• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.2
• /
• pp.69-78
• /
• 2024

Recently, the use of CCTV to prevent crowd accidents has been promoted, but research is needed to compensate for the spatial limitations of CCTV. In this study, pedestrian density was measured using drone footage, and based on a review of existing literature, a threshold of 6.7 people/m² was selected as the cutoff risk level for crowd accidents. In addition, we conducted a preliminary study to determine drone parameters and found that the pedestrian recognition rate was high at a drone altitude of 20 meters and an angle of 60°. Based on a previous study, we selected a target area with a high concentration of pedestrians and measured pedestrian density, which was found to be 0.27~0.30 per m². The study shows it is possible to measure risk levels by determining pedestrian densities in target areas using drone images. We believe drone surveillance will be utilized for crowd safety management in the near future.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.24 no.1
• /
• pp.160-166
• /
• 2010

Railroad level crossing systems are used to prevent train from collisions by informing pedestrians and vehicles of approaching trains on the level crossing. The current detection systems mostly use track-based electrical circuits to detect approaching trains. The making and breaking of the circuit when the train wheel passes along the track sends a signal to barriers that restrict access to the track. Unfortunately, this track-based signal system is vulnerable to malfunctions in certain situations. If the rail becomes rusted due to moisture, weather conditions, or infrequent use, the electrical circuit detection system could fail. Such a failure could lead to a train-vehicle or train-pedestrian collision. This paper suggests a replacement of the electrical circuit-based system with an infrared detection system. The research shows that an infrared detection system improves safety by reducing the frequency of detection failure of the alarming circuit to system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.668-674
• /
• 2022

Machine learning techniques using visual data have high usability in fields of industry and service such as scene recognition, fault detection, security and user analysis. Among these, user analysis through the videos from CCTV is one of the practical way of using vision data. Also, many studies about lightweight artificial neural network have been published to increase high usability for mobile and embedded environment so far. In this study, we propose the network combining the object detection and classification for mobile graphic processing unit. This network detects pedestrian and face, classifies age and gender from detected face. Proposed network is constructed based on MobileNet, YOLOv2 and skip connection. Both detection and classification models are trained individually and combined as 2-stage structure. Also, attention mechanism is used to improve detection and classification ability. Nvidia Jetson Nano is used to run and evaluate the proposed system.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.61-68
• /
• 2024

Despite the continuous efforts to mitigate pedestrian accidents at crosswalks, the problem persist. Vulnerable groups, including the elderly and disabled individuals are at a risk of being involved in traffic incidents. This paper proposes the implementation of object detection algorithm using the YOLO v5 model specifically for pedestrians using assistive devices like wheelchairs and crutches. For this research, data was collected and utilized through image crawling, Roboflow, and Mobility Aids datasets, which comprise of wheelchair users, crutch users, and pedestrians. Data augmentation techniques were applied to improve the model's generalization performance. Additionally, ensemble techniques were utilized to mitigate type 2 errors, resulting in 96% recall rate. This demonstrates that employing ensemble methods with a single YOLO model to target transportation-disadvantaged individuals can yield accurate detection performance without overlooking crucial objects.

• Journal of Digital Contents Society
• /
• v.12 no.3
• /
• pp.279-289
• /
• 2011

The latest hardware and software techniques are combined to give safe walking guidance and convenient service of realtime walking assistance system for visually impaired person. This system consists of obstacle detection and perception, place recognition, and sign recognition for pedestrian can safely walking to arrive at their destination. In this paper, we exploit the sign object detection system in subway station for sign recognition that one of the important factors of walking assistance system. This paper suggest the adaptive feature map that can be robustly extract the sign object region from complexed environment with light and noise. And recognize a sign using fast zernike moment features which is invariant under translation, rotation and scale of object during walking. We considered three types of signs as arrow, restroom, and exit number and perform the training and recognizing steps through adaboost classifier. The experimental results prove that our method can be suitable and stable for real-time system through yields on the average 87.16% stable detection rate and 20 frame/sec of operation time for three types of signs in 5000 images of sign database.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.389-395
• /
• 2022

Because of improvement of deep learning techniques, deep learning using computer vision such as classification, detection and segmentation has also been used widely at many fields. Expecially, automatic driving is one of the major fields that applies computer vision systems. Also there are a lot of works and researches to combine multiple tasks in a single network. In this study, we propose the network that predicts the individual depth of pedestrians and vehicles. Proposed model is constructed based on YOLOv3 for object detection and Monodepth for depth estimation, and it process object detection and depth estimation consequently using encoder and decoder based on hard parameter sharing. We also used attention module to improve the accuracy of both object detection and depth estimation. Depth is predicted with monocular image, and is trained using self-supervised training method.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.2
• /
• pp.128-133
• /
• 2021

Currently, autonomous vehicle markets are commercializing a third-level autonomous vehicle, but there is a possibility that an accident may occur even during fully autonomous driving due to stability issues. In fact, autonomous vehicles have recorded 81 accidents. This is because, unlike level 3, autonomous vehicles after level 4 have to judge and respond to emergency situations by themselves. Therefore, this paper proposes a vehicle crisis detection system(VCDS) that collects and stores information outside the vehicle through CNN, and uses the stored information and vehicle sensor data to output the crisis situation of the vehicle as a number between 0 and 1. The VCDS consists of two modules. The vehicle external situation collection module collects surrounding vehicle and pedestrian data using a CNN-based neural network model. The vehicle crisis situation determination module detects a crisis situation in the vehicle by using the output of the vehicle external situation collection module and the vehicle internal sensor data. As a result of the experiment, the average operation time of VESCM was 55ms, R-CNN was 74ms, and CNN was 101ms. In particular, R-CNN shows similar computation time to VESCM when the number of pedestrians is small, but it takes more computation time than VESCM as the number of pedestrians increases. On average, VESCM had 25.68% faster computation time than R-CNN and 45.54% faster than CNN, and the accuracy of all three models did not decrease below 80% and showed high accuracy.

• Journal of Broadcast Engineering
• /
• v.18 no.4
• /
• pp.535-542
• /
• 2013

In this paper, we proposed a advanced hardware engine architecture for high speed and high detection rate image recognitions. We adopted the HOG-LBP feature extraction algorithm and more parallelized architecture in order to achieve higher detection rate and high throughput. As a simulation result, the designed engine which can search about 90 frames per second detects 97.7% of pedestrians when false positive per window is $10^{-4}$.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.3
• /
• pp.98-110
• /
• 2018

In this paper, we propose both Dense grid model and Anchor model to improve the recognition rate of dynamic objects. Two experiments are conducted to study the performance of two proposed CNNs models (Dense grid model and Anchor model), which are to detect dynamic objects. In the first experiment, YOLO-v2 network is adjusted, and then fine-tuned on KITTI datasets. The Dense grid model and Anchor model are then compared with YOLO-v2. Regarding to the evaluation, the two models outperform YOLO-v2 from 6.26% to 10.99% on car detection at different difficulty levels. In the second experiment, this paper conducted further training of the models on a new dataset. The two models outperform YOLO-v2 up to 22.40% on car detection at different difficulty levels.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.4
• /
• pp.259-266
• /
• 2016

Recently, CCTV cameras are emplaced actively to reinforce security and intelligent surveillance systems have been under development for detecting and monitoring of the objects in the video. In this study, we propose a method for detection of upper body in intelligent surveillance system using FCM-based RBFNN classifier realized with the aid of HOG features. Firstly, HOG features that have been originally proposed to detect the pedestrian are adopted to train the unique gradient features about upper body. However, HOG features typically exhibit a very high dimension of which is proportional to the size of the input image, it is necessary to reduce the dimension of inputs of the RBFNN classifier. Thus the well-known PCA algorithm is applied prior to the RBFNN classification step. In the computer simulation experiments, the RBFNN classifier was trained using pre-classified upper body images and non-person images and then the performance of the proposed classifier for upper body detection is evaluated by using test images and video sequences.