• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.3
• /
• pp.83-95
• /
• 2022

This paper proposes a system that performs object detection and distance estimation for application to autonomous vehicles. Object detection is performed by a network that adjusts the split grid to the input image ratio using the characteristics of the recently actively used deep learning model YOLOv4, and is trained to a custom dataset. The distance to the detected object is estimated using a bounding box and homography. As a result of the experiment, the proposed method improved in overall detection performance and processing speed close to real-time. Compared to the existing YOLOv4, the total mAP of the proposed method increased by 4.03%. The accuracy of object recognition such as pedestrians, vehicles, construction sites, and PE drums, which frequently occur when driving to the city center, has been improved. The processing speed is approximately 55 FPS. The average of the distance estimation error was 5.25m in the X coordinate and 0.97m in the Y coordinate.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.9
• /
• pp.77-85
• /
• 2011

In this paper, we propose an region segmentation and texture based feature extraction method which split the pavement and roadway from the camera which equipped to the visually impaired person during a walk. We perform the hough transformation method for detect the boundary between pavement and roadway, and devide the segmented region into 3-level according to perspective. Next step, split into pavement and roadway according to the extracted texture feature of segmented regions. Our walking assistance system use rotation-invariant LBP and GLCM texture features for compare the characteristic of pavement block with various pattern and uniformity roadway. Our proposed method show that can segment two regions with illumination invariant in day and night image, and split there regions rotation and occlution invariant in complexed outdoor image.

• Journal of Digital Contents Society
• /
• v.15 no.4
• /
• pp.449-455
• /
• 2014

Detection of moving objects is a fundamental task in most of the computer vision applications, such as video surveillance, activity recognition and human motion analysis. This is a difficult task due to many challenges in realistic scenarios which include irregular motion in background, illumination changes, objects cast shadows, changes in scene geometry and noise, etc. In this paper, we propose an foreground extraction algorithm based on codebook, a database of information about background pixel obtained from input image sequence. Initially, we suppose a first frame as a background image and calculate difference between next input image and it to detect moving objects. The resulting difference image may contain noises as well as pure moving objects. Second, we investigate a codebook with color and brightness of a foreground pixel in the difference image. If it is matched, it is decided as a fault detected pixel and deleted from foreground. Finally, a background image is updated to process next input frame iteratively. Some pixels are estimated by input image if they are detected as background pixels. The others are duplicated from the previous background image. We apply out algorithm to PETS2009 data and compare the results with those of GMM and standard codebook algorithms.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.25-27
• /
• 2021

With the recent development of deep learning technology, computer vision-based AI technologies have been studied to analyze the abnormal behavior of objects in image information acquired through CCTV cameras. There are many cases where surveillance cameras are installed in dangerous areas or security areas for crime prevention and surveillance. For this reason, companies are conducting studies to determine major situations such as intrusion, roaming, falls, and assault in the surveillance camera environment. In this paper, we propose a real-time abnormal behavior analysis algorithm using object detection and tracking method.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.65 no.1
• /
• 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.

• 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.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.5
• /
• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.8
• /
• pp.385-392
• /
• 2016

Market analysis for a business plain is required for the success in the modern world. Most important part in this analysis is pedestrian traffic counting. A traditional way for this is counting it in person. However, it causes high labor costs and mistakes. This paper proposes an automatic algorithm to measure the pedestrian traffic count using images with webcam. The proposed algorithm is composed of two parts: pedestrian area detection and movement tracking. In pedestrian area detection, moving blobs are extracted and pedestrian areas are detected using HoG features and Adaboost algorithm. In movement tracking, multi-level matching and false positive removal are applied to track pedestrian areas and count the pedestrian traffic. Multi-level matching is composed of 3 steps: (1) the similarity calculation between HoG area, (2) the similarity calculation of the estimated position with Kalman filtering, and (3) the similarity calculation of moving blobs in the pedestrian area detection. False positive removal is to remove invalid pedestrian area. To analyze the performance of the proposed algorithm, a comparison is performed with the previous human area detection and tracking algorithm. The proposed algorithm achieves 83.6% accuracy in the pedestrian traffic counting, which is better than the previous algorithm over 11%.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.179-186
• /
• 2016

A study is to research crash barriers for vehicles that prevent road breakaway of vehicles and protect car passengers and pedestrians as absorbing impulse. Protection performance tests on vehicle passengers were simulated by using a LS-DYNA program. Through repetitive simulation on various speed and angles, passenger protection performance according to different impact condition was contemplated. Variable setting for the simulation was calculated as the mean weight of domestic car sales. By analyzing NASS (National Automotive Sampling System) of NHTSA (National Highway Traffic Safety Administration) of the U.S., the actual speed and collision angle section of accidents were computed. As a result, we confirmed that THIV (Theoretical Head Impact Velocity) and PHD (Post-impact Head Deceleration) are increased according to the impact speed and angle. Also, when the vehicle hit the guardrail post, we could be confirmed that the passenger protection performance greatly decreased.

• Journal of Digital Contents Society
• /
• v.14 no.4
• /
• pp.455-462
• /
• 2013

This paper proposes a detection system that, by determining whether a dangerous act is being carried out among other pedestrians in the images captured using CCTV, provides pre-warnings and establishes emergency measures. To determine the presence of a dangerous act, after setting zones of interest and danger zones within those zones of interest, the danger level is determined in accordance with the range of encroachment upon detecting an object. Especially, this research aims at detecting a suicide jump from the bridge and extends to detecting a dangerous act among pedestrians from detecting a dangerous act of only one person with no one in the previous research. This system classifies the status into 3 levels as safe, alert, and danger according to the amount of part being over the bridge railing. If a situation is deemed as warning-worthy and emergency, the integrated control center is immediately alerted to facilitate prevention in advance.