http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Real-Time Vehicle Detection Design and Implementation on GPU
Vinh Dinh Nguyen,Thuy Tuong Nguyen,Dung Duc Nguyen,Jae Wook Jeon 제어로봇시스템학회 2011 제어로봇시스템학회 국제학술대회 논문집 Vol.2011 No.10
Vehicle detection and distance estimation system has become important due to their assistance in reducing vehicle accidents. Therefore, an efficient vehicle detection and distance estimation algorithm using a knowledge-based method and image segmentation technique has been developed. The proposed algorithm can detect and estimate the distance of the preceding vehicle under various road conditions using a single CCD camera of 16 mm and 25 mm focal lenghts mounted on a vehicle. A GPU implementation of this proposed algorithm is introduced to enable our proposed system to support real-time processing. Experimental results under various road and weather conditions prove that our proposed system is suitable for a real-time system.
A Fast Evolutionary Algorithm for Real-Time Vehicle Detection
Vinh Dinh Nguyen,Thuy Tuong Nguyen,Dung Duc Nguyen,Sang Jun Lee,Jae Wook Jeon IEEE 2013 IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY Vol.62 No.6
<P>The evolutionary algorithm (EA) is an effective method for solving various problems because it can search through very large search spaces and can quickly come to nearly optimal solutions. However, existing EA-based methods for vehicle detection cannot achieve high performance because their fitness functions depend on sensitive information, such as edge or color information on the preceding vehicle. This paper focuses on improving the performance of existing evolutionary-based methods for vehicle detection by introducing an effective fitness function that can more accurately capture a vehicle's information by combining a disparity map, edge information, and the position and motion of the preceding vehicle. The proposed method can detect multiple vehicles by using a turn-back genetic algorithm (GA) and can prevent false detection by using motion detection. Our fitness function is designed in a typical manner along with the fitness parameters. These parameters are usually selected using heuristic methods, making the choice of optimal parameters difficult. Therefore, this paper proposes a new approach to estimating optimal fitness parameters using EA and the least squares method. Robustness testing showed that the proposed method provides detection rate (DR) results close to those obtained using a state-of-the-art system and outperforms other dominant vehicle-detection-based EAs.</P>
Thermocapillary migration of a fluid compound droplet
Vinh T. Nguyen,Truong V. Vu,Phan H. Nguyen,Nang X. Ho,Binh D. Pham,Hoe D. Nguyen,Hung V. Vu 대한기계학회 2021 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.35 No.9
Compound and simple droplets have been studied and appeared in many life applications, e.g., drug processing and microfluidic systems. Many studies have been conducted on the thermocapillary effects on simple droplets, but similar studies on compound droplets are quite rare. Filling this missing gap, this paper presents the front-tracking-based simulation results of the thermocapillary effects on compound droplets in a certain limited domain. The compound droplet consists of a single inner core that is initially concentric with the outer one. Various dimensionless parameters including Reynolds number from 1 to 50, Marangoni number from 1 to 100, droplet radius ratio from 0.3 to 0.8, and viscosity ratios from 0.1 to 6.4 are varied to reveal their influences on the migration of a compound droplet from cold to hot regions. Initially, the inner droplet moves faster than the outer one, and when the leading surface of the inner droplet touches the outer one, the inner and outer droplets migrate at the same speed. The effects of these parameters on the compound droplet eccentricity are also considered.
Numerical study of the indentation formation of a compound droplet in a constriction
Hoe D. Nguyen,Truong V. Vu,Phan H. Nguyen,Binh D. Pham,Nang X. Ho,Cuong T. Nguyen,Vinh T. Nguyen 대한기계학회 2021 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.35 No.4
A compound droplet deforming in a constricted tube widely appears in drug delivery and microfluidic devices. In such a constriction, an indentation can present at the trailing surface of the droplet. However, this aspect has not been fully investigated and understood so far. This study focuses on the effects of some dimensionless parameters on the negative curvature, i.e., indentation, at the trailing surface of a compound droplet moving through a constricted tube. The presence of the constriction at the middle of the tube length enhances the droplet indentation. Numerical results were obtained for the capillary number Ca (varied in range of 0.1 - 1.0), the inner-to-outer droplet radius ratio R 21 (varied in range of 0.2 - 0.9), the droplet-to-tube radius ratio R 10 (varied in range of 0.2 - 0.9), the inner-to-outer interfacial tension coefficient ratio σ 21 (varied in range of 0.1 - 6.4), and the normalized depth of the constriction d/R (varied in range of 0.0 - 0.8). The results reveal that the most influencing factor is Ca, increasing its value leads to the increment of the maximum indentation at the trailing surface of the inner and outer droplets. The indentation is also increased with increasing the value of R 10and d/R. In contrast, increasing R 21 results in a decrease in the indentation at the trailing surface of the outer droplet. When increasing σ 21 , the indentation at the trailing surface of the inner one is quickly suppressed, while the outer droplet is minorly affected. We also point out the patterns of the trailing surface of the inner and outer droplets and their transitions from one to the other patterns in the diagrams based on these parameters.
ROBUST TRAFFIC LIGHT DETECTION AND CLASSIFICATION UNDER DAY AND NIGHT CONDITIONS
Phuc Manh Nguyen,Vu Cong Nguyen,Son Ngoc Nguyen,Linh My Thi Dang,Ha Xuan Nguyen,Vinh Dinh Nguyen 제어로봇시스템학회 2020 제어로봇시스템학회 국제학술대회 논문집 Vol.2020 No.10
Recently, traffic light detection and classification systems have been studied and developed to build an autonomous car by many research institutes, universities, and companies. However, the results of existing traffic light detection systems are still not stable under day and night conditions. It is difficult to detect the location of traffic light due to their small size. Moreover, traffic lights’ shapes are also similar to advertisement lights in a city road. Therefore, this paper proposed a new approach to improve the performance of existing traffic light detection systems by using the benefits of hand-crafted features and deep learning techniques. Experimental results show that the proposed system obtained the detection rate of 80% under night conditions, while the color-based density method only got the detection rate of 50.43% under night conditions.
Yen-Lien T. Nguyen,Anh-Tuan Le,Khanh Nguyen Duc,Vinh Nguyen Duy,Cong Doan Nguyen 서울시립대학교 도시과학연구원 2021 도시과학국제저널 Vol.25 No.4
This study aims to develop the models of emission and fuel consumption during idling of motorcycles (MCs) in Hanoi, including the unsteady and steady idling stages. Five MC models commonly used in Hanoi were selected to measure the instantaneous emission and fuel consumption rates under the controlled conditions at the laboratory conditions. The instantaneous emission and fuel consumption models during idling were developed for the test MCs in the unsteady idling stage. The R2 of obtained models are higher than 0.9. The average emission and fuel consumption rates in the steady idling stages were determined. The average idling emissions of pollutants CO, CO2, HC and NOx were 60.9, 534.3, 10.3 and 1.8 g/h, respectively. The average fuel loss during idling is around 180 g/h. The emission released from the MC fleet in Hanoi during idling was estimated for the year 2018. The total idling emissions from the MC fleet of 3.9 million vehicles in the year 2018 of CO, CO2, HC and NOx were 6.5, 57.1, 1.1 and 0.2 kt, respectively. The total fuel loss during idling of the MC fleet in 2018 was ∼19.3 kt. The air pollutants eliminated in the idle mode as CO, CO2, HC and NOx contributed 2.23%, 3.19%, 1.14% and 1.03%, respectively, of the total emission from the MC fleet in Hanoi.