• International Journal of Internet, Broadcasting and Communication
• /
• 제11권4호
• /
• pp.76-85
• /
• 2019

We introduce a vision-based object detection method for real-time video surveillance system in low-end edge computing environments. Recently, the accuracy of object detection has been improved due to the performance of approaches based on deep learning algorithm such as Region Convolutional Neural Network(R-CNN) which has two stage for inferencing. On the other hand, one stage detection algorithms such as single-shot detection (SSD) and you only look once (YOLO) have been developed at the expense of some accuracy and can be used for real-time systems. However, high-performance hardware such as General-Purpose computing on Graphics Processing Unit(GPGPU) is required to still achieve excellent object detection performance and speed. To address hardware requirement that is burdensome to low-end edge computing environments, We propose sub-frame analysis method for the object detection. In specific, We divide a whole image frame into smaller ones then inference them on Convolutional Neural Network (CNN) based image detection network, which is much faster than conventional network designed forfull frame image. We reduced its computationalrequirementsignificantly without losing throughput and object detection accuracy with the proposed method.

• 대한원격탐사학회지
• /
• 제37권4호
• /
• pp.747-761
• /
• 2021

With the increasing application of UAVs in intelligent transportation systems, vehicle detection for aerial images has become an essential engineering technology and has academic research significance. In this paper, a vehicle detection method for aerial images based on the YOLOv4 deep learning algorithm is presented. At present, the most known datasets are VOC (The PASCAL Visual Object Classes Challenge), ImageNet, and COCO (Microsoft Common Objects in Context), which comply with the vehicle detection from UAV. An integrated dataset not only reflects its quantity and photo quality but also its diversity which affects the detection accuracy. The method integrates three public aerial image datasets VAID, UAVD, DOTA suitable for YOLOv4. The training model presents good test results especially for small objects, rotating objects, as well as compact and dense objects, and meets the real-time detection requirements. For future work, we will integrate one more aerial image dataset acquired by our lab to increase the number and diversity of training samples, at the same time, while meeting the real-time requirements.

• 로봇학회논문지
• /
• 제17권4호
• /
• pp.417-424
• /
• 2022

In this paper, the developed trunk cargo unloading automation system is introduced, and the RGB-D sensor-based box loading situation recognition method and unloading plan applied to this system are suggested. First of all, it is necessary to recognize the position of the box in a truck. To do this, we first apply CNN-based YOLO, which can recognize objects in RGB images in real-time. Then, the normal vector of the center of the box is obtained using the depth image to reduce misrecognition in parts other than the box, and the inner wall of the truck in an image is removed. And a method of classifying the layers of the boxes according to the distance using the recognized depth information of the boxes is suggested. Given the coordinates of the boxes on the nearest layer, a method of generating the optimal path to take out the boxes the fastest using this information is introduced. In addition, kinematic analysis is performed to move the conveyor to the position of the box to be taken out of the truck, and kinematic analysis is also performed to control the robot arm that takes out the boxes. Finally, the effectiveness of the developed system and algorithm through a test bed is proved.

• 대한안전경영과학회지
• /
• 제25권3호
• /
• pp.17-22
• /
• 2023

As the importance of artificial intelligence grows rapidly and emerges as a leader in technology, it is becoming an important variable in the next-generation industrial system along with the robot industry. In this study, a safety system was developed using deep learning technology to provide worker safety in a robot workplace environment. The implemented safety system has multiple cameras installed with various viewing directions to avoid blind spots caused by interference. Workers in various scenario situations were detected, and appropriate robot response scenarios were implemented according to the worker's risk level through IO communication. For human detection, the YOLO algorithm, which is widely used in object detection, was used, and a separate robot class was added and learned to compensate for the problem of misrecognizing the robot as a human. The performance of the implemented system was evaluated by operator detection performance by applying various operator scenarios, and it was confirmed that the safety system operated stably.

• 드라이브 ㆍ 컨트롤
• /
• 제21권3호
• /
• pp.36-45
• /
• 2024

Collaborative robots, designed for direct interaction with humans have limited adaptability to environmental changes. This study addresses this limitation by implementing a barista robot system using AI technology. To overcome limitations of traditional collaborative robots, a model that applies a real-time object detection algorithm to a 6-degree-of-freedom robot arm to recognize and control the position of random cups is proposed. A coffee ordering application is developed, allowing users to place orders through the app, which the robot arm then automatically prepares. The system is connected to ROS via TCP/IP socket communication, performing various tasks through state transitions and gripper control. Experimental results confirmed that the barista robot could autonomously handle processes of ordering, preparing, and serving coffee.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권8호
• /
• pp.2688-2703
• /
• 2022

Research on the advanced detection of harmful objects in airport cargo for passenger safety against terrorism has increased recently. However, because associated studies are primarily focused on the detection of relatively large objects, research on the detection of small objects is lacking, and the detection performance for small objects has remained considerably low. Here, we verified the limitations of existing research on object detection and developed a new model called the Small Hazardous Object detection enhanced and reconstructed Model based on the You Only Look Once version 5 (YOLOv5) algorithm to overcome these limitations. We also examined the performance of the proposed model through different experiments based on YOLOv5, a recently launched object detection model. The detection performance of our model was found to be enhanced by 0.3 in terms of the mean average precision (mAP) index and 1.1 in terms of mAP (.5:.95) with respect to the YOLOv5 model. The proposed model is especially useful for the detection of small objects of different types in overlapping environments where objects of different sizes are densely packed. The contributions of the study are reconstructed layers for the Small Hazardous Object detection enhanced and reconstructed Model based on YOLOv5 and the non-requirement of data preprocessing for immediate industrial application without any performance degradation.

• 경영정보학연구
• /
• 제22권1호
• /
• pp.113-124
• /
• 2020

농가를 운영함에 있어서 수확한 작물에 대한 품질을 평가하여 불량품을 분류하는 작업은 매우 중요하다. 그러나, 농가는 부족한 자본과 인력으로 인하여 품질평가에 소요되는 비용과 시간을 감당하는데 어려움이 있다. 이에 본 연구는 인공지능 기술인 딥 러닝 알고리즘을 이용하여 과일의 표피를 분석함으로써 불량을 검출하고자 한다. 과일을 촬영한 동영상 이미지에 대하여 영역기반 합성곱 신경망(Region Convolutional Neural Network)을 기반으로 한 YOLOv3 알고리즘을 적용하여 표피를 분석할 수 있는 모델을 개발하였다. 총 4개의 클래스를 정해서 학습을 진행하였고, 총 97,600번의 epoch을 통해서 우수한 성능의 불량검출 모델을 얻을 수 있었다. 본 연구에서 제안한 농작물 불량검출 모델은 데이터 수집, 분석된 데이터를 통한 품질평가, 그리고 불량검출에 이르는 과정의 자동화에 활용될 수 있다. 특히, 농작물들 중에서도 외상에 가장 취약한 복숭아를 대상으로 분석모델을 개발하였기 때문에, 다른 작물에도 적용될 수 있을 것으로 기대된다.

• 한국전자통신학회논문지
• /
• 제19권3호
• /
• pp.563-570
• /
• 2024

본 논문은 운전자의 운행 보조 역할로 주행 가능한 차선 영역을 인식하고 추적하는 방법을 제안한다. 주요 주제는 차량 내부의 앞 유리 중앙에 설치된 카메라를 통해 실시간으로 획득한 영상을 기반으로 컴퓨터 비전과 딥 러닝 기술을 활용하여 주행 가능한 도로 영역을 예측하는 심층 기반 네트워크를 설계한다. 본 연구는 YOLOv8 알고리즘을 이용하여 카메라에서 직접 획득한 데이터로 훈련한 새로운 모델을 개발하는 것을 목표한다. 실제 도로에서 자신의 차량의 정확한 위치를 실제 영상과 일치하게 시각화하여 주행 가능한 차선 영역을 표시 및 추적함으로써 운전자 운행의 보조하는 역할을 기대한다. 실험 결과, 대부분 주행 가능한 도로 영역의 추적이 가능했으나 밤에 비가 심하게 오는 경우와 같은 악천후에서 차선이 정확하게 인식되지 않는 경우가 발생하여 이를 해결하기 위한 모델의 성능 개선이 필요하다.

• 한국융합학회논문지
• /
• 제10권1호
• /
• pp.103-113
• /
• 2019

차량 번호판 인식 카메라는 차량 번호판 내 문자와 숫자의 인식을 위하여 대상 차량의 이미지 취득을 목적으로 하는 전용 카메라를 말하며 대부분 단독 사용보다는 서버와 영상 분석 모듈과 결합된 시스템의 일부로 적용된다. 그러나 차량 번호판 인식을 위한 시스템 구축을 위해서는 취득 영상 관리 및 분석 지원을 위한 서버와 문자, 숫자의 추출 및 인식을 위한 영상 분석 모듈을 함께 구성하여야 하므로 구축을 위한 설비가 필요하고 초기 비용이 많이 든다는 문제점이 있다. 이에 본 연구에서는 카메라의 기능을 차량 번호판 인식에만 한정하지 않고 방범 기능을 함께 수행할 수 있도록 확장하고 카메라 단독으로도 두가지 기능 수행이 가능한 Edge Base의 임베디드형 융합 카메라를 개발한다. 임베디드형 융합 카메라는 선명한 영상 취득 및 빠른 데이터 전송을 위해 고해상도 4K IP 카메라를 탑재하고 오픈소스 신경망 알고리즘 기반의 다중 객체 인식을 위한 딥러닝 SW인 YOLO를 적용하여 차량 번호판 영역을 추출한 후 차량 번호판 내의 문자와 숫자를 검출하고 검출 정확도와 인식 정확도를 검증하여 CCTV 방범 기능과 차량 번호 인식 기능이 가능한지를 확인 하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.2086-2097
• /
• 2021

The current cultural assets are being restored depending on the opinions of experts (craftsmen). We intend to introduce digitalized artificial intelligence techniques, excluding the personal opinions of experts on reconstruction of such cultural properties. The first step toward restoring digitized cultural properties is separation. The restoration of cultural properties should be reorganized based on recorded documents, period historical backgrounds and regional characteristics. The cultural properties in the form of photographs or images should be collected by separating the background. In addition, when restoring cultural properties most of them depend a lot on the tendency of the restoring person workers. As a result, it often occurs when there is a problem in the accuracy and reliability of restoration of cultural properties. In this study, we propose a search method for learning stored digital cultural assets using AI technology. Pagoda was selected for restoration of Cultural Properties. Pagoda data collection was collected through the Internet and various historical records. The pagoda data was classified by period and region, and grouped into similar buildings. The collected data was learned by applying the well-known CNN algorithm for artificial intelligence learning. The pagoda search used Yolo Marker to mark the tower shape. The tower was used a total of about 100-10,000 pagoda data. In conclusion, it was confirmed that the probability of searching for a tower differs according to the number of pagoda pictures and the number of learning iterations. Finally, it was confirmed that the number of 500 towers and the epochs in training of 8000 times were good. If the test result exceeds 8,000 times, it becomes overfitting. All so, I found a phenomenon that the recognition rate drops when the enemy repeatedly learns more than 8,000 times. As a result of this study, it is believed that it will be helpful in data gathering to increase the accuracy of tower restoration.