• Journal of Korea Multimedia Society
• /
• v.23 no.10
• /
• pp.1236-1249
• /
• 2020

In a most recent object tracking research work, applying Convolutional Neural Network and Recurrent Neural Network-based strategies become relevant for resolving the noticeable challenges in it, like, occlusion, motion, object, and camera viewpoint variations, changing several targets, lighting variations. In this paper, the LSTM Network-based Tracking association method has proposed where the technique capable of real-time multi-object tracking by creating one of the useful LSTM networks that associated with tracking, which supports the long term tracking along with solving challenges. The LSTM network is a different neural network defined in Keras as a sequence of layers, where the Sequential classes would be a container for these layers. This purposing network structure builds with the integration of tracking association on Keras neural-network library. The tracking process has been associated with the LSTM Network feature learning output and obtained outstanding real-time detection and tracking performance. In this work, the main focus was learning trackable objects locations, appearance, and motion details, then predicting the feature location of objects on boxes according to their initial position. The performance of the joint object tracking system has shown that the LSTM network is more powerful and capable of working on a real-time multi-object tracking process.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.80-88
• /
• 2023

RGB-thermal (RGB-T) tracking using unmanned aerial vehicles (UAVs) involves challenges with regards to the similarity of objects, occlusion, fast motion, and motion blur, among other issues. In this study, we propose dynamic tracking aggregation (DTA) as a unified framework to perform object detection and data association. The proposed approach obtains fused features based a transformer model and an L1-norm strategy. To link the current frame with recent information, a dynamically updated embedding called dynamic tracking identification (DTID) is used to model the iterative tracking process. For object association, we designed a long short-term tracking aggregation module for dynamic feature propagation to match spatial and temporal embeddings. DTA achieved a highly competitive performance in an experimental evaluation on public benchmark datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.11
• /
• pp.5624-5638
• /
• 2016

A novel method based on Surf points is proposed to detect and lock-track single ground target in aerial videos. Videos captured by moving cameras contain complex motions, which bring difficulty in moving object detection. Our approach contains three parts: moving target template detection, search area estimation and target tracking. Global motion estimation and compensation are first made by grids-sampling Surf points selecting and matching. And then, the single ground target is detected by joint spatial-temporal information processing. The temporal process is made by calculating difference between compensated reference and current image and the spatial process is implementing morphological operations and adaptive binarization. The second part improves KALMAN filter with surf points scale information to predict target position and search area adaptively. Lastly, the local Surf points of target template are matched in this search region to realize target tracking. The long-term tracking is updated following target scaling, occlusion and large deformation. Experimental results show that the algorithm can correctly detect small moving target in dynamic scenes with complex motions. It is robust to vehicle dithering and target scale changing, rotation, especially partial occlusion or temporal complete occlusion. Comparing with traditional algorithms, our method enables real time operation, processing $520{\times}390$ frames at around 15fps.

• International journal of advanced smart convergence
• /
• v.4 no.2
• /
• pp.20-28
• /
• 2015

In this paper, we propose an effective tracking algorithm with an appearance model based on features extracted from a video frame with posture variation and camera view point adaptation by employing the non-adaptive random projections that preserve the structure of the image feature space of objects. The existing online tracking algorithms update models with features from recent video frames and the numerous issues remain to be addressed despite on the improvement in tracking. The data-dependent adaptive appearance models often encounter the drift problems because the online algorithms does not get the required amount of data for online learning. So, we propose an effective tracking algorithm with an appearance model based on features extracted from a video frame.

• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.345-354
• /
• 2021

Recently, deep learning-based image recognition systems have been adopted to various surveillance environments, but most of them are still picture-type object recognition methods, which are insufficient for the long term temporal analysis and high-dimensional situation management. Therefore, we propose a method recognizing the specific dangerous situation generated by human in real-time, and utilizing deep learning-based object analysis techniques. The proposed method uses deep learning-based object detection and tracking algorithms in order to recognize the situations such as 'trespassing', 'loitering', and so on. In addition, human's joint pose data are extracted and analyzed for the emergent awareness function such as 'falling down' to notify not only in the security but also in the emergency environmental utilizations.

• Journal of Digital Contents Society
• /
• v.16 no.6
• /
• pp.901-908
• /
• 2015

Networked multiple CCTV systems are required to effectively trace down long-term abnormal behaviors, such as stalking. However, the occluding event, which often takes place during tracking, may result in critical errors of cessation of tracing, or tracking wrong objects. Thus, utilizing installed regular CCTVs, this study aims to trace the relation tracking in a continuous manner by recognizing distinctive features of each object and its perspective projection depth to address the problem with occluded objects. In addition, this study covers occlusion event between the stationary background objects, such as street lights, or walls, and the targeted object.

• Journal of Advanced Information Technology and Convergence
• /
• v.10 no.1
• /
• pp.15-23
• /
• 2020

In this paper, we propose a new method to detect traffic accidents in video from vehicle-mounted cameras (vehicle black box). We use the distance between vehicles to determine whether an accident has occurred. To calculate the position of each vehicle, we use object detection and tracking method. By the way, in a crowded road environment, it is so difficult to decide an accident has occurred because of parked vehicles at the edge of the road. It is not easy to discriminate against accidents from non-accidents because a moving vehicle and a stopped vehicle are mixed on a regular downtown road. In this paper, we try to increase the accuracy of the vehicle accident detection by using not only the motion of the surrounding vehicle but also ego-motion as the input of the Recurrent Neural Network (RNN). We improved the accuracy of accident detection compared to the previous method.

• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.103-106
• /
• 2003

In this paper, we present a hybrid inertial and vision-based tracking system for VR applications. One of the most important aspects of VR (Virtual Reality) is providing a correspondence between the physical and virtual world. As a result, accurate and real-time tracking of an object's position and orientation is a prerequisite for many applications in the Virtual Environments. Pure vision-based tracking has low jitter and high accuracy but cannot guarantee real-time pose recovery under all circumstances. Pure inertial tracking has high update rates and full 6DOF recovery but lacks long-term stability due to sensor noise. In order to overcome the individual drawbacks and to build better tracking system, we introduce the fusion of vision-based and inertial tracking. Sensor fusion makes the proposal tracking system robust, fast, accurate, and low jitter and noise. Hybrid tracking is implemented with Kalman Filter that operates in a predictor-corrector manner. Combining bluetooth serial communication module gives the system a full mobility and makes the system affordable, lightweight energy-efficient. and practical. Full 6DOF recovery and the full mobility of proposal system enable the user to interact with mobile device like PDA and provide the user with natural interface.

• Current Optics and Photonics
• /
• v.3 no.1
• /
• pp.27-32
• /
• 2019

We present an autofocus tracking system implemented by the digital refocusing of digital holographic microscopy (DHM) and the tunability of an electrically tunable lens (ETL). Once the defocusing distance of an image is calculated with the DHM, then the focal plane of the imaging system is optically tuned so that it always gives a well-focused image regardless of the object location. The accuracy of the focus is evaluated by calculating the contrast of refocused images. The DHM is performed in an off-axis holographic configuration, and the ETL performs the focal plane tuning. With this proposed system, we can easily track down the object drifting along the depth direction without using any physical scanning. In addition, the proposed system can simultaneously obtain the digital hologram and the optical image by using the RGB channels of a color camera. In our experiment, the digital hologram is obtained by using the red channel and the optical image is obtained by the blue channel of the same camera at the same time. This technique is expected to find a good application in the long-term imaging of various floating cells.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.27-33
• /
• 2020

Recently, visual object detection and tracking has become a vital role in many different applications. It spans various applications like robotics, video surveillance, and intelligent vehicle navigation. Especially, in current situation where the use of UAVs is expanding widely, detection and tracking to soot down illegal UAVs flying over the sky at airports, nuclear power plants and core facilities is becoming a very important task. The remarkable method in object tracking is correlation filter based tracker like KCF (Kernelized Correlation Filter). But it has problems related to target drift in tracking process for long-term tracking. To mitigate the target drift problem in video surveillance application, we propose a tracking method which uses KCF, adaptive thresholding and Kalman filter. In the experiment, the proposed method was verified by using monochrome video sequences which were obtained in the operational environment of UAV.