• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.6
• /
• pp.537-641
• /
• 2007

In this paper, motion analysis algorithm is presented for home surveillance of the aged who lives alone. For the first step, we acquire images from a camera. To enhance the image, we use median filtering and binarize it to reduce processing time. And then morphological operations are performed to remove small blobs and small holes. At the forth step, blobs are analysed to extracts tor foreground region. Then, motions are predicted from these images by using optical tlow technique, and the predicted motion data are refined by comparing our cardboard models so as to judge behavior pattern.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.7
• /
• pp.1325-1334
• /
• 2016

The video incident detection System is a probe for rapid detecting the walker, falling, stopped, backwards, smoke situation in tunnel. Recently, the importance is increases from the downtown double deck tunnel in great depth underground space[1], but the legal basis is weak and the vulnerable situation experimental data. So, In this paper, we introduce a long-term log data analysis information in the tunnenl video incident detection system installed and experimental results in order to verify the feasibility of apply to video incident detection system for the double deck tunnel. It is proposed a few things about derives the problem of existing video incident detection system, improvements and reflect attributes for double deck tunnel. The contents described in this paper will contribute to refine the prototype of video incident detection system will apply to future double deck multi-layer tunnels.

• Journal of Information Processing Systems
• /
• v.10 no.1
• /
• pp.1-22
• /
• 2014

Recent technological advances provide the opportunity to use large amounts of multimedia data from a multitude of sensors with different modalities (e.g., video, text) for the detection and characterization of criminal activity. Their integration can compensate for sensor and modality deficiencies by using data from other available sensors and modalities. However, building such an integrated system at the scale of neighborhood and cities is challenging due to the large amount of data to be considered and the need to ensure a short response time to potential criminal activity. In this paper, we present a system that enables multi-modal data collection at scale and automates the detection of events of interest for the surveillance and reconnaissance of criminal activity. The proposed system showcases novel analytical tools that fuse multimedia data streams to automatically detect and identify specific criminal events and activities. More specifically, the system detects and analyzes series of incidents (an incident is an occurrence or artifact relevant to a criminal activity extracted from a single media stream) in the spatiotemporal domain to extract events (actual instances of criminal events) while cross-referencing multimodal media streams and incidents in time and space to provide a comprehensive view to a human operator while avoiding information overload. We present several case studies that demonstrate how the proposed system can provide law enforcement personnel with forensic and real time tools to identify and track potential criminal activity.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1275-1281
• /
• 2011

This paper presents synthetic circumstantial judgement system that detects and predicts a fire in subway station. Unlike conventional fire surveillance systems that judge the fire or not through smoke, CO, temperature or variation of temperature, a proposed system discovers a fire more easily or gives the alarm high possibility of fire to operator through recognition of fire levels based on Fuzzy Inference System using by FCM and information of objects from video data.

• Proceedings of the Korea Database Society Conference
• /
• 1998.09a
• /
• pp.83-98
• /
• 1998

Who needs Media Asset Management？ ◆ Publishers ◆ Any company publishing newspapers, magazines, catalogs or web sites. ◆ Content Creators ◆ Companies who create content for use in their business ◆ Broadcasters, Advertising Agencies, Studios, Sports Houses (NBA, NFL), Corporate Training Depts, Retailers ◆ Content Distributors ◆ Cable Operators, Telecoms, Internet Service Providers, Online Service Providers Who needs Media Asset Management？ ◆ There's a LOT of money being spent on this kind of technology, and not just by 'media' companies ◆ Retailers, for catalogs, web sites, call centers ◆ Chems/Pharms, for drug. discovery, knowledge management ◆ Legal, for document and knowledge management ◆ Federal, for video surveillance and knowledge management ◆ Manufacturing, for integration of CAD, text and business-to-business applications ◆ Anyone with a Web/Content Management challenge(omitted)

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.5
• /
• pp.55-61
• /
• 2016

For the purpose of video security equipment is to protect personal property and life against from terrorism or recent threats. In this study, if you proceed with the recorded data search, we propose a method for increasing the user's search convenience. It has predefined data structure which is between camera's movement path and relationship. Also, design and implement a tool that automatically generates a files which has inter camera related information on the control center in a multi-camera is installed environment. Using generated file, minimize searching time and increase searching efficiency.

• Journal of Broadcast Engineering
• /
• v.5 no.1
• /
• pp.41-49
• /
• 2000

In this paper, we propose a new method of indexing and searching based on object-specific features at different semantic levels for video retrieval. A moving trajectory model is used as an indexing key for accessing the individual object in the semantic level. By tracking individual objects with segmented data, we can generate motion trajectories and set model parameters using polynomial curve fitting. The proposed searching scheme supports various types of queries including query by example, query by sketch, and query on weighting parameters for event-based video retrieval. When retrieving the interested video clip, the system returns the best matching event in the similarity order.

• Journal of Korean Society for Geospatial Information Science
• /
• v.17 no.4
• /
• pp.95-103
• /
• 2009

Global interests for construction of 3 dimensional spatial information has risen due to development of measurement sensors and data processing technologies. In spite of criticism for the violation of personal privacy, CCTV cameras equipped in outdoor public space of urban area are used as a fundamental sensor for traffic management, crime prevention or hazard monitoring. For safety guarantee in urban environment and disaster prevention, a surveillance system integrating pre-constructed 3 dimensional spatial information with CCTV data or video sequence is needed for monitoring and observing emergent situation interactively in real time. In this study, we proposed applicability of the prototype system for web visualization based on X3D, an international standard of real time web visualization, by integrating 3 dimensional spatial information with video sequence.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.730-744
• /
• 2023

The topic of this paper is the recognition of human activities using egocentric vision, particularly captured by body-worn cameras, which could be helpful for video surveillance, automatic search and video indexing. This being the case, it could also be helpful in assistance to elderly and frail persons for revolutionizing and improving their lives. The process throws up the task of human activities recognition remaining problematic, because of the important variations, where it is realized through the use of an external device, similar to a robot, as a personal assistant. The inferred information is used both online to assist the person, and offline to support the personal assistant. With our proposed method being robust against the various factors of variability problem in action executions, the major purpose of this paper is to perform an efficient and simple recognition method from egocentric camera data only using convolutional neural network and deep learning. In terms of accuracy improvement, simulation results outperform the current state of the art by a significant margin of 61% when using egocentric camera data only, more than 44% when using egocentric camera and several stationary cameras data and more than 12% when using both inertial measurement unit (IMU) and egocentric camera data.