• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.848-849
• /
• 2023

본 논문은 로봇의 실내 환경에서의 자율성을 높이기 위한 SLAM과 내비게이션 방법을 제시한다. 2D LiDAR와 카메라를 이용하여 위치를 인식하고 사람과 장애물을 의미론적으로 검출하며, ICP와 RTAB-map, YOLOv3를 통합하여 Semantic Map을 생성하고 실내 환경에서 자율성을 유지한다. 이 연구를 통해 로봇이 복잡한 환경에서도 높은 수준의 자율성을 유지할 수 있는지 확인하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.553-556
• /
• 2023

데이터 증강은 데이터 불균형 문제를 해결하기 위해 일반화 성능을 향상시킨다. 이는 과적합 문제를 해결하고 정확도를 높이는 데 도움을 준다. 과적합을 해결하기 위해서 본 논문에서는 분할 마스크 라벨링을 자동화하여 효율성을 높이고, RoI를 활용한 분할 Copy-Paste 데이터 증강 기법을 제안한다. 본 논문의 제안 방법을 적용한 결과 YOLOv8 모델에서 기존의 분할, 박스 Copy-Paste 데이터 증강 기법과 비교해서 쓰러진 사람 객체에 대한 정확도가 10.2% 증가함으로써 제안한 방법이 일반화 성능을 높이는 데 효과가 있음을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.11-12
• /
• 2024

건설 현장에서 자율주행 로봇의 안전한 주행을 위해 동적 장애물의 정확한 인식 및 추적이 중요하다. 본 논문에서는 실시간 3D 객체 인식 및 추적을 위한 방법을 제안한다. Complex-YOLOv4 모델을 이용한 객체 인식, SORT 알고리즘 확장을 통한 객체 추적을 구현하였다. Jetson AGX Orin 보드의 ROS2 환경에서 시스템을 구축하여, 실시간 3D 객체 인식 및 추적이 가능함을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.607-610
• /
• 2024

기업의 운영에 있어서 기업의 핵심 정보가 유출되지 않도록 관리하는 것은 매우 중요하다. 따라서, 사내에서 유통되는 문서들에 대해 핵심적인 정보가 사외로 유출되지 않도록 관리하고 추적하는 것은 필수적이다. 특히, 데이터가 구조화되지 않고, 다양한 형식으로 구성되어있는 비정형 문서 내에서 핵심 정보를 식별하는 것은 기술적으로 어려움이 존재한다. 본 논문에서는 YOLOv8을 사용하여 비정형 문서 내에서 영역을 식별하고, 자연어 처리 모델인 Word2Vec을 사용하여 비정형 문서 내에서 핵심 내용을 식별한 후 이를 시각화함으로써 사내에서 유통되는 비정형 문서 내의 핵심 정보를 식별하고 추적하는 방법을 제안하였다.

• Journal of IKEEE
• /
• v.28 no.2
• /
• pp.150-157
• /
• 2024

In this paper, we propose a novel algorithm for predicting the number of apples on an apple tree using a deep learning-based object detection model and a polynomial regression model. Measuring the number of apples on an apple tree can be used to predict apple yield and to assess losses for determining agricultural disaster insurance payouts. To measure apple fruit load, we photographed the front and back sides of apple trees. We manually labeled the apples in the captured images to construct a dataset, which was then used to train a one-stage object detection CNN model. However, when apples on an apple tree are obscured by leaves, branches, or other parts of the tree, they may not be captured in images. Consequently, it becomes difficult for image recognition-based deep learning models to detect or infer the presence of these apples. To address this issue, we propose a two-stage inference process. In the first stage, we utilize an image-based deep learning model to count the number of apples in photos taken from both sides of the apple tree. In the second stage, we conduct a polynomial regression analysis, using the total apple count from the deep learning model as the independent variable, and the actual number of apples manually counted during an on-site visit to the orchard as the dependent variable. The performance evaluation of the two-stage inference system proposed in this paper showed an average accuracy of 90.98% in counting the number of apples on each apple tree. Therefore, the proposed method can significantly reduce the time and cost associated with manually counting apples. Furthermore, this approach has the potential to be widely adopted as a new foundational technology for fruit load estimation in related fields using deep learning.

• Journal of Broadcast Engineering
• /
• v.28 no.1
• /
• pp.31-41
• /
• 2023

Directly converting the focal depth and image size of computer-generated-hologram (CGH), which is obtained by calculating the interference pattern of light from the 3D image, is known to be quite difficult because of the less similarity between the CGH and the original image. This paper proposes a method for separately converting the each of focal length of the given CGH, which is composed of multi-depth images. Firstly, the proposed technique converts the 3D image reproduced from the CGH into a Light-Field (LF) image composed of a set of 2D images observed from various angles, and the positions of the moving objects for each observed views are checked using an object detection algorithm YOLOv5 (You-Only-Look-Once-version-5). After that, by adjusting the positions of objects, the depth-transformed LF image and CGH are generated. Numerical simulations and experimental results show that the proposed technique can change the focal length within a range of about 3 cm without significant loss of the image quality when applied to the image which have original depth of 10 cm, with a spatial light modulator which has a pixel size of 3.6 ㎛ and a resolution of 3840⨯2160.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.165-167
• /
• 2022

The proportion of cat cats among companion animals has been increasing at an average annual rate of 25.4% since 2012. Cats have strong wildness compared to dogs, so they have a characteristic of hiding diseases well. Therefore, when the guardian finds out that the cat has a disease, the disease may have already worsened. Symptoms such as anorexia (eating avoidance), vomiting, diarrhea, polydipsia, and polyuria in cats are some of the symptoms that appear in cat diseases such as diabetes, hyperthyroidism, renal failure, and panleukopenia. It will be of great help in treating the cat's disease if the owner can recognize the cat's polydipsia (drinking a lot of water), polyuria (a large amount of urine), and frequent urination (urinating frequently) more quickly. In this paper, 1) Efficient version of DeepLabCut for posture prediction running on an artificial intelligence server, 2) yolov4 for object detection, and 3) LSTM are used for behavior prediction. Using artificial intelligence technology, it predicts the cat's next, polyuria and frequency of urination through the analysis of the cat's behavior pattern from the home CCTV video and the weight sensor of the water bowl. And, through analysis of cat behavior patterns, we propose an application that reports disease prediction and abnormal behavior to the guardian and delivers it to the guardian's mobile and the main server system.

• The Journal of Korea Robotics Society
• /
• v.15 no.2
• /
• pp.184-189
• /
• 2020

This paper is a study on data augmentation for small dataset by using deep learning. In case of training a deep learning model for recognition and classification of non-mainstream objects, there is a limit to obtaining a large amount of training data. Therefore, this paper proposes a data augmentation method using perspective transform and image synthesis. In addition, it is necessary to save the object area for all training data to detect the object area. Thus, we devised a way to augment the data and save object regions at the same time. To verify the performance of the augmented data using the proposed method, an experiment was conducted to compare classification accuracy with the augmented data by the traditional method, and transfer learning was used in model learning. As experimental results, the model trained using the proposed method showed higher accuracy than the model trained using the traditional method.

• International journal of advanced smart convergence
• /
• v.9 no.3
• /
• pp.232-238
• /
• 2020

In this paper, we study on aerial objects detection and position estimation algorithm for the safety of UAV that flight in BVLOS. We use the vision sensor and LiDAR to detect objects. We use YOLOv2 architecture based on CNN to detect objects on a 2D image. Additionally we use a clustering method to detect objects on point cloud data acquired from LiDAR. When a single sensor used, detection rate can be degraded in a specific situation depending on the characteristics of sensor. If the result of the detection algorithm using a single sensor is absent or false, we need to complement the detection accuracy. In order to complement the accuracy of detection algorithm based on a single sensor, we use the Kalman filter. And we fused the results of a single sensor to improve detection accuracy. We estimate the 3D position of the object using the pixel position of the object and distance measured to LiDAR. We verified the performance of proposed fusion algorithm by performing the simulation using the Gazebo simulator.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.125-132
• /
• 2023

Roundabouts have strengths in traffic flow and safety but can present difficulties for inexperienced drivers. Demand to acquire and analyze drone images has increased to enhance a traffic environment allowing drivers to deal with roundabouts easily. In this paper, we propose a roundabout traffic analysis system that detects, tracks, and analyzes vehicles using a deep learning-based object detection model (YOLOv7) in drone images. About 3600 images for object detection model learning and testing were extracted and labeled from 1 hour of drone video. Through training diverse conditions and evaluating the performance of object detection models, we achieved an average precision (AP) of up to 97.2%. In addition, we utilized SORT (Simple Online and Realtime Tracking) and OC-SORT (Observation-Centric SORT), a real-time object tracking algorithm, which resulted in an average MOTA (Multiple Object Tracking Accuracy) of up to 89.2%. By implementing a method for measuring roundabout entry speed, we achieved an accuracy of 94.5%.