• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.519-521
• /
• 2019

자율주행 자동차에서의 보행자 인식 및 사람의 행동 인식과 같은 분야 등에 대한 연구들이 활발하게 진행되고 그에 기반을 둔 기술들이 많이 개발되고 있다. 그리고 대부분의 연구에서는 사람에 대한 경계 박스를 검출한다. 영상에서 사람의 유무 혹은 위치를 판단하는 문제에서는 경계 박스만을 검출하는 것이 효율적일 수 있으나 경계 박스는 행동 인식과 같은 분야에 사용하기에는 많은 정보의 손실이 발생할 수 있다. 본 논문에서는 U-NET 구조의 딥러닝 모델을 사용해 경계 박스로 인한 정보 손실을 줄일 수 있는 보행자 분할 방법을 제안한다. 모델의 학습을 위해 2017 COCO 데이터셋의 사람 카테고리를 사용하였으며 Penn-Fudan 보행자 데이터셋을 이용하여 제안 방법을 테스트하였으며 기존의 방법들과 비교하여 의미 있는 결과를 얻었다.

• Tunnel and Underground Space
• /
• v.31 no.5
• /
• pp.374-384
• /
• 2021

In this study, we propose a new approach for automatic fracture detection in CT scan images of rock specimens. This approach is built on top of two-stage object detection deep learning algorithm called Faster R-CNN with a major modification of using rotated bounding box. The use of rotated bounding box plays a key role in the future work to overcome several inherent difficulties of fracture segmentation relating to the heterogeneity of uninterested background (i.e., minerals) and the variation in size and shape of fracture. Comparing to the commonly used bounding box (i.e., axis-align bounding box), rotated bounding box shows a greater adaptability to fit with the elongated shape of fracture, such that minimizing the ratio of background within the bounding box. Besides, an additional benefit of rotated bounding box is that it can provide relative information on the orientation and length of fracture without the further segmentation and measurement step. To validate the applicability of the proposed approach, we train and test our approach with a number of CT image sets of fractured granite specimens with highly heterogeneous background and other rocks such as sandstone and shale. The result demonstrates that our approach can lead to the encouraging results on fracture detection with the mean average precision (mAP) up to 0.89 and also outperform the conventional approach in terms of background-to-object ratio within the bounding box.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.957-960
• /
• 2017

디지털 비디오의 발전이 가속됨에 따라, 비디오 샷 경계 검출은 비디오 분석 및 카타로깅 등 여러 분야에 있어 필수적인 요소가 되었다. 기존 샷 경계 검출 방법들은 잠음이나 카메라 혹은 물체의 이동, 그리고 색상의 급격한 변화 등에 민감한 성능을 보인다. 본 논문에서는 개선된 지역 방향 패턴 기반(eLDP) 검출 방법을 제안한다. 제안하는 방법은 RGB 색상의 일부와 eLDP의 특징을 결합해 더욱 강인한 샷 경계 검출 성능을 보였다. 또한, 셋톱박스 품질검사 시 필요한 채널 간 동기화의 신뢰성을 높였고, 실시간으로 검사하면서도 안정적인 샷 경계 검출이 가능함을 입증하였다.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1994.10a
• /
• pp.111-115
• /
• 1994

본 연구에서는 보강 되지 않은 사각단면 박스 구조물, 보강된 사각 단면 박스 구조물, 그리고 보강된 요철형 단면 박스 구좀ㄹ에 대하여 양단 고정(clamped-clamped)과 일단 고정 타단 자유(clamped-free)의 경계 조건에 대해 실험적 진동 해석을 수행 하였으며, 유한요소 code인 ANSYS를 이용하여 유한 요소 해석을 수행하였다. 또한 유한 요소 해석과 실험을 통하여 신뢰성이 검증된 요소를 각 박스 구조물에 적용하여 각 경우에 대한 응력해석을 유한요소법을 이용하여 수행하였다. 또한 각각의 경우에 보강재의 개수 및 단면 형상 변화, 그리고 두께 변화가 진동과 응력에 미치는 민감도를 연구하였다.

• Land and Housing Review
• /
• v.14 no.4
• /
• pp.95-102
• /
• 2023

Numerous investigations have explored the integration of machine leaning algorithms with high-resolution drone image for object detection in urban settings. However, a prevalent limitation in vehicle extraction studies involves the reliance on bounding boxes rather than instance segmentation. This limitation hinders the precise determination of vehicle direction and exact boundaries. Instance segmentation, while providing detailed object boundaries, necessitates labour intensive labelling for individual objects, prompting the need for research on automating unsupervised instance segmentation in vehicle extraction. In this study, a novel approach was proposed for vehicle extraction utilizing unsupervised SVM classification applied to vehicle bounding boxes in drone images. The method aims to address the challenges associated with bounding box-based approaches and provide a more accurate representation of vehicle boundaries. The study showed promising results, demonstrating an 89% accuracy in vehicle extraction. Notably, the proposed technique proved effective even when dealing with significant variations in spectral characteristics within the vehicles. This research contributes to advancing the field by offering a viable solution for automatic and unsupervised instance segmentation in the context of vehicle extraction from image.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.5
• /
• pp.747-753
• /
• 2018

In the license-plate recognition systems for automobile black Image, the license-plate image frequently has a shadow due to outdoor environments which are frequently changing. Such a shadow makes unpredictable errors in the segmentation process of individual characters and numbers of the license plate image, and reduces the overall recognition rate. In this paper, to improve the recognition rate in these circumstance, a license-plate image binarization algorithm is proposed removing the shadow effectively. The propose algorithm splits the license-plate image into the regions with the shadow and without. To find out the boundary of two regions, the algorithm estimates the curve for shadow boundary using the least-squares method. The simulation is performed for the license-plate image having its shadow, and the results show much higher recognition rate than the previous algorithm.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.5
• /
• pp.13-20
• /
• 2019

Recently, object detection technology based on CNN has been actively studied. Object detection technology is used as an important technology in autonomous vehicles, intelligent image analysis, and so on. In this paper, we propose a rotation change robust object detection system by applying MI-FL (Moment Invariant-Feature Layer) to SSD (Single Shot Multibox Detector) which is one of CNN-based object detectors. First, the features of the input image are extracted based on the VGG network. Then, a total of six feature layers are applied to generate bounding boxes by predicting the location and type of object. We then use the NMS algorithm to get the bounding box that is the most likely object. Once an object bounding box has been determined, the invariant moment feature of the corresponding region is extracted using MI-FL, and stored and learned in advance. In the detection process, it is possible to detect the rotated image more robust than the conventional method by using the previously stored moment invariant feature information. The performance improvement of about 4 ~ 5% was confirmed by comparing SSD with existing SSD and MI-FL.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.364-368
• /
• 2018

In this paper, we use Faster R-CNN that is one of object detection algorithm and OpenCV that purposes computer vision, to implement the system that can detect danger when a vehicle attempts to change lanes into its own lane in videos of highway, national road, general road and etc. Also, the performance of implemented system is evaluated to prove that the performance is not bad.

• Journal of Korean Society of Steel Construction
• /
• v.13 no.1
• /
• pp.41-52
• /
• 2001

In this paper the analysis of laminate composite folded plates with arbitrary angle connection like box girder is studied by finite strip method Total stiffness of laminated plate is obtained by integration of the stiffness in each layer or lamina through laminate thickness and total stiffness in each layer or lamina through laminate thickness and total tiffness matrix is obtained by substitutionto equilibrium equation derived from the minimum total potential energy theorem. The assumed displacement functions for a finite strip method in plate or box girder analysis are combinations of one-way polynomial functions in the transverse direction and harmonic functions in the span-wise direction. Finite strip method with the merits of the simplification in modeling and the reduction of analytical time is accurate in the analysis of laminate composite folded plates shaped like box firders.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.50-53
• /
• 2022

In order to detect an object in yolv5, a process of annotating location information on an existing image is required when learning an image. The most representative method is to draw a bounding box on an image to store location information as meta information. However, if the boundary of the object is ambiguous, it will be difficult to make a bounding box. A representative example would be to classify parts that are not fire and parts that are fire. Therefore, in this paper, images of 100 samples judged to have caught fire were learned by varying the number of boxes. The results showed better fire detection performance in the model where the bounding box was trained by annotating it with three boxes by segmenting it slightly more than annotating it with one box by holding the edge as large as possible during annotating it with one box.