• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1184-1186
• /
• 2022

횡단보도에서의 보행자 교통사고 방지를 위한 다양한 방법들이 연구되고 있다. 본 논문에서는 점멸 신호등 상황에서 보행자 교통사고를 감소시키기 위해 영상을 이용한 심층 신경망 기반 횡단보도 보행자 검출 방법을 소개한다. YOLOv5 와 Faster R-CNN 각각을 기반으로 다양한 버전의 횡단보도 보행자 검출기를 구현하고, 이번 실험에서 중점이 되는 이들의 수행 시간을 비교 평가하고 mAP@0.5 가 어느 정도인지 판단하여 가장 적합한 모델을 판단한다. 실험 결과 실시간 처리 측면에서 YOLOs 모델이 84 fps 를 달성함으로써 실시간 보행자 검출에 가장 좋은 성능을 보였다. 횡단보도의 상황은 상시 빠르게 변하므로 가장 빠른 처리 성능을 기록한 YOLOv5s 모델이 실시간 횡단보도 보행자 검출 시스템에 가장 적합한 것으로 판단된다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.45-48
• /
• 2019

Detection of crosswalk is an important issue for the blind to walk without the help of others. There is a braille block on the sidewalk, which helps the blind to walk. On the other hand, crosswalk is more dangerous due to the moving vehicles. However, there is no appropriate means to induce the blind. In this paper, we propose a method to detect crosswalk in front of a blind and estimate its direction using an image sensor. We adopt multi-ROIs and make their binary versions. In order to determine whether it is a crosswalk, two features are extracted; one is the number of crossing in the binary image and the other is the ratio of white area. We can also estimate the direction of the crosswalk through the slope of the projection data. We evaluated the performance using experimental dataset and the proposed algorithm showed 80% accuracy of detection.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.141-148
• /
• 2021

This paper presents a method to detect zebra-crossing using deep learning which combines SegNet and ResNet. For the blind, a safe crossing system is important to know exactly where the zebra-crossings are. Zebra-crossing detection by deep learning can be a good solution to this problem and robotic vision-based assistive technologies sprung up over the past few years, which focused on specific scene objects using monocular detectors. These traditional methods have achieved significant results with relatively long processing times, and enhanced the zebra-crossing perception to a large extent. However, running all detectors jointly incurs a long latency and becomes computationally prohibitive on wearable embedded systems. In this paper, we propose a model for fast and stable segmentation of zebra-crossing from captured images. The model is improved based on a combination of SegNet and ResNet and consists of three steps. First, the input image is subsampled to extract image features and the convolutional neural network of ResNet is modified to make it the new encoder. Second, through the SegNet original up-sampling network, the abstract features are restored to the original image size. Finally, the method classifies all pixels and calculates the accuracy of each pixel. The experimental results prove the efficiency of the modified semantic segmentation algorithm with a relatively high computing speed.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.1
• /
• pp.11-18
• /
• 2022

The use of multi-spectral cameras is essential for day and night pedestrian detection. In this paper, a color camera and a thermal imaging infrared camera were used to detect pedestrians near a crosswalk for 24 hours at an intersection with a high risk of traffic accidents. For pedestrian detection, the YOLOv5 object detector was used, and the detection performance was improved by using color images and thermal images at the same time. The proposed system showed a high performance of 0.940 mAP in the day/night multi-spectral (color and thermal image) pedestrian dataset obtained from the actual crosswalk site.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.06a
• /
• pp.107-108
• /
• 2017

횡단보도 인근에서는 보행취약자의 사고가 끊이지 않고 있으며 사고예방 및 사고의 절감을 위하여 선제적안 안전시스템의 개발이 요구되고 있다. 선제적 안전시스템의 개발을 위하여 빅데이터를 이용한 안전 데이터 도출, 영상분석을 이용한 보행자 행동특성 모니터링 시스템의 개발 및 사고감소를 위한 안전 시스템 개발이 진행되고 있다. 보행취약자 위험상황 판단에 대한 정의를 빅데이터 분석을 통해 도출하고 횡단보도 주변 안전 시스템의 개발을 기존 시스템에 적용 및 새로운 시스템을 개발하며 이에 적합한 딥러닝 영상분석 시스템을 개발하였다. 본 논문에서는 딥러닝 모델을 이용하여 객체의 검출, 분석을 수행하는 객체 검출부, 객체의 포즈와 행동을 보여주는 영상 분석부로 구성되어 있으며 기존 모델을 응용하여 최적화한 모델을 적용하였다. 딥러닝 모델의 구동은 리눅스 서버에서 운용되고 있으며 딥러닝 모델 구동을 위한 여러 툴을 적용하였다. 본 연구를 통하여 보행취약자의 검출, 추적, 보행취약자의 포즈 및 위험상황을 인식하고 안전시스템과 연계할 수 있도록 구성하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.3
• /
• pp.271-278
• /
• 2014

In spite of that stop line and crosswalk should be aware of the most basic objects in transportation system, its features extracted are very limited. In addition to image-based recognition technology, laser and RF, GPS/INS recognition technology, it is difficult to recognize. For this reason, the limited research in this area has been done. In this paper, the algorithm to recognize the stop line and crosswalk is designed and implemented using image-based recognition technology with the images input through a vision sensor. This algorithm consists of three functions.; One is to select the area, in advance, needed for feature extraction in order to speed up the data processing, 'Region of Interest', another is to process the images only that white color is detected more than a certain proportion in order to remove the unnecessary operation, 'Color Pattern Inspection', the other is 'Feature Extraction and Recognition', which is to extract the edge features and compare this to the previously-modeled one to identify the stop line and crosswalk. For this, especially by using case based feature comparison algorithm, it can identify either both stop line and crosswalk exist or just one exists. Also the proposed algorithm is to develop existing researches by comparing and analysing effect of in-vehicle camera installation and changes in recognition rate of distance estimation and various constraints such as backlight and shadow.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.5
• /
• pp.631-637
• /
• 2010

In this paper, We propose a method of motion interpretation of pedestrian for active traffic signal control. We detect pedestrian object in a movie of crosswalk area by using the code book method and acquire contour information. To do this stage fast, we use parallel processing based on CUDA (Compute Unified Device Architecture). And we remove shadow which causes shape distortion of objects. Shadow removed object is judged by using the hilbert scan distance whether to human or noise. If the objects are judged as a human, we analyze pedestrian objects' motion, face area feature, waiting time to decide that they have intetion to across a crosswalk for pdestrians. Traffic signal can be controlled after judgement.

• Journal of Korean Society for Geospatial Information Science
• /
• v.10 no.3 s.21
• /
• pp.41-51
• /
• 2002

Recently, many studies extracting the geography information using digital aerial image have been implemented. But it is very difficult that automatically recognizing objects using edge detection method on the aerial image, and so that work have practiced manually or semi-automatically. Therefore, in this study, we have removed impedimental elements for recognition using the image which overlapped the significant information bands of brightness-sliced aerial images, then have developed the algorithm which can automatically recognize and extract road information and we will try to apply that method when we develope a system. For this, first of all, we have developed the 'template conformal-transformation moving operator' for automatically recognizing crosswalk area from crosswalk band image and the 'window normal search algorithm' which is able to track road area based on long-side length of crosswalk, so that we have proposed the method that can extract directly the road information from the aerial image.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.755-758
• /
• 2002

보행자 추적은 무인 자동차 시스템, 보안 또는 감시 시스템, 횡단보도 신호제어 시스템 등 실세계의 다양한 응용 분야에서 사용될 수 있다. 본 논문에서는 걸어다니는 보행자의 움직임 정보를 이용하여 다수의 보행자를 추적하는 새로운 방법을 제안한다. 보행자의 움직임 정보는 연속된 두 개의 비디오 프레임간의 그레이 레벨 차를 이용하여 추하고, 이를 통하여 물체를 검출한다. 검출된 물체에는 보행자뿐만 아니라 다른 이동 물체가 포함될 수 있으므로 프로젝션 히스토그램(PH: Projection Histogram)을 생성한 후 보행자 유형을 기반으로 PH를 분석하여 보행자를 검출, 추적한다. 제안된 방법의 성능 평가를 위해서 복잡한 도시 환경 영상에 적용하고 그 성공적인 결과를 보인다.

• The Journal of Korea Robotics Society
• /
• v.12 no.2
• /
• pp.217-227
• /
• 2017

Crosswalk detection is an important part of the Pedestrian Protection System in autonomous vehicles. Different methods of crosswalk detection have been introduced so far using crosswalk edge features, the distance between crosswalk blocks, laser scanning, Hough Transformation, and Fourier Transformation. However, most of these methods failed to detect crosswalks accurately, when they are damaged, faded away or partly occluded. Furthermore, these methods face difficulties when applying on real road environment where there are lot of vehicles. In this paper, we solve this problem by first using a region based binarization technique and x-axis histogram to detect the candidate crosswalk areas. Then, we apply Support Vector Machine (SVM) based classification method to decide whether the candidate areas contain a crosswalk or not. Experiment results prove that our method can detect crosswalks in different environment conditions with higher recognition rate even they are faded away or partly occluded.