• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4816-4834
• /
• 2020

This paper proposes transfer learning and fine-tuning techniques for a deep learning model to detect three distinct brain tumors from Magnetic Resonance Imaging (MRI) scans. In this work, the recent YOLOv4 model trained using a collection of 3064 T1-weighted Contrast-Enhanced (CE)-MRI scans that were pre-processed and labeled for the task. This work trained with the partial 29-layer YOLOv4-Tiny and fine-tuned to work optimally and run efficiently in most platforms with reliable performance. With the help of transfer learning, the model had initial leverage to train faster with pre-trained weights from the COCO dataset, generating a robust set of features required for brain tumor detection. The results yielded the highest mean average precision of 93.14%, a 90.34% precision, 88.58% recall, and 89.45% F1-Score outperforming other previous versions of the YOLO detection models and other studies that used bounding box detections for the same task like Faster R-CNN. As concluded, the YOLOv4-Tiny can work efficiently to detect brain tumors automatically at a rapid phase with the help of proper fine-tuning and transfer learning. This work contributes mainly to assist medical experts in the diagnostic process of brain tumors.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.7-11
• /
• 2022

Object detection technology is one of the main research topics in the field of computer vision and has established itself as an essential base technology for implementing various vision systems. Recent DNN (Deep Neural Networks)-based algorithms achieve much higher recognition accuracy than traditional algorithms. However, it is well-known that the DNN model inference operation requires a relatively high computational power. In this paper, we analyze the inference time complexity of the state-of-the-art object detection architecture Yolov7 in various environments. Specifically, we compare and analyze the time complexity of four types of the Yolov7 model, YOLOv7-tiny, YOLOv7, YOLOv7-X, and YOLOv7-E6 when performing inference operations using CPU and GPU. Furthermore, we analyze the time complexity variation when inferring the same models using the Pytorch framework and the Onnxruntime engine.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.128-132
• /
• 2023

Recently, with the development of deep learning technology, research on pedestrian attribute recognition technology using deep neural networks has been actively conducted. Existing pedestrian attribute recognition techniques can be obtained in such a way as global-based, regional-area-based, visual attention-based, sequential prediction-based, and newly designed loss function-based, depending on how pedestrian attributes are detected. It is known that the performance of these pedestrian attribute recognition technologies varies greatly depending on the type of backbone network that constitutes the deep neural networks model. Therefore, in this paper, several backbone networks are applied to the baseline pedestrian attribute recognition model and the performance changes of the model are analyzed. In this paper, the analysis is conducted using Resnet34, Resnet50, Resnet101, Swin-tiny, and Swinv2-tiny, which are representative backbone networks used in the fields of image classification, object detection, etc. Furthermore, this paper analyzes the change in time complexity when inferencing each backbone network using a CPU and a GPU.

• Transactions on Semiconductor Engineering
• /
• v.2 no.1
• /
• pp.17-20
• /
• 2024

This paper presents a novel lightweight object detection model tailored for low-powered edge devices, addressing the limitations of traditional resource-intensive computer vision models. Our proposed detector, inspired by the Single Shot Detector (SSD), employs a compact yet robust network design. Crucially, it integrates an 'enhancer block' that significantly boosts its efficiency in detecting smaller objects. The model comprises two primary components: the Light_Block for efficient feature extraction using Depth-wise and Pointwise Convolution layers, and the Enhancer_Block for enhanced detection of tiny objects. Trained from scratch on the Udacity Annotated Dataset with image dimensions of 300x480, our model eschews the need for pre-trained classification weights. Weighing only 5.5MB with approximately 0.43M parameters, our detector achieved a mean average precision (mAP) of 27.7% and processed at 140 FPS, outperforming conventional models in both precision and efficiency. This research underscores the potential of lightweight designs in advancing object detection for edge devices without compromising accuracy.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.291-292
• /
• 2024

국내의 산재 사고 사망 비율 중 대부분은 건설업이 차지하고 있으며 사망 원인 중 42.9%는 추락사가 차지하고 있다. 따라서 국내 사고 사망을 예방하기 위해서는 노동자의 생명을 지켜주는 안전 장비의 착용 여부가 중요하다. 본 논문에서는 객체 탐지에 사용되는 YOLO v4와 YOLO v4-TINY 알고리즘과 영상 처리에 사용되는 OpenCV를 이용하여 실시간 영상에서 안전모 미착용 인원을 감지하고 관리자에게 알려주는 시스템을 개발하였다. 이 시스템을 활용하여 건설 현장에서 현장 카메라로 안전모 미착용 인원을 실시간으로 검출하여 경고하므로써 작업자의 안전에 기여할 수 있다.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.468-474
• /
• 2022

In this paper, we propose a method to implement a real-time fire alarm system using deep learning. The deep learning image dataset for fire alarms acquired 1,500 sheets through the Internet. If various images acquired in a daily environment are learned as they are, there is a disadvantage that the learning accuracy is not high. In this paper, we propose a fire image data expansion method to improve learning accuracy. The data augmentation method learned a total of 2,100 sheets by adding 600 pieces of learning data using brightness control, blurring, and flame photo synthesis. The expanded data using the flame image synthesis method had a great influence on the accuracy improvement. A real-time fire detection system is a system that detects fires by applying deep learning to image data and transmits notifications to users. An app was developed to detect fires by analyzing images in real time using a model custom-learned from the YOLO V4 TINY model suitable for the Edge AI system and to inform users of the results. Approximately 10% accuracy improvement can be obtained compared to conventional methods when using the proposed data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.355-366
• /
• 2022

This paper proposes a microcode-based neural network accelerator controller for artificial intelligence accelerators that can be reconstructed using a programmable architecture and provide the advantages of low-power and ultra-small chip size. In order for the target accelerator to support various neural network models, the neural network model can be converted into microcode through microcode compiler and mounted on accelerator to control the operators of the accelerator such as datapath and memory access. While the proposed controller and accelerator can run various CNN models, in this paper, we tested them using the YOLOv2-Tiny CNN model. Using a system clock of 200 MHz, the Controller and accelerator achieved an inference time of 137.9 ms/image for VOC 2012 dataset to detect object, 99.5ms/image for mask detection dataset to detect wearing mask. When implementing an accelerator equipped with the proposed controller as a silicon chip, the gate count is 618,388, which corresponds to 65.5% reduction in chip area compared with an accelerator employing a CPU-based controller (RISC-V).

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.63-71
• /
• 2021

Among drone autonomous flight technologies, obstacle avoidance is a very important technology that can prevent damage to drones or surrounding environments and prevent danger. Although the LiDAR sensor-based obstacle avoidance method shows relatively high accuracy and is widely used in recent studies, it has disadvantages of high unit price and limited processing capacity for visual information. Therefore, this paper proposes an obstacle avoidance algorithm for drones using camera-based PPO(Proximal Policy Optimization) reinforcement learning, which is relatively inexpensive and highly scalable using visual information. Drone, obstacles, target points, etc. are randomly located in a learning environment in the three-dimensional space, stereo images are obtained using a Unity camera, and then YOLov4Tiny object detection is performed. Next, the distance between the drone and the detected object is measured through triangulation of the stereo camera. Based on this distance, the presence or absence of obstacles is determined. Penalties are set if they are obstacles and rewards are given if they are target points. The experimennt of this method shows that a camera-based obstacle avoidance algorithm can be a sufficiently similar level of accuracy and average target point arrival time compared to a LiDAR-based obstacle avoidance algorithm, so it is highly likely to be used.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.536-539
• /
• 2023

딥러닝 기술은 더 많은 분야와 과제에 적용되기 위해서 네트워크는 더 복잡하고 거대한 형태로 발전해왔다. YOLOv7-tiny과 같은 객체탐지 네트워크는 다양한 객체와 환경에서 활용하기 위해 COCO 데이터 세트를 대상으로 발전해왔다. 그러나 본 논문에서 적용할 모델은 임베디드 보드 환경에서 실시간으로 1개의 Class를 대상으로 객체를 탐지하는 네트워크 모델이 찾고자 프루닝을 적용하였다. 모델의 프루닝을 할 필터를 찾기 위해 본 논문에서는 클러스터링을 통한 필터 프루닝 방법을 제안한다. 본 논문의 제안 방법을 적용했을 때 기준 모델보다 정확도가 7.6% 감소하였으나, 파라미터가 1% 미만으로 남고, 속도는 2.1배 증가함을 확인하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.187-188
• /
• 2021

최근 COVID19 상황에서 생활 속 거리두기가 강조되면서 관광지나 다중이용시설 등의 이용객 수와 밀집도를 파악하는 것이 중요해지고 있다. 따라서, CCTV 영상을 활용하여 저렴한 비용으로 다중이용시설의 출입자수에 대한 정보를 실시간으로 모니터링할 수 있는 시스템이 필요하다. 이를 위해 본 논문에서는 딥러닝 실시간 객체인식기술을 활용한 출입자의 수와 동선을 측정하여 출입자에 대한 통계정보를 웹브라우저를 통해 제공하는 시스템을 개발하였다. 실시간 객체인식기술인 YOLOv4와 YOLOv4-tiny 알고리즘을 Nvidia사의 Jetson AGX Xavier 와 데스크톱PC에 적용하여 각 알고리즘의 FPS와 객체 인식률을 비교 분석 하여 알고리즘을 적용하였다.