• The KIPS Transactions:PartB
• /
• v.11B no.3
• /
• pp.317-326
• /
• 2004

This paper presents a new method for the detection of multiple pedestrians and tracking of a specific pedestrian using color information from a moving camera. We first extract motion vector on the input image using BMA. Next, a difference image is calculated on the basis of the motion vector. The difference image is converted to a binary image. The binary image has an unnecessary noise. So, it is removed by means of the proposed noise deletion method. Then, we detect pedestrians through the projection algorithm. But, if pedestrians are very adjacent to each other, we separate them using RGB color information. And we track a specific pedestrian using RGB color information in center region of it. The experimental results on our test sequences demonstrated the high efficiency of our approach as it had shown detection success ratio of 97％ and detection failure ratio of 3％ and excellent tracking.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.10
• /
• pp.162-170
• /
• 2013

In recent years, the interests and needs of the Pedestrian Protection System (PPS), which is mounted on the vehicle for the purpose of traffic safety improvement is increasing. In this paper, we propose a pedestrian candidate window extraction and unit cell histogram based HOG descriptor calculation methods. At pedestrian detection candidate windows extraction stage, the bright ratio of pedestrian and its circumference region, vertical edge projection, edge factor, and PCA reconstruction image are used. Dalal's HOG requires pixel based histogram calculation by Gaussian weights and trilinear interpolation on overlapping blocks, But our method performs Gaussian down-weight and computes histogram on a per-cell basis, and then the histogram is combined with the adjacent cell, so our method can be calculated faster than Dalal's method. Our PCA reconstruction error based pedestrian detection candidate window extraction method efficiently classifies background based on the difference between pedestrian's head and shoulder area. The proposed method improves detection speed compared to the conventional HOG just using image without any prior information from camera calibration or depth map obtained from stereo cameras.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.103-111
• /
• 2023

Mountains area, especially walking in open space is important for special active field which is based on mountain terrain. Recent research on pedestrian-path includes elements about pedestrian and various environment by analyzing network, but it is mainly focusing on limited space except for data-poor terrain like a mountain terrain. This paper proposes an architecture to generate walking path considering the slope for mountain terrain open space through virtual network made of mesh. This architecture shows that it reflects real terrain more effective when measuring distance using slope and is possible to generate mountain walking path using open space unlike other existing services, and is verified through the test. The proposed architecture is expected to utilize for pedestrian-path generation way considering mountain terrain open space in case of distress, mountain rescue and tactical training and so on.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.01a
• /
• pp.265-268
• /
• 2011

본 논문은 시각 장애인 및 보도 보행에 어려움을 갖는 사람들에게 안전한 보도 보행을 돕기 위한 보도 및 차도 영역 추출을 위해 보도 및 차도의 라인검출 기법을 제안한다. 사람의 눈높이에서 영상을 취득, 자연영상에서 입력된 잡음 및 노이즈를 제거하고, 캐니 에지 맵 추출, 허프 변환을 통해 보도/차도의 라인을 추출한다. 추출된 라인은 본 논문에서 제안한 방법으로 유효라인을 얻게 되며, 얻어진 유효 라인의 교점을 통해 소실점 영역을 생성, 이후 추출되는 라인의 기준이 된다. 제안된 방법은 자연영상의 보도 위치에서 보도와 차도의 올바른 라인을 추출하는데 강인함을 실험을 통해 검증하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2010.07a
• /
• pp.121-124
• /
• 2010

본 논문은 시각 장애인 및 보도 보행에 어려움을 갖는 사람들에게 안전한 보도 보행을 돕기 위한 보도 및 차도 영역 추출을 위해 보도 및 차도의 라인검출 기법을 제안한다. 사람의 눈높이에서 영상을 취득, 자연영상에서 입력된 잡음 및 노이즈를 제거하고, 캐니 에지 맵 추출, 허프 변환을 통해 보도/차도의 라인을 추출한다. 추출된 라인은 본 논문에서 제안한 방법으로 유효라인을 얻게 되며, 얻어진 유효 라인의 결합으로 삼각 표본을 생성하여 보도의 영역을 추출 하게 된다. 제안된 방법은 자연영상의 보도 위치에서 보도와 차도의 올바른 라인을 추출하는데 강인함을 실험을 통해 검증하였다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.4
• /
• pp.37-44
• /
• 2012

There are approximately 25,724 shelters to which people can be quickly evacuated for safety in case of emergency across the nation, and Seoul has about 3,870 shelters. Those nationwide shelters are located at a point within a five-minute radius for quick evacuation. Seoul's shelter capacity can hold 285% of its population. The problem is, however, that there is no knowing how many shelters are reachable within five minutes when considering walking speed according to individual differences in age, height, health state, and physical condition. In addition, available service areas become different according to the spatial allocation and distribution of shelters with possible vulnerable points. This study thus defined the pedestrian walking speed at 1m/s, 1.3m/s, and 2m/s by reviewing previous studies and conducted network analysis of the Location Allocation Model with the designated shelters and road networks in Seoul. The results identified the shelter service and vulnerable areas in each administrative district of Seoul according to walking speeds. It was analyzed that the vulnerable areas in which the elderly could not reach a shelter were more than twice as big as those of adult men and women with a fast walking speed.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.6
• /
• pp.84-92
• /
• 2007

The gait recognition is presented for human identification from a sequence of noisy silhouettes segmented from video by capturing at a distance. The proposed gait recognition algorithm gives better performance than the baseline algorithm because of segmentation of the object by using multiple modules; i) motion detection, ii) object region detection, iii) head detection, and iv) active shape models, which solve the baseline algorithm#s problems to make background, to remove shadow, and to be better recognition rates. For the experiment, we used the HumanID Gait Challenge data set, which is the largest gait benchmarking data set with 122 objects, For realistic simulation we use various values for the following parameters; i) viewpoint, ii) shoe, iii) surface, iv) carrying condition, and v) time.

• Journal of Korean Society of Transportation
• /
• v.33 no.3
• /
• pp.276-283
• /
• 2015

Pedestrians have been exposed to dangerous traffic environments, in which walking spaces in a city decrease without improved facilities even though cars increase. Such poor walking environments are deadly dangerous to the vulnerable as well as the non-vulnerable. This study analyzed the road facilities use characteristics according to a type of vulnerability in order to improve traffic safety and walking environment for vulnerable pedestrians. This study surveyed the vulnerable in terms of issues that they encountered on existing walkways and conducted the analytic hierarchy process (AHP), which took all quantitative and qualitative variables into account. The results of Level-3 analysis were showed that the elderly and the disabled were partially similar; both felt most inconvenient at enter-exit sections, steep walkway and bad paved walkway. Unlike those results, people with children and/or infants answered that overpass or underpass walkways without lifting facilities were most inconvenient walking environments.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.534-539
• /
• 2008

This paper is about intelligent hexapod robot for the support walking of the aged person. The robot using various sensors and small camera has various abilities of forward backward walking, turing left or right, control the speed of walking, avoiding the obstacles and detecting risky situation of fire or gas. To let the aged feel soft and safe walking, we used special servo motor and developed hexapod walking mechanism and effective algorithm.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.10
• /
• pp.1173-1182
• /
• 1988

The stability, energetic efficiency and walking volume are affected by the geometric structure of legs of a walking robot. A quadruped walking robot is considered to have large stability margin among the walking robots and pantograph leg permits large walk stroke and mutually independent vertical and horizontal movements, but the kinematic characteristics are difficult to analyze. Graphical method may be useful to characterize three dimensional legged motion of the pantograph mechanism. We present the modelling method for three different quadruped robots with pantograph legs that have different joints mechanism. The modeled robots are animated by a path that is planned with respect to the center of body. In particular, graphical animation incorporates leg control to rotation and side walking and uses the window of Sun-3 system for displaying joint information.