• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• pp.289-296
• /
• 2022

In this paper, we developed a deep learning-based recyclable object detection model. The model is developed based on YOLOv5 that is a one-stage detector. The deep learning model detects and classifies the recyclable object into 7 categories: paper, carton, can, glass, pet, plastic, and vinyl. We propose two methods for recyclable object detection models to solve problems during training. Bounding Box CutMix solved the no-objects training images problem of Mosaic, a data augmentation used in YOLOv5. Standardized Distance-based IoU replaced DIoU using a normalization factor that is not affected by the center point distance of the bounding boxes. The recyclable object detection model showed a final mAP performance of 0.91978 with Bounding Box CutMix and 0.91149 with Standardized Distance-based IoU.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.904-911
• /
• 2022

Occlusion is one of the most challenging problems for computer vision-based construction monitoring. Due to the intrinsic dynamics of construction scenes, vision-based technologies inevitably suffer from occlusions. Previous researchers have proposed the occlusion handling methods by leveraging the prior information from the sequential images. However, these methods cannot be employed for construction object detection in non-sequential images. As an alternative occlusion handling method, this study proposes a data augmentation-based framework that can enhance the detection performance under occlusions. The proposed approach is specially designed for rebar occlusions, the distinctive type of occlusions frequently happen during construction worker detection. In the proposed method, the artificial rebars are synthetically generated to emulate possible rebar occlusions in construction sites. In this regard, the proposed method enables the model to train a variety of occluded images, thereby improving the detection performance without requiring sequential information. The effectiveness of the proposed method is validated by showing that the proposed method outperforms the baseline model without augmentation. The outcomes demonstrate the great potential of the data augmentation techniques for occlusion handling that can be readily applied to typical object detectors without changing their model architecture.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1079-1087
• /
• 2018

Recently, computer vision field based deep learning artificial intelligence has become a hot topic among various image analysis boundaries. In this study, flames are detected in fire images using the Faster R-CNN algorithm, which is used to detect objects within the image, among various image recognition algorithms based on deep learning. In order to improve fire detection accuracy through a small amount of data sets in the learning process, we use image augmentation techniques, and learn image augmentation by dividing into 6 types and compare accuracy, precision and detection rate. As a result, the detection rate increases as the type of image augmentation increases. However, as with the general accuracy and detection rate of other object detection models, the false detection rate is also increased from 10% to 30%.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.1-9
• /
• 2022

Ship detection in synthetic aperture radar (SAR) images is an important application in marine monitoring for the military and civilian domains. Over the past decade, object detection has achieved significant progress with the development of convolutional neural networks (CNNs) and lot of labeled databases. However, due to difficulty in collecting and labeling SAR images, it is still a challenging task to solve SAR ship detection CNNs. To overcome the problem, some methods have employed conventional data augmentation techniques such as flipping, cropping, and affine transformation, but it is insufficient to achieve robust performance to handle a wide variety of types of ships. In this paper, we present a novel and effective approach for deep SAR ship detection, that exploits label-rich Electro-Optical (EO) images. The proposed method consists of two components: a data augmentation network and a ship detection network. First, we train the data augmentation network based on conditional generative adversarial network (cGAN), which aims to generate additional SAR images from EO images. Since it is trained using unpaired EO and SAR images, we impose the cycle-consistency loss to preserve the structural information while translating the characteristics of the images. After training the data augmentation network, we leverage the augmented dataset constituted with real and translated SAR images to train the ship detection network. The experimental results include qualitative evaluation of the translated SAR images and the comparison of detection performance of the networks, trained with non-augmented and augmented dataset, which demonstrates the effectiveness of the proposed framework.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.539-540
• /
• 2022

본 논문에서는 Bounding Box가 포함된 증강 이미지 데이터셋을 손쉽게 생성할 수 있는 독립형 GUI 프로그램을 제안한다. 본 논문의 연구를 통하여 직관적인 마우스 클릭 동작만으로 적은 수의 이미지 파일과 annotation 파일로부터 필요한 만큼의 증강 이미지 데이터셋을 짧은 시간 내에 생성하고, 다양한 아키텍처의 학습용 이미지 데이터셋 증강에 적용할 수 있다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.2
• /
• pp.245-261
• /
• 2024

The COVID-19 pandemic has led to the widespread adoption of contactless transactions, resulting in a noticeable increase in the trend towards fully unmanned stores. In such stores, all operational processes are automated, primarily using artificial intelligence (AI) technology. However, this AI technology has several security vulnerabilities, which can be critical in the environment of fully unmanned stores. This paper analyzes the security vulnerabilities that AI-based fully unmanned stores may face, focusing particularly on the object detection model YOLO, demonstrating that Hiding Attacks and Altering Attacks using adversarial patches are possible. It is confirmed that objects with adversarial patches attached may not be recognized by the detection model or may be incorrectly recognized as other objects. Furthermore, the paper analyzes how Data Augmentation techniques can mitigate security threats by providing a defensive effect against adversarial patch attacks. Based on these results, we emphasize the need for proactive research into defensive measures to address the inherent security threats in AI technology used in fully unmanned stores.

• Journal of Software Engineering Society
• /
• v.29 no.1
• /
• pp.13-21
• /
• 2020

As CNN model is applied to various domains such as image classification and object detection, the performance of CNN model which is used to safety critical system like autonomous vehicles should be reliable. To evaluate that CNN model can sustain the performance in various environments, we developed an image data augmentation apparatus which generates images that is changed background. If an image which contains object is entered into the apparatus, it extracts an object image from the entered image and generate s composed images by synthesizing the object image with collected background images. A s a method to evaluate a CNN model, the apparatus generate s new test images from original test images, and we evaluate the CNN model by the new test image. As a case study, we generated new test images from Pascal VOC2007 and evaluated a YOLOv3 model with the new images. As a result, it was detected that mAP of new test images is almost 0.11 lower than mAP of the original test images.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.346-351
• /
• 2023

With the release of numerous open driving datasets, the demand for domain adaptation in perception tasks has increased, particularly when transferring knowledge from rich datasets to novel domains. However, it is difficult to solve the change 1) in the sensor domain caused by heterogeneous LiDAR sensors and 2) in the environmental domain caused by different environmental factors. We overcome domain differences in the semi-supervised setting with 3-stage model parameter training. First, we pre-train the model with the source dataset with object scaling based on statistics of the object size. Then we fine-tine the partially frozen model weights with copy-and-paste augmentation. The 3D points in the box labels are copied from one scene and pasted to the other scenes. Finally, we use the knowledge distillation method to update the student network with a moving average from the teacher network along with a self-training method with pseudo labels. Test-Time Augmentation with varying z values is employed to predict the final results. Our method achieved 3rd place in ECCV 2022 workshop on the 3D Perception for Autonomous Driving challenge.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.51-54
• /
• 2023

최근 딥러닝 기술의 발달로 물체 탐지를 위한 객체 인식 분야가 기계학습을 접목한 연구가 급격히 증가하고 있다. 하지만, 탐지하려는 물체가 다른 객체에 가려진 경우와 같이 특수한 상황에 대한 데이터의 수량이 부족하여 성능 저하를 야기한다는 점과, 객체 탐지 수행 과정에서 작은 객체의 탐지가 어렵다는 한계점이 있다. 본 연구는 전술한 문제점을 보완할 방법을 제안한다. 데이터 증강 기법을 이용하여 클래스가 부족한 데이터의 양을 늘려 학습 데이터를 증강시켰다. 한편, SRGAN을 사용하여 작은 객체를 확대시킨 뒤 이미지를 합성시켜 데이터를 구성하였다. 제안된 방법은 PyTorch 환경에서 YOLOv5를 수행한 결과, 객체 탐지 성능이 향상되는 것을 확인할 수 있었다.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.37 no.3
• /
• pp.261-273
• /
• 2024

This paper is an experimental study on the improvement of smoke and flame detection from different materials with YOLO. For the study, images of fires occurring in various materials were collected through an open dataset, and experiments were conducted by changing the main factors affecting the performance of the fire object detection model, such as the bounding box, polygon, and data augmentation of the collected image open dataset during data preprocessing. To evaluate the model performance, we calculated the values of precision, recall, F1Score, mAP, and FPS for each condition, and compared the performance of each model based on these values. We also analyzed the changes in model performance due to the data preprocessing method to derive the conditions that have the greatest impact on improving the performance of the fire object detection model. The experimental results showed that for the fire object detection model using the YOLOv5s6.0 model, data augmentation that can change the color of the flame, such as saturation, brightness, and exposure, is most effective in improving the performance of the fire object detection model. The real-time fire object detection model developed in this study can be applied to equipment such as existing CCTV, and it is believed that it can contribute to minimizing fire damage by enabling early detection of fires occurring in various materials.