• Smart Media Journal
• /
• v.13 no.10
• /
• pp.35-42
• /
• 2024

This study aims to develop a system that predicts the health status of cattle based on behavior patterns and environmental data within a smart barn using an autonomous driving system. Maintaining a unique ID for each cow using only a camera, without external devices (such as RFID tags), is essential. This enables the tracking of behavior patterns such as standing, sitting, and lying for each cow over time. Additionally, environmental data such as temperature and humidity are integrated to comprehensively assess the cows' health conditions. To achieve this, we propose a unique ID retention algorithm that combines object detection using YOLO, tracking with Deep SORT, and re-identification (ReID). Experimental results show that the YOLO + Deep SORT + ReID algorithm delivers the best performance in maintaining unique IDs, and the LSTM-based behavior analysis model demonstrates high accuracy in predicting behavior patterns. This system can serve as an effective tool for real-time prediction of livestock health conditions, such as disease or stress, through comprehensive analysis of environmental data and behavior patterns inside the barn.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.329-331
• /
• 2018

지속적인 딥러닝 기반의 영상처리 기술의 발전으로 객체분류나 객체검출 문제에 대해서 뛰어난 성능 보이고 있다. 하지만 객체추적 문제에서는 성능이 좋은 추적기는 실시간 동작이 불가능하고 딥러닝 기반의 객체추적도 단일 객체에만 고려한 기법이 많기 때문에 개선할 필요가 있다. 전처리로 검출된 객체영역과 kalman filter를 통해 예측된 추적영역 간의 embedding feature 비교를 통해 동일인물인지 판단하여 고유 ID를 부여하고 추적한다. 객체끼리 교차하거나 가려지는 상황에서 추적을 실패하게 되는데 이 후에 지속적인 추적을 위해 IoU 비교를 통해 후보 추적기로 남겨두는 과정을 거친다. 실험 결과 실시간 동작여부와 객체끼리 교차하거나 프레임 밖으로 나갔다가 다시 나타나는 경우에도 추적이 가능함을 확인하였다.

• Horticultural Science & Technology
• /
• v.30 no.3
• /
• pp.278-285
• /
• 2012

Cymbidium goeringii is one of the most important and popular species in the orchid family in north-east Asia. In the present study, we prepared multiplex PCR system, and used it for the genotyping of eight simple sequence repeats (SSR) markers (CG409, CG415, CG709, CG722, CG787, CG1023, CG1210, and CG1281) in subject with 40 samples of cultivated varieties. All the analyzed samples showed different combined genotypes. The average combined power of discrimination was very high value of $7.14{\times}10^{-10}$, and observed heterozygosity (Ho = 0.466) was similar with two wild populations of C. goeringii, which may indicate no or little occurrence of genetic change after collection from wild habitats. The present study also developed a two-dimensional barcode to express information of genotype results of eight SSR markers (SSR DNA ID). The discrimination power of DNA ID between two individuals will be statistically more than 99.999999%. The SSR DNA ID and two-dimensional barcode may be very usefully applied for the discrimination and maintence of cultivars of C. goeringii.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.22 no.4
• /
• pp.489-499
• /
• 2011

RFID technologies, which allow collecting, storing, processing, and tracking information by wirelessly recognizing the inherent ID of object through an attached electronic tag, have a variety of application areas. This paper presents a novel carrier leakage suppression RF(CLS-RF) front-end for ultra-high-frequency RF identification reader. The proposed reader CLS-RF front-end structure generates the carrier leakage replica through the nonlinear path that contains limiter. The limiting function only preserves the frequency and phase information of the leakage signal and rejects the amplitude modulated tag signal in the envelope. The carrier leakage replica is then injected into the linear path that contains phase shifter. Therefore, the carrier leakage signal is effectively cancelled out, while not affecting the gain of the desired tag backscattering signal. We experimentally confirm that the prototype shows a significant improvement in the leakage to signal ratio by up to 36 dB in 910 MHz, which is consistent with our simulation results.

• Journal of the Korea Computer Industry Society
• /
• v.8 no.4
• /
• pp.253-262
• /
• 2007

As the internet environment is applied in the various service field, the recognition on security is increasing. Because the authentication methods for web service user do not confirm person oneself, the serious problems of reliability, safety and security can be caused. In order to solve this problems, the authentication methods of user id and password or authentication key is used. Because the password and authentication key using the existent authentication methods for security is composed of a string, authentication information can easily hacked or leaked by hackers, and the serious problems of security can be caused. In this paper, in order to improve the web security, an authentication module using the fingerprint that have the unique properties of person is proposed. As the proposed module makes use of fingerprint authentication, the security of the web service user from hackers can be maintained. The proposed method is more excellent than the existent method in the web security.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.18-26
• /
• 2023

In this study, we propose a cow behavior recognition system based on YOLOX and OC-SORT. YOLO X detects targets in real-time and provides information on cow location and behavior. The OC-SORT module tracks cows in the video and assigns unique IDs. The quantitative analysis module analyzes the behavior and location information of cows. Experimental results show that our system demonstrates high accuracy and precision in target detection and tracking. The average precision (AP) of YOLOX was 82.2%, the average recall (AR) was 85.5%, the number of parameters was 54.15M, and the computation was 194.16GFLOPs. OC-SORT was able to maintain high-precision real-time target tracking in complex environments and occlusion situations. By analyzing changes in cow movement and frequency of mounting behavior, our system can help more accurately discern the estrus behavior of cows.