러나 기존의 연구는 특화된 센서나 장비를 요구하거나, 낮은 인식률을 보이고 있다. 본 논문은 정적 손 제스처와 동적 손 제스처 인식을 위해 카메라 이외의 별도의 센서나 장비 없이 딥러닝 기술을 사용한 손 제스처 인식 방법을 제안한다. 일련의 손 제스처 영상을 고주파 영상으로 변환한 후 손 제스처 RGB 영상들과 이에 대한 고주파 영상들 각각에 대해 덴스넷 3차원 합성곱 신경망을 통해 학습한다. 6개의 정적 손 제스처와 9개의 동적 손 제스처 인터페이스에 대해 실험한 결과 기존 덴스넷에 비해 4.6%의 성능이 향상된 평균 92.6%의 인식률을 보였다. 본 연구결과를 검증하기 위하여 3D 디펜스 게임을 구현한 결과 평균 34ms로 제스처 인식이 가능하여 가상현실 응용의 실시간 사용자 인터페이스로 사용가능함을 알 수 있었다.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제11권3호
• /
• pp.99-104
• /
• 2022

대부분 첨단 동작 인식 컨볼루션 네트워크는 RGB 스트림과 광학 흐름 스트림, 양 스트림 아키텍처를 기반으로 하고 있다. RGB 프레임 스트림은 모양 특성을 나타내고 광학 흐름 스트림은 동작 특성을 해석한다. 그러나 광학 흐름은 계산 비용이 매우 높기 때문에 동작 인식 시간에 지연을 초래한다. 이에 양 스트림 네트워크와 교사-학생 아키텍처에서 영감을 받아 행동 인식을 위한 새로운 네트워크 디자인을 개발하였다. 제안 신경망은 두 개의 하위 네트워크로 구성되어있다. 즉, 교사 역할을 하는 광학 흐름 하위 네트워크와 학생 역할을 하는 RGB 프레임 하위 네트워크를 연결하였다. 훈련 단계에서 광학 흐름의 특징을 추출하고 교사 서브 네트워크를 훈련시킨 다음 그 특징을 학생 서브 네트워크를 훈련시키기 위한 기준선으로 지정하여 학생 서브 네트워크에 전송한다. 테스트 단계에서는 광학 흐름을 계산하지 않고 대기 시간이 줄어들도록 학생 네트워크만 사용한다. 제안 네트워크는 실험을 통하여 정확도 면에서 일반 이중 스트림 아키텍처에 비해 높은 정확도를 보여주는 것을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권7호
• /
• pp.3599-3619
• /
• 2019

In human activity recognition system both static and motion information play crucial role for efficient and competitive results. Most of the existing methods are insufficient to extract video features and unable to investigate the level of contribution of both (Static and Motion) components. Our work highlights this problem and proposes Static-Motion fused features descriptor (SMFD), which intelligently leverages both static and motion features in the form of descriptor. First, static features are learned by two-stream 3D convolutional neural network. Second, trajectories are extracted by tracking key points and only those trajectories have been selected which are located in central region of the original video frame in order to to reduce irrelevant background trajectories as well computational complexity. Then, shape and motion descriptors are obtained along with key points by using SIFT flow. Next, cholesky transformation is introduced to fuse static and motion feature vectors to guarantee the equal contribution of all descriptors. Finally, Long Short-Term Memory (LSTM) network is utilized to discover long-term temporal dependencies and final prediction. To confirm the effectiveness of the proposed approach, extensive experiments have been conducted on three well-known datasets i.e. UCF101, HMDB51 and YouTube. Findings shows that the resulting recognition system is on par with state-of-the-art methods.