• The KIPS Transactions:PartB
• /
• v.19B no.3
• /
• pp.177-182
• /
• 2012

We propose effective motion and observation models for the position of a WiFi-equipped smartphone user in large indoor environments. Three component motion models provide better proposal distribution of the pedestrian's motion. Our Gaussian interpolation-based observation model can generate likelihoods at locations for which no calibration data is available. These models being incorporated into the particle filter framework, our WiFi fingerprint-based localization algorithm can track the position of a smartphone user accurately in large indoor environments. Experiments carried with an Android smartphone in a multi-story building illustrate the performance of our WiFi localization algorithm.

• The Journal of the Korea Contents Association
• /
• v.14 no.3
• /
• pp.451-462
• /
• 2014

In this paper, Coordinated Semi-Actuated Signal Control algorithm was developed and evaluated. According to the analysis of simulation, the coordinated semi-actuated signal control led to reduced vehicle delay as the difference of traffic volume between major and minor streets was getting bigger. But when there was relatively high traffic volume, or the equivalent amount of traffic volume on major and minor streets, optimized pre-timed signal control was verified to lower delay times compared to coordinated semi-actuated signal control; however, it might increase pedestrian delay. Therefore, the coordinated semi-actuated signal control should be implemented at intersections where traffic volume is relatively low.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.1
• /
• pp.1-9
• /
• 2017

This paper proposes to improve the performance of a strap down inertial navigation system using a foot-mounted low-cost inertial measurement unit/magnetometer by configuring an attitude and heading reference system. To track position accurately and for attitude estimations, considering different dynamic constraints, magnetic measurement and a zero velocity update technique is used. A conventional strap down method based on integrating angular rate to determine attitude will inevitably induce long-term drift, while magnetometers are subject to short-term orientation errors. To eliminate this accumulative error, and thus, use the navigation system for a long-duration mission, a hybrid configuration by integrating a miniature micro electromechanical system (MEMS)-based attitude and heading detector with the conventional navigation system is proposed in this paper. The attitude and heading detector is composed of three-axis MEMS accelerometers and three-axis MEMS magnetometers. With an absolute algorithm based on gravity and Earth's magnetic field, rather than an integral algorithm, the attitude detector can obtain an absolute attitude and heading estimation without drift errors, so it can be used to adjust the attitude and orientation of the strap down system. Finally, we verify (by both formula analysis and from test results) that the accumulative errors are effectively eliminated via this hybrid scheme.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.2
• /
• pp.239-246
• /
• 2015

Video based object detection is basic technology of implementing smart CCTV system. Various features and algorithms are developed to detect object, however computations of them increase with the performance. In this paper, performances of object detection algorithms with GPU and CPU are compared. Adaboost and SVM algorithm which are widely used to detect pedestrian detection are implemented with CPU and GPU, and speeds of detection processing are compared for the same video. As results of frame rate comparison of Adaboost and SVM algorithm, it is shown that the frame rate with GPU is faster than CPU.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.9
• /
• pp.2189-2196
• /
• 2014

In this paper, a VLIW(Very Long Instruction Word) vision coprocessor which can efficiently accelerate computer vision algorithm for automotive is designed. The VLIW coprocessor executes four instructions per clock cycle via 8-stage pipelined structure and has 36 integer and floating-point instructions to accelerate computer vision algorithm for pedestrian detection. The processor has about 300-MHz operating frequency and about 210,900 gates under 45nm CMOS technology and its estimated performance is 1.2 GOPS(Giga Operations Per Second). The vision system composed of vision primitive engine and eight VLIW coprocessors can execute pedestrian detection at 25~29 frames per second(FPS). Because the VLIW coprocessor has high detection rate and loosely coupled interface with host processor, it can be efficiently applicable to a wide range of vision applications.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.4
• /
• pp.315-321
• /
• 2017

This paper is a study on the design and realization of Pedestrian navigation service system for the visually impaired. As it is an user interface considering visually impaired, voice recognition functioned smartphone was used as the input tool and the Osteoacusis headset, which can vocally guide directions while recognizing the surrounding environment sound, was used as the output tool. Unlike the pre-existing pedestrian navigation smartphone apps, the developed system guides walking direction by the scale of the left and right stereo sound of the headset wearing, and the voice guidance about the forked or curved path is given several meters before according to the speed of the user, and the user is immediately warned of walking opposite direction or proceeding off the path. The system can acquire stable and reliable directional information using the motion tracker with the dynamic heading accuracy of 1.5 degrees. In order to overcome GPS position error, we proposed a robust trajectory planning algorithm for position error. Experimental results for the developed system show that the average directional angle error is 6.82 degrees (standard deviation: 5.98) in the experimental path, which can be stated that it stably navigated the user relatively.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.599-607
• /
• 2021

Street-view images, which are omnidirectional scenes centered on a specific location on the road, can provide various obstacle information for the pedestrians. Pedestrian network data for the navigation services should reflect the up-to-date obstacle information to ensure the mobility of pedestrians, including people with disabilities. In this study, the object detection model was trained for the bollard as a major obstacle in Seoul using street-view images and a deep learning algorithm. Also, a process for updating information about the presence and number of bollards as obstacle properties for the crosswalk node through spatial matching between the detected bollards and the pedestrian nodes was proposed. The missing crosswalk information can also be updated concurrently by the proposed process. The proposed approach is appropriate for crowdsourcing data as the model trained using the street-view images can be applied to photos taken with a smartphone while walking. Through additional training with various obstacles captured in the street-view images, it is expected to enable efficient information update about obstacles on the road.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.25 no.3
• /
• pp.309-316
• /
• 2017

In shuttle vans designed to transport children, the recognition of a child's approach and departure is very important. Ultrasonic sensors are generally used for a short distance around a vehicle. Although ultrasonic sensors are cheaper than other ADAS sensors, the number of sensors installed in a van should be optimized. In order to recognize the presence of a child around a shuttle van, this paper proposes the placement of ultrasonic sensors in the van. Considering the turning radius of the van and the distance from each sensor to a child, collision risk is classified as 'safe', 'warning', and 'danger'. The sensor placement and the recognition algorithm are verified in a virtual driving environment.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.1
• /
• pp.62-68
• /
• 2012

In this paper, a detection method of a pedestrian safety road marking was proposed. The proposed algorithm uses laser range and reflectivity of a range finder (LRF). For a detection of crosswalk marking and stop line, the DFT (Discrete Fourier Transform) of reflectivity and cross-correlation method between the reference replica and the measured reflectivity are used. A speed bump is detected through measuring an altitude difference of two LRFs which have the different tilted angle. Furthermore, we proposed a velocity constrained a detection method of a speed bump. Finally, the proposed methods are tested in on-line, on the pavement of a road. The considered road markings are wholly detected. The localization errors of both road markings are smaller than 0.4 meter.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.2
• /
• pp.961-968
• /
• 2018

Recently, researches on automatic recognition of human activities have been actively carried out with the emergence of various intelligent systems. Since a large amount of visual data can be secured through Closed Circuit Television, it is required to recognize human behavior in a dynamic situation rather than a static situation. In this paper, we propose new intelligent human activity recognition model using the trajectory information extracted from the video sequence. The proposed model consists of three steps: segmentation and partitioning of trajectory step, feature extraction step, and behavioral learning step. First, the entire trajectory is fuzzy partitioned according to the motion characteristics, and then temporal features and spatial features are extracted. Using the extracted features, four pedestrian behaviors were modeled by decision tree learning algorithm and performance evaluation was performed. The experiments in this paper were conducted using Caviar data sets. Experimental results show that trajectory provides good activity recognition accuracy by extracting instantaneous property and distinctive regional property.