• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.5
• /
• pp.445-453
• /
• 2001

The multiple targets tracking problem has been one of the main issues in the radar applications area in the last decade. Besides the standard Kalman filtering, various methods including the variable dimen-sion filter, input estimation filter, interacting multiple model(IMM) filter, dederated variable dimension filter with input estimation, etc., have proposed to address the tracking and sensor fusion issues. In this pa- per, two existing tracking algorithm, i.e, the IMM filter and the variable dimension filter with input estima-tion(VDIE), are combined for the purpose of improving the tracking performance for maneuvering targets. To evaluate the tracking performance of the proposed algorithm, three typical maneuvering patterns, i.e., waver, pop-up, and high-diver motions, are defined and are applied to the modified IMM filter as well as the standard IMM filter. The smaller RMS tracking errors, in position and velocity, of the modified IMM filter than the standard IMM filter are demonstrated though computer simulations.

• Journal of KIBIM
• /
• v.7 no.1
• /
• pp.45-53
• /
• 2017

Continuous research efforts have been made on acquiring location data on construction sites. As a result, GPS and RFID are increasingly employed on the site to track the location of equipment and materials. However, these systems are based on radio frequency technologies which require attaching tags on every target entity. Implementing the systems incurs time and costs for attaching/detaching/managing the tags or sensors. For this reason, efforts are currently being made to track construction entities using only cameras. Vision-based 3D tracking has been presented in a previous research work in which the location of construction manpower, vehicle, and materials were successfully tracked. However, the proposed system is still in its infancy and yet to be implemented on practical applications for two reasons. First, it does not involve entity matching across two views, and thus cannot be used for tracking multiple entities, simultaneously. Second, the use of a checker board in the camera calibration process entails a focus-related problem when the baseline is long and the target entities are located far from the cameras. This paper proposes a vision-based method to track multiple workers simultaneously. An entity matching procedure is added to acquire the matching pairs of the same entities across two views which is necessary for tracking multiple entities. Also, the proposed method simplified the calibration process by avoiding the use of a checkerboard, making it more adequate to the realistic deployment on construction sites.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.633-635
• /
• 2016

Convolutional Networks (ConvNets) are powerful models that learn hierarchies of visual features, which could also be used to obtain image representations for transfer learning. The basic pipeline for transfer learning is to first train a ConvNet on a large dataset (source task) and then use feed-forward units activation of the trained ConvNet as image representation for smaller datasets (target task). Our key contribution is to demonstrate superior performance of multiple ConvNet layer features over single ConvNet layer features. Combining multiple ConvNet layer features will result in more complex feature space with some features being repetitive. This requires some form of feature selection. We use AdaBoost with single stumps to implicitly select only distinct features that are useful towards classification from concatenated ConvNet features. Experimental results show that using multiple ConvNet layer activation features instead of single ConvNet layer features consistently will produce superior performance. Improvements becomes significant as we increase the distance between source task and the target task.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.2
• /
• pp.221-228
• /
• 2020

A sonobuoy is dropped onto the surface of water to estimate the bearing of an underwater target. A Directional Frequency Analysis and Recording (DIFAR) sonobuoy has an error in the specific angular section due to the method of estimating bearing and noise, which causes an error in target localization using multiple sonobuoys. In addition, the position of the sonobuoy continues to move, but since a sonobuoy with a GPS is intermittently arranged, it is difficult to estimate the exact position of the sonobuoy. This also causes target localization performance degradation. In this paper, we propose a technique to improve the target localization performance by compensating for bearing errors using characteristics of the DIFAR sonobuoy and multiple-sonobuoy position errors based on the intermittently arranged active sonobuoy with a GPS.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.131-136
• /
• 2003

The problem of maneuvering target tracking has been studied in the field of the state estimation over decades. The Kalman filter has been widely used to estimate the states of the target, but in the presence of a maneuver, its performance may be seriously degraded. In this paper, to solve this problem and track a maneuvering target effectively, DNA coding-based intelligent Kalman filter (DNA coding-based IKF) is proposed. The proposed method can overcome the mathematical limits of conventional methods and can effectively track a maneuvering target with only one filter by using the fuzzy logic based on DNA coding method. The tracking performance of the proposed method is compared with those of the adaptive interacting multiple model (AIMM) method and the GA-based IKF in computer simulations.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.5 s.43
• /
• pp.75-86
• /
• 2006

Target word selection is one of the most important and difficult tasks in English-Korean Machine Translation. It effects on the translation accuracy of machine translation systems. In this paper, we present a new approach to select Korean target word for an English noun with translation ambiguities using multiple knowledge such as verb frame patterns, sense vectors based on collocations, statistical Korean local context information and co-occurring POS information. Verb frame patterns constructed with dictionary and corpus play an important role in resolving the sparseness problem of collocation data. Sense vectors are a set of collocation data when an English word having target selection ambiguities is to be translated to specific Korean target word. Statistical Korean local context Information is an N-gram information generated using Korean corpus. The co-occurring POS information is a statistically significant POS clue which appears with ambiguous word. The experiment showed promising results for diverse sentences from web documents.

• Ocean and Polar Research
• /
• v.32 no.2
• /
• pp.113-122
• /
• 2010

Understanding the abundance and distribution of massive jellyfish is necessary to forecast where or when their blooms will happen. The acoustic technique is one of the most useful methods of obtaining information if the acoustic characteristics of the targets are known. This study was conducted to determine the acoustic target strength (TS, dB) of two jellyfish species, Aurelia aurita and Cyanea nozakii, in the southern coast of Korea. For the ex situ measurements, 120, 200, and 420 kHz split beam transducers were used, and jellyfish with various bell lengths were arranged to prepare multiple jellyfish. Under 2 vertical individuals, the mean TS for multiple A. aurita at 120, 200, and 420 kHz was -72.7, -71.7, and -68.2 dB, respectively. In the case of 5 vertical individuals, the mean TS of the species was -71.3, -68.2, and -62.0 dB. Finally, the mean TS of C. nozakii at 120, 200, and 200 kHz was -62.0, -60.3, and -58.2 dB under 2 individuals and -58.1, -57.4, and -54.0 dB under 4 individuals, respectively. For both species, higher numbers of jellyfish resulted in a higher TS. In addition, higher frequencies were associated with a higher TS for the same jellyfish. These TS results for two species can be used as essential data for the acoustic detection of jellyfish in an open ocean or coastal area.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.68-73
• /
• 2005

Various techniques have been proposed for detection and tracking of targets in order to develop a real-world computer vision system, e.g., visual surveillance systems, intelligent transport systems (ITSs), and so forth. Especially, the idea of distributed vision system is required to realize these techniques in a wide-spread area. In this paper, we develop a ubiquitous vision system for location-awareness of multiple targets. Here, each vision sensor that the system is composed of can perform exact segmentation for a target by color and motion information, and visual tracking for multiple targets in real-time. We construct the ubiquitous vision system as the multiagent system by regarding each vision sensor as the agent (the vision agent). Therefore, we solve matching problem for the identity of a target as handover by protocol-based approach. We propose the identified contract net (ICN) protocol for the approach. The ICN protocol not only is independent of the number of vision agents but also doesn't need calibration between vision agents. Therefore, the ICN protocol raises speed, scalability, and modularity of the system. We adapt the ICN protocol in our ubiquitous vision system that we construct in order to make an experiment. Our ubiquitous vision system shows us reliable results and the ICN protocol is successfully operated through several experiments.

• Journal of KIISE:Software and Applications
• /
• v.34 no.10
• /
• pp.937-944
• /
• 2007

In this paper, we propose multiple human tracking with an moving stereo camera. The tracking process is based on mean shift algorithm which is using color information of the target. Color based tracking approach is invariant to translation and rotation of the target but, it has several problems. Because of mean shift uses color distribution, it is sensitive to color distribution of background and targets. In order to solve this problem, we combine color and depth information of target. Also, we build human body part model to handle occlusions and we have created adaptive box scale. As a result, the proposed method is simple and efficient to track multiple humans in real time.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.479-482
• /
• 2004

In this article we consider a single maneuvering target Tracking algorithm in the presence of missing measurements and high clutter environments for multi-sensor target tracking problem. The tracking algorithm is based on the Particle filtering method to predict and update target states. Proposed is the AMM-PF(Auxiliary Multiple Model Particle Filter)[2] method for maneuvering target tracking to improve performance in track estimate and maintenance with a high level of uncertainty. The algorithm we propose is compared to the Extended Kalman Filter(EKF). A simulation study is included.