• Korean Journal of Remote Sensing
• /
• v.39 no.3
• /
• pp.297-309
• /
• 2023

The degradation of coastal ecosystems and fishery environments is accelerating due to the recent phenomenon of invertebrate grazers. To effectively monitor and implement preventive measures for this phenomenon, the adoption of remote sensing-based monitoring technology for extensive maritime areas is imperative. In this study, we compared and analyzed the robustness of deep learning-based object detection modelsfor detecting and monitoring invertebrate grazersfrom underwater videos. We constructed an image dataset targeting seven representative species of invertebrate grazers in the coastal waters of South Korea and trained deep learning-based object detection models, You Only Look Once (YOLO)v7 and YOLOv8, using this dataset. We evaluated the detection performance and speed of a total of six YOLO models (YOLOv7, YOLOv7x, YOLOv8s, YOLOv8m, YOLOv8l, YOLOv8x) and conducted robustness evaluations considering various image distortions that may occur during underwater filming. The evaluation results showed that the YOLOv8 models demonstrated higher detection speed (approximately 71 to 141 FPS [frame per second]) compared to the number of parameters. In terms of detection performance, the YOLOv8 models (mean average precision [mAP] 0.848 to 0.882) exhibited better performance than the YOLOv7 models (mAP 0.847 to 0.850). Regarding model robustness, it was observed that the YOLOv7 models were more robust to shape distortions, while the YOLOv8 models were relatively more robust to color distortions. Therefore, considering that shape distortions occur less frequently in underwater video recordings while color distortions are more frequent in coastal areas, it can be concluded that utilizing YOLOv8 models is a valid choice for invertebrate grazer detection and monitoring in coastal waters.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.193-205
• /
• 2023

A large amount of floating debris from land-based sources during heavy rainfall has negative social, economic, and environmental impacts, but there is a lack of monitoring systems for floating debris accumulation areas and amounts. With the recent development of artificial intelligence technology, there is a need to quickly and efficiently study large areas of water systems using drone imagery and deep learning-based object detection models. In this study, we acquired various images as well as drone images and trained with You Only Look Once (YOLO)v5s and the recently developed YOLO7 and YOLOv8s to compare the performance of each model to propose an efficient detection technique for land-based floating debris. The qualitative performance evaluation of each model showed that all three models are good at detecting floating debris under normal circumstances, but the YOLOv8s model missed or duplicated objects when the image was overexposed or the water surface was highly reflective of sunlight. The quantitative performance evaluation showed that YOLOv7 had the best performance with a mean Average Precision (intersection over union, IoU 0.5) of 0.940, which was better than YOLOv5s (0.922) and YOLOv8s (0.922). As a result of generating distortion in the color and high-frequency components to compare the performance of models according to data quality, the performance degradation of the YOLOv8s model was the most obvious, and the YOLOv7 model showed the lowest performance degradation. This study confirms that the YOLOv7 model is more robust than the YOLOv5s and YOLOv8s models in detecting land-based floating debris. The deep learning-based floating debris detection technique proposed in this study can identify the spatial distribution of floating debris by category, which can contribute to the planning of future cleanup work.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.237-239
• /
• 2019

최근 인터넷 영상 매체가 발전하고 대중화되며 이를 통한 광고 효과가 커지고 있다. 이들 영상에 관련된 광고를 자동으로 연결할 수 있다면 효과적일 것이다. 본 논문은 딥러닝 검출 툴을 적용한 영상 카테고리 분류 기법을 제안한다. 이 기법은 주어진 영상을 몇 가지 카테고리로 분류하고, 분류 정보를 바탕으로 관련성이 높은 광고를 연결지어, 결과적으로 영상 시청자에게 맞춤형 광고를 제시한다.

• Journal of information and communication convergence engineering
• /
• v.18 no.3
• /
• pp.147-154
• /
• 2020

In this study, we created a system that can determine the number of vehicles entering and departing a charging station in real time for solving waiting time problems during refueling. Accordingly, we use the You Only Look Once object detection algorithm to detect and count the number of vehicles in the charging station and send the data to the Firebase Realtime Database. The result is shown using an Android application that provides a map function with the Kakao Maps API at the user interface side. Our system has an accuracy of 91% and an average response time of 3.1 s. Therefore, this system can be used by drivers to determine the availability of a charging station and to identify the charging station with the least waiting time for charging their vehicle.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.924-927
• /
• 2018

본 논문에서는 거동이 불편한 환자나 장애인들을 위해 신체에 착용하는 부가적인 장비 없이 멀리 있는 가전을 직접 움직이지 않고 편리하게 제어할 수 있는 RGB-D 카메라를 활용한 손 인식과 딥러닝 기반 IoT 장치 컨트롤 시스템을 제안한다. 특히, 제어하고자 하는 장치의 위치를 알기 위하여 YOLO 알고리즘을 이용하여 장치를 인식한다. 또한 그와 동시에 RGB-D 카메라의 라이브러리를 이용하여 사용자의 손을 인식, 현재 사용자 손의 위치와 사용자가 취하는 손동작을 통하여 해당 위치의 장치를 제어한다.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.521-523
• /
• 2018

본 논문은 보이스피싱 발생 후의 대처 방안이 아닌, 범죄 행위 자체의 예방을 목적으로 하는 신원 허가 후의 자동인출기 시스템을 제안한다. 범죄예방 현금인출기(ATM)의 작동과정은 크게 두 가지이다. 첫째, YOLO Detection System을 이용하여 학습된 데이터에 기반하여, 사용자의 얼굴에서 선글라스와 마스크를 검출한다. 둘째, 미리 학습된 범죄자 모델 데이터에 앞서 사용자의 신원을 조회하고 ATM의 사용허가를 내준다. 혹은 주요지명 피의자일 경우, 경찰에 실시간 안내를 주어 범죄 수사를 용이하게 한다.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.664-665
• /
• 2018

효과적인 에너지 절약 시스템을 구현하기 위해서는 실내의 재실자 존재 여부를 판별할 수 있는 근거가 필요하다. 본 연구에서는 천장에 광각렌즈 카메라를 설치하여 재실자 수를 탐지하는 방법을 소개한다. 인식 기술은 합성 곱 신경망의 한 종류인 Yolo v2를 사용하였으며, 건물 내부의 다양한 장소의 천장에 카메라 센서를 설치하여 필요한 데이터를 수집하였다. 수집한 2,200장의 데이터를 기준으로 학습을 수행하였고, 인식의 정확도를 측정해본 결과 96.15%의 정확도와 91.72%의 재현율을 얻어냈다.

• International Journal of Advanced Culture Technology
• /
• v.9 no.3
• /
• pp.298-304
• /
• 2021

Currently, to prevent the spread of COVID-19 virus infection, gathering of more than 5 people in the same space is prohibited. The purpose of this paper is to measure the distance between objects using the Yolov5 model for processing real-time images with OpenCV in order to restrict the distance between several people in the same space. Also, Utilize Euclidean distance calculation method in DeepSORT and OpenCV to minimize occlusion. In this paper, to detect the distance between people, using the open-source COCO dataset is used for learning. The technique used here is using the YoloV5 model to measure the distance, utilizing DeepSORT and Euclidean techniques to minimize occlusion, and the method of expressing through visualization with OpenCV to measure the distance between objects is used. Because of this paper, the proposed distance measurement method showed good results for an image with perspective taken from a higher position than the object in order to calculate the distance between objects by calculating the y-axis of the image.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.227-241
• /
• 2021

Object detection techniques based on deep learning such as YOLO have high detection performance and precision in a single channel video stream. In order to expand to multiple channel object detection in real-time, however, high-performance hardware is required. In this paper, we propose a novel back-end server framework, a real-time AI vision platform (RAVIP), which can extend the object detection function from single channel to simultaneous multi-channels, which can work well even in low-end server hardware. RAVIP assembles appropriate component modules from the RODEM (real-time object detection module) Base to create per-channel instances for each channel, enabling efficient parallelization of object detection instances on limited hardware resources through continuous monitoring with respect to resource utilization. Through practical experiments, RAVIP shows that it is possible to optimize CPU, GPU, and memory utilization while performing object detection service in a multi-channel situation. In addition, it has been proven that RAVIP can provide object detection services with 25 FPS for all 16 channels at the same time.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.4
• /
• pp.151-156
• /
• 2021

Low-end IoT devices do not have enough computation and memory resources for DNN learning and inference. Integer quantization of real-type neural network models can reduce model size, hardware computational burden, and power consumption. This paper describes the design and implementation of a web-based quantization platform for CNN deep learning accelerator chips. In the web service platform, we implemented visualization of the model through a convenient UI, analysis of each step of inference, and detailed editing of the model. Additionally, a data augmentation function and a management function of files that store models and inference intermediate results are provided. The implemented functions were verified using three YOLO models.