• 한국우주과학회:학술대회논문집(한국우주과학회보)
• /
• 한국우주과학회 2006년도 한국우주과학회보 제15권1호
• /
• pp.129-132
• /
• 2006

한국항공대학교 우주시스템연구실에서는 나노급 위성인 HAUSAT-2 개발과 더불어 주요 탑재체인 동물 추적 시스템을 직접 연구 개발하고 있다. 동물 추적 시스템은 위성에 탑재되는 동물 추적 시스템 수신기와 동물 추적 송신기, 위성으로부터 수신된 신호를 해석하고 처리하는 지상국으로 구성되어 있다. 본 논문에서는 동물추적시스템의 전반적인 운용개념과 하드웨어 개발에 대하여 기술하며 데이터를 처리하기 위한 소프트웨어 알고리즘 및 도플러 편이(Doppler Shift)를 이용한 동물 위치 추정 알고리즘에 대하여 논한다.

• 스마트미디어저널
• /
• 제5권1호
• /
• pp.78-87
• /
• 2016

The major problems of recent object tracking methods are related to the inefficient detection of moving objects due to occlusions, noisy background and inconsistent body motion. This paper presents a robust method for the detection and tracking of a moving in infrared animal videos. The tracking system is based on adaptive optical flow generation, Gaussian mixture and Kalman filtering. The adaptive Gaussian model of optical flow (GMOF) is used to extract foreground and noises are removed based on the object motion. Kalman filter enables the prediction of the object position in the presence of partial occlusions, and changes the size of the animal detected automatically along the image sequence. The presented method is evaluated in various environments of unstable background because of winds, and illuminations changes. The results show that our approach is more robust to background noises and performs better than previous methods.

• 센서학회지
• /
• 제23권2호
• /
• pp.82-86
• /
• 2014

This paper reports the development of a platform for tracking and analysis of animal locomotion. The platform is composed of a commercial webcam, a metal stand for the webcam, and a plastic bathtub as a cage. Using it, researchers can track and analyze an animal's movement within the plastic bathtub's dimensions of $100cm{\times}100cm{\times}55cm$ in a cost-effective manner. After recording the locomotion of an animal with $1920{\times}1080$ resolution at a rate of 30 frames per second, finding the position of the animal in each frame and analyzing the ambulation pattern were executed with custom software. To evaluate the performance of the platform, movements of imprinting control region mice and transgenic mice were recorded and analyzed. The analysis successfully compared velocity, moving pattern, and total moving distance for the two mouse groups. In addition, the developed platform can be used not only in simple motion analysis but also in various experimental conditions, such as a water maze, by easy customization of the platform. Such a simple and cost-effective platform yields a powerful tool for animal ambulatory analysis.

• Molecules and Cells
• /
• 제23권2호
• /
• pp.132-137
• /
• 2007

With the advance of stem cell transplantation research, in vivo cell tracking techniques have become increasingly important in recent years. Magnetic resonance imaging (MRI) may provide a unique tool for non-invasive tracking of transplanted cells. Since the initial findings on the stem cell migration by MRI several years ago, there have been numerous studies using various animal models, notably in heart or brain disease models. In order to develop more reliable and clinically applicable methodologies, multiple aspects should be taken into consideration. In this review, we will summarize the current status and future perspectives of in vivo cell tracking technologies using MRI. In particular, use of different MR contrast agents and their detection methods using MRI will be described in much detail. In addition, various cell labeling methods to increase the sensitivity of signals will be extensively discussed. We will also review several key experiments, in which MRI techniques were utilized to detect the presence and/or migration of transplanted stem cells in various animal models. Finally, we will discuss the current problems and future directions of cell tracking methods using MRI.

• 한국인터넷방송통신학회논문지
• /
• 제9권5호
• /
• pp.79-84
• /
• 2009

최근 센서 네트워크를 이용하여 특정 환경에서 동물의 행위나 반응 등을 모니터링하고, RFID 기술을 이용하여 동물 이력을 추적하거나 동물을 식별하는 연구가 진행되고 있다. 그리고 GPS 기술을 동물에 적용하여 애완견 도난 방지이나 관리 등에 대해 연구하고 있다. 그러나 아직 GPS, RFID, 센서 네트워크를 이용하여 동물원에서 일반 사용자나 관리자를 대상으로 지능적인 서비스를 제공하는 연구는 미흡하다. 따라서 본 논문에서 GPS, RFID, 센서를 동물원에 적용하여 동물 상태를 추적하는 지능적인 서비스를 제안한다. 이를 위해 먼저 동물 상태 추적 서비스 시나리오를 제시하고, 이 서비스를 제공하기 위한 시스템 구성을 작성한다. 제시된 동물 상태 추적 서비스는 GPS, RFID, 센서를 이용하여 동물의 현재 위치, 체온, 사진 등의 상태 정보를 실시간으로 제공하고, 또한 동물이 우리를 이탈할 경우 위치와 상태를 알고 추적할 수 있다. 더불어 제시한 서비스 시나리오에 따른 동물 상태 추적 시스템의 프로토타입을 구현하고 실험하여 동작됨을 확인한다.

• 대한수의학회지
• /
• 제60권2호
• /
• pp.55-59
• /
• 2020

This study was purposed to make the referenced range of stomach antral contraction strain in 50 dogs using 2-dimensional speckle tracking. In addition, the strain results were compared among body condition scores to reveal the correlations of obesity among the subjects of the study. Finally, the medetomidine group that was comprised of 10 dogs was compared with the normal group to identify the medetomidine pharmacologic effect in the stomach antral contraction. Clinically healthy 50 dogs were recruited for the study. In an ultrasonographic examination, the stomach antrum region was scanned, and at least one cycle of antral contraction was recorded. The peak strain of antral contraction in healthy dogs was 58.2 ± 20.47% (mean ± SD). The obesity group showed a high strain result and there were significant correlations between the body condition score (BCS) 2, BCS 3 groups and BCS 8 group. The medetomidine group revealed a low strain result and was significantly correlated with normal group. Two-dimensional speckle tracking was useful to the evaluation of stomach motility disorders.

• 스마트미디어저널
• /
• 제11권8호
• /
• pp.84-92
• /
• 2022

Precision livestock monitoring promises greater management efficiency for farmers and higher welfare standards for animals. Recent studies on video-based animal activity recognition and tracking have shown promising solutions for understanding animal behavior. To achieve that, surveillance cameras are installed diagonally above the barn in a typical cattle farm setup to monitor animals constantly. Under these circumstances, tracking individuals requires addressing challenges such as occlusion and visual appearance, which are the main reasons for track breakage and increased misidentification of animals. This paper presents a framework for multi-cattle tracking in closed barns with appearance and motion models. To overcome the above challenges, we modify the DeepSORT algorithm to achieve higher tracking accuracy by three contributions. First, we reduce the weight of appearance information. Second, we use an Ensemble Kalman Filter to predict the random motion information of cattle. Third, we propose a supplementary matching algorithm that compares the absolute cattle position in the barn to reassign lost tracks. The main idea of the matching algorithm assumes that the number of cattle is fixed in the barn, so the edge of the barn is where new trajectories are most likely to emerge. Experimental results are performed on our dataset collected on two cattle farms. Our algorithm achieves 70.37%, 77.39%, and 81.74% performance on HOTA, AssA, and IDF1, representing an improvement of 1.53%, 4.17%, and 0.96%, respectively, compared to the original method.

• 제어로봇시스템학회논문지
• /
• 제13권10호
• /
• pp.983-989
• /
• 2007

Most of life thing including human being have tendency of reaction with inherently their own pattern against environmental change caused by such as light, sound, smell etc. Especially, a sense of direction often works as a very important factor in such reaction. Actually, human or animal lift that can react instantly to a stimulus determine their action with a sense of direction to a stimulant. In this paper, we try to propose how to give a sense of direction to a robot using sound being representative stimulant, and tracking sensors being able to detect the direction of such sound source. We also try to propose how to determine the relative directions among devices or robots using the digital compass and the RSSI on wireless network.

• 한국항공우주학회지
• /
• 제34권11호
• /
• pp.61-69
• /
• 2006

도플러 효과를 이용해서 동물의 위치를 추적하는 경우 동물에 장착된 단말기의 송신신호를 위성의 수신기에서 얼마나 많이, 정확하게 측정하느냐에 따라 위치 추적의 정밀도가 달라진다. ARGOS 위성시스템의 경우 다수의 위성을 운용하여 단말기의 송신신호를 비교적 많이 측정하며, 이러한 많은 측정 데이터를 이용해서 상당히 높은 위치추적 정밀도를 유지하고 있다. 하지만 단일 위성을 사용하는 동물추적시스템의 경우 위성이 단말기를 통과하는 짧은 시간동안 송신 신호를 많이 측정하기 힘들며, 이는 위치추적의 정밀도를 떨어뜨리는 가장 큰 원인이 된다. 따라서 본 논문에서는 단일 위성에서 도플러 천이 측정 데이터의 개수를 증가시키기 위해서 도플러 천이 변화율을 이용하여 수신 데이터를 추정하였으며, 추정된 데이터를 측정치로 사용하여 측정 데이터의 개수를 증가 시켰다. 결과적으로 도플러 천이 변화율을 이용하여 비교적 높은 위치추적 정밀도를 획득 할 수 있으며, 단일 위성을 사용하는 동물추적시스템에 적합한 방식임을 알 수 있다.

• Journal of Veterinary Science
• /
• 제23권1호
• /
• pp.17.1-17.10
• /
• 2022

Background: Inspection of livestock farms using surveillance cameras is emerging as a means of early detection of transboundary animal disease such as African swine fever (ASF). Object tracking, a developing technology derived from object detection aims to the consistent identification of individual objects in farms. Objectives: This study was conducted as a preliminary investigation for practical application to livestock farms. With the use of a high-performance artificial intelligence (AI)-based 3D depth camera, the aim is to establish a pathway for utilizing AI models to perform advanced object tracking. Methods: Multiple crossovers by two humans will be simulated to investigate the potential of object tracking. Inspection of consistent identification will be the evidence of object tracking after crossing over. Two AI models, a fast model and an accurate model, were tested and compared with regard to their object tracking performance in 3D. Finally, the recording of pig pen was also processed with aforementioned AI model to test the possibility of 3D object detection. Results: Both AI successfully processed and provided a 3D bounding box, identification number, and distance away from camera for each individual human. The accurate detection model had better evidence than the fast detection model on 3D object tracking and showed the potential application onto pigs as a livestock. Conclusions: Preparing a custom dataset to train AI models in an appropriate farm is required for proper 3D object detection to operate object tracking for pigs at an ideal level. This will allow the farm to smoothly transit traditional methods to ASF-preventing precision livestock farming.