• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2016년도 춘계학술대회
• /
• pp.363-366
• /
• 2016

본 논문에서는 보행자 검출 시, 교차 상황에서 발생하는 문제 해결을 위한 방법을 제안한다. 영상에서 특정 보행자를 검출하는 동안 다른 보행자와 교차하는 경우, 기존에 검출하던 보행자가 아닌 다른 보행자를 잘못 검출하는 문제가 발생한다. 문제 해결을 위해 제안하는 방법은 다음과 같다. 먼저, 검출할 특정 보행자를 bounding box로 선택하고 해당영역을 템플릿으로 추출한다. HOG를 이용하여 영상에서 보행자들을 검출하고, 후보영역으로 지정한다. 후보영역으로 지정된 보행자들을 앞서 템플릿으로 추출한 특정보행자와 비교하여 검출할 보행자를 최종 선택한다. 비교에는 템플릿 매칭, 히스토그램 비교와 LBP를 이용한다.

• 대한임베디드공학회논문지
• /
• 제18권5호
• /
• pp.259-265
• /
• 2023

Pedestrian detection is used to effectively detect pedestrians in various situations based on deep learning. Pedestrian detection has difficulty detecting pedestrians due to problems such as camera performance, pedestrian description, height, and occlusion. Even in the same pedestrian, performance in detecting them can differ according to the height of the pedestrian. The height of general pedestrians encompasses various scales, such as those of infants, adolescents, and adults, so when the model is applied to one group, the extraction of data becomes inaccurate. Therefore, this study proposed a pedestrian detection method that fine-tunes the pedestrian area by Refining Layer and Feature Concatenation to consider various heights of pedestrians. Through this, the score and location value for the pedestrian area were finely adjusted. Experiments on four types of test data demonstrate that the proposed model achieves 2-5% higher average precision (AP) compared to Faster R-CNN and DRPN.

• 한국ITS학회:학술대회논문집
• /
• 한국ITS학회 2008년도 제7회 추계학술대회 및 정기총회
• /
• pp.371-375
• /
• 2008

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2015년도 춘계학술대회
• /
• pp.564-566
• /
• 2015

신호등은 적색, 녹색일 때 다른 의미를 나타낸다. 자동차 운전자와 횡단보도의 보행자는 신호등의 신호에 따라 움직이거나 멈춰야한다. 그러나 이러한 신호를 무시하거나 보지 않을 경우 사고가 발생할 확률이 높다. 또한 곡선형 횡단보도에서는 적외선 센서를 이용한 안내 방송 시스템을 설치하기가 어려운 실정이다. 본 논문에서는 카메라를 이용하여 보행자를 검지하는 방법을 설계 및 구현한다. 보행철주에 설치된 카메라가 보행자를 촬영하고, 촬영된 이미지를 통해 보행자 검지구간을 설정한다. 제안하는 시스템을 사용하면 곡선형 횡단보도에서 보행자 검지를 하는데 효율적이다.

• Journal of Positioning, Navigation, and Timing
• /
• 제13권3호
• /
• pp.289-299
• /
• 2024

In the Pedestrian Dead Reckoning (PDR)/Global Positioning System (GPS)/Wi-Fi-integrated navigation system for indoor/outdoor continuous positioning of pedestrians, the process of detecting outliers in measurements is very important. When accurate location information from measurements is used, reliable correction data can be generated during the fusion filtering process. However, abnormal measurements may occur in certain situations, such as indoor/outdoor transitions, which can degrade filter performance and lead to significant errors in the estimated position. To address this issue, this paper proposes a method for detecting outliers in measurements based on Rényi Divergence (RD). When the deviation of the RD value is large, the measurements are considered outliers, and positioning is performed using only pure PDR. Based on experiments conducted with real data, it was confirmed that outliers were effectively detected for abnormal measurements, leading to an improvement in the performance of pedestrian navigation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권8호
• /
• pp.3769-3789
• /
• 2018

Social pedestrian groups are the basic elements that constitute a crowd; therefore, detection of such groups is scientifically important for modeling social behavior, as well as practically useful for crowd video understanding. A social group refers to a cluster of members who tend to keep similar motion state for a sustained period of time. One of the main challenges of social group detection arises from the complex dynamic variations of crowd patterns. Therefore, most works model dynamic groups to analysis the crowd behavior, ignoring the existence of stationary groups in crowd scene. However, in this paper, we propose a novel unified framework for detecting social pedestrian groups in crowd videos, including dynamic and stationary pedestrian groups, based on spatiotemporal-oriented energy measurements. Dynamic pedestrian groups are hierarchically clustered based on energy flow similarities and trajectory motion correlations between the atomic groups extracted from principal spatiotemporal-oriented energies. Furthermore, the probability distribution of static spatiotemporal-oriented energies is modeled to detect stationary pedestrian groups. Extensive experiments on challenging datasets demonstrate that our method can achieve superior results for social pedestrian group detection and crowd video classification.

• 전기학회논문지P
• /
• 제65권1호
• /
• pp.66-71
• /
• 2016

According to the development of depth sensing devices and depth estimation technology, depth information becomes more important for object detection in computer vision. In terms of recognition rate, pedestrian detection methods have been improved more accurately. However, the methods makes slower detection time. So, many researches have overcome this problem by using GPU. Here, we propose a real-time pedestrian detection algorithm that does not rely on GPU. First, the depth-weighted distance map is used for detecting expected human regions. Next, human detection is performed on the regions. The performance for the proposed approach is evaluated and compared with the previous methods. We show that proposed method can detect human about 7 times faster than conventional ones.

• International Journal of Contents
• /
• 제9권3호
• /
• pp.1-9
• /
• 2013

In this paper, we propose a fast and accurate system for detecting pedestrians from a static image. Histogram of Oriented Gradients (HOG) is a well-known feature for pedestrian detection systems but extracting HOG is expensive due to its high dimensional vector. It will cause long processing time and large memory consumption in case of making a pedestrian detection system on high resolution image or video. In order to deal with this problem, we use Principal Components Analysis (PCA) technique to reduce the dimensionality of HOG. The output of PCA will be input for a linear SVM classifier for learning and testing. The experiment results showed that our proposed method reduces processing time but still maintains the similar detection rate. We got twenty five times faster than original HOG feature.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권12호
• /
• pp.5978-5999
• /
• 2018

Pedestrian detection is a challenging area in the intelligent vehicles domain. During the last years, many works have been proposed to efficiently detect motion in images. However, the problem becomes more complex when it comes to detecting moving areas while the vehicle is also moving. This paper presents a variational optical flow-based method for motion estimation in vehicular traffic scenarios. We introduce a framework for detecting motion areas with small and large displacements by computing optical flow using a multilevel architecture. The flow field is estimated at the shortest level and then successively computed until the largest level. We include a filtering parameter and a warping process using bicubic interpolation to combine the intermediate flow fields computed at each level during optimization to gain better performance. Furthermore, we find that by including a penalization function, our system is able to effectively reduce the presence of outliers and deal with all expected circumstances in real scenes. Experimental results are performed on various image sequences from Daimler Pedestrian Dataset that includes urban traffic scenarios. Our evaluation demonstrates that despite the complexity of the evaluated scenes, the motion areas with both moving and static camera can be effectively identified.

• 전기전자학회논문지
• /
• 제18권1호
• /
• pp.106-113
• /
• 2014

보행자 검출기는 보안이 필요한 곳에서 모니터링을 하거나 특정 장소를 드나드는 사람의 수를 셀 때, 운전 중 차도에 뛰어드는 사람을 감지할 때 등 상황에 따라 여러 목적으로 응용될 수 있다. 이와 관련한 연구는 많이 진행되어 왔지만, 임베디드 시스템에서는 제한된 컴퓨팅 능력으로 인해 검출 속도가 느리다는 문제가 있다. 본 논문에서는 입력 영상에서 배경 부분을 빠르게 제거하여 검출 속도를 향상하는 방법과 ARM SIMD 아키텍처에서 NEON 병렬화 기법을 이용하여 검출 속도를 향상하는 방법을 제시한다. 제시한 방법으로 구현한 검출기는 INRIA Person Dataset을 이용하여 테스트한 결과 기존에 비해 3.01배의 향상된 속도를 나타냈다.