• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.81-89
• /
• 2021

Under natural conditions, Apple detection has the problems of occlusion and small object detection difficulties. This paper proposes an improved model based on SSD. The SSD backbone network VGG16 is replaced with the ResNet50 network model, and the receptive field structure RFB structure is introduced. The RFB model amplifies the feature information of small objects and improves the detection accuracy of small objects. Combined with the attention mechanism (SE) to filter out the information that needs to be retained, the semantic information of the detection objectis enhanced. An improved SSD algorithm is trained on the VOC2007 data set. Compared with SSD, the improved algorithm has increased the accuracy of occlusion and small object detection by 3.4% and 3.9%. The algorithm has improved the false detection rate and missed detection rate. The improved algorithm proposed in this paper has higher efficiency.

• ETRI Journal
• /
• v.37 no.2
• /
• pp.212-221
• /
• 2015

As the amount of re-sequencing genome data grows, minimizing the execution time of an analysis is required. For this purpose, recent computing systems have been adopting both high-performance coprocessors and host processors. However, there are few applications that efficiently utilize these heterogeneous computing resources. This problem equally refers to the work of single nucleotide polymorphism (SNP) detection, which is one of the bottlenecks in genome data processing. In this paper, we propose a method for speeding up an SNP detection by enhancing the utilization of heterogeneous computing resources often used in recent high-performance computing systems. Through the measurement of workload in the detection procedure, we divide the SNP detection into several task groups suitable for each computing resource. These task groups are scheduled using a window overlapping method. As a result, we improved upon the speedup achieved by previous open source applications by a magnitude of 10.

• Journal of Advanced Information Technology and Convergence
• /
• v.10 no.1
• /
• pp.15-23
• /
• 2020

In this paper, we propose a new method to detect traffic accidents in video from vehicle-mounted cameras (vehicle black box). We use the distance between vehicles to determine whether an accident has occurred. To calculate the position of each vehicle, we use object detection and tracking method. By the way, in a crowded road environment, it is so difficult to decide an accident has occurred because of parked vehicles at the edge of the road. It is not easy to discriminate against accidents from non-accidents because a moving vehicle and a stopped vehicle are mixed on a regular downtown road. In this paper, we try to increase the accuracy of the vehicle accident detection by using not only the motion of the surrounding vehicle but also ego-motion as the input of the Recurrent Neural Network (RNN). We improved the accuracy of accident detection compared to the previous method.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.723-726
• /
• 2021

현재 단일 이미지에서 Object Detection 성능은 매우 좋은 편이다. 하지만 동영상에서는 처리 속도가 너무 느리고 임베디드 시스템에서는 real-time이 힘든 상황이다. 연구 논문에서는 하이엔드 GPU에서 다른 기능 없이 YOLO만 구동했을 때 real-time이 가능하다고 하지만 실제 사용자들은 상대적으로 낮은 사양의 GPU를 사용하거나 CPU를 사용하기 때문에 일반적으로는 자연스러운 real-time을 하기가 힘들다. 본 논문에서는 이러한 제한점을 해결하고자 계산량이 많은 Object Detection model 사용을 줄이는 방안은 제시하였다. 현재 Video영상에서 Object Detection을 수행할 때 매 frame마다 YOLO모델을 구동하는 것에서 YOLO 사용을 줄임으로써 계산 효율을 높였다. 본 논문의 알고리즘은 카메라가 움직이거나 배경이 바뀌는 상황에서도 사용이 가능하다. 속도는 최소2배에서 ~10배이상까지 개선되었다.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.11
• /
• pp.4377-4384
• /
• 2014

According to the World Health Organization (WHO), 1.37 million people died of lung cancer all around the world in 2008, occupying the first place in all cancer-related deaths. However, this number might be decreased if patients were detected earlier and treated appropriately. Unfortunately, traditional imaging techniques are not sufficiently satisfactory for early detection of lung cancer because of limitations. As one alternative, breath volatile organic compounds (VOCs) may reflect the biochemical status of the body and provide clues to some diseases including lung cancer at early stage. Early detection of lung cancer based on breath analysis is becoming more and more valued because it is non-invasive, sensitive, inexpensive and simple. In this review article, we analyze the limitations of traditional imaging techniques in the early detection of lung cancer, illustrate possible mechanisms of the production of VOCs in cancerous cells, present evidence that supports the detection of such disease using breath analysis, and summarize the advances in the study of E-noses based on gas sensitive sensors. In conclusion, the analysis of breath VOCs is a better choice for the early detection of lung cancer compared to imaging techniques. We recommend a more comprehensive technique that integrates the analysis of VOCs and non-VOCs in breath. In addition, VOCs in urine may also be a trend in research on the early detection of lung cancer.

• Journal of Sensor Science and Technology
• /
• v.28 no.3
• /
• pp.157-163
• /
• 2019

The LiDAR sensor, which is widely regarded as one of the most important sensors, has recently undergone active commercialization owing to the significant growth in the production of ADAS and autonomous vehicle components. The LiDAR sensor technology involves radiating a laser beam at a particular angle and acquiring a three-dimensional image by measuring the lapsed time of the laser beam that has returned after being reflected. The LiDAR sensor has been incorporated and utilized in various devices such as drones and robots. This study focuses on object detection and recognition by employing sensor fusion. Object detection and recognition can be executed as a single function by incorporating sensors capable of recognition, such as image sensors, optical sensors, and propagation sensors. However, a single sensor has limitations with respect to object detection and recognition, and such limitations can be overcome by employing multiple sensors. In this paper, the performance of an eight-channel scanning LiDAR was evaluated and an object detection algorithm based on it was implemented. Furthermore, object detection characteristics during daytime and nighttime in a real road environment were verified. Obtained experimental results corroborate that an excellent detection performance of 92.87% can be achieved.

• International Journal of Computer Science & Network Security
• /
• v.22 no.11
• /
• pp.121-126
• /
• 2022

The number of vehicles has increased exponentially over the past 20 years due to technological advancements. It is becoming almost impossible to manually control and manage the traffic in a city like Karachi. Without license plate recognition, traffic management is impossible. The Framework for License Plate Detection & Recognition to overcome these issues is proposed. License Plate Detection & Recognition is primarily performed in two steps. The first step is to accurately detect the license plate in the given image, and the second step is to successfully read and recognize each character of that license plate. Some of the most common algorithms used in the past are based on colour, texture, edge-detection and template matching. Nowadays, many researchers are proposing methods based on deep learning. This research proposes a framework for License Plate Detection & Recognition using a custom YOLOv5 Object Detector, image segmentation techniques, and Tesseract's optical character recognition OCR. The accuracy of this framework is 0.89.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.6
• /
• pp.624-629
• /
• 2016

Recently various types of disaster monitoring system using smart-phones are under active studying. In this paper, we propose a system that automatically performs the disaster and fire detection. Additionally we implement the Arduino-based smart image sensor system in the web platform. When a fire is detected, an SMS is sent to the Fire and Disaster Management Agency. In order to improve fire detection probability, we proposed a smart Arduino fire detection sensor simulation which searches the smart sensor inference algorithm using fuzzy rules.

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.496-499
• /
• 1995

In this paper, a new detection scheme, the detectable maneuver set (DMS) scheme, is proposed by incorporating the trade-off property between target maneuver magnitude and detection time delay. With this new detection scheme, small maneuvers can be effectively detected without enlarging window size. Simulation results show that the proposed DMS scheme gives better tracking performance.

• Journal of Sensor Science and Technology
• /
• v.26 no.6
• /
• pp.391-396
• /
• 2017

Human body motion detection is important in several industry sectors, such as entertainment, healthcare, rehabilitation, and so on. In this paper, we first discuss commercial human motion detection technologies (optical markers, MEMS acceleration sensors, infrared imaging, etc.) and then explain recent advances in the development of flexible and stretchable strain sensors for human motion detection. In particular, flexible and stretchable strain sensors that are fabricated using carbon nanotubes, silver nanowires, graphene, and other materials are reviewed.