해저연약지반에서 궤도차량의 기동 성능평가 기법에 대한 고찰

권오순,장인성,오명학,강현 (사)한국연안방재학회 2019 한국연안방재학회지 Vol.6 No.4

Recently, the underwater robots in the ocean have been used more frequently. Not only the tracked heavy duty underwater vehicles for underwater pipeline or cabling but also tracked vehicles for the shallow water level area(0~5m water depth) where on-land working vehicles and ships can not work. Tracked vehicles secure trafficability by pushing the ground in the track, and if the ground is weak, the soil thrust sufficient to move the equipment cannot be ensured, making the vehicle impossible to move. In the previous study to evaluate the trafficability of tracked vehicle on the soft ground, vehicle can move when the ground thrust is greater by calculating the soil thrust exerted by the ground and the resistance to the vehicle's movement. However, if the seabed soil strength is very small and the ground is not sufficiently supported, the method of assessment by settlement may overestimate the vehicle’s trafficability. In this paper, the depth of destruction beyond the supporting force of the ground due to the heavy tracked vehicle's self weight placed on the weak ground was assessed as the vehicle's sinking load, and the trafficability of the tracked vehicle was evaluated by comparing the resistance and thrust of the ground at this time. In addition, if soft ground exists thinly on hard soil or rocky condition of the seabed, the trafficability of the tracked vehicle was finally assessed, taking into account the increased resistance of the ground due to the settlement of the track vehicle on the soft ground.

A real-time multiple vehicle tracking method for traffic congestion identification

( Xiaoyu Zhang ),( Shiqiang Hu ),( Huanlong Zhang ),( Xing Hu ) 한국인터넷정보학회 2016 KSII Transactions on Internet and Information Syst Vol.10 No.6

Traffic congestion is a severe problem in many modern cities around the world. Real-time and accurate traffic congestion identification can provide the advanced traffic management systems with a reliable basis to take measurements. The most used data sources for traffic congestion are loop detector, GPS data, and video surveillance. Video based traffic monitoring systems have gained much attention due to their enormous advantages, such as low cost, flexibility to redesign the system and providing a rich information source for human understanding. In general, most existing video based systems for monitoring road traffic rely on stationary cameras and multiple vehicle tracking method. However, most commonly used multiple vehicle tracking methods are lack of effective track initiation schemes. Based on the motion of the vehicle usually obeys constant velocity model, a novel vehicle recognition method is proposed. The state of recognized vehicle is sent to the GM-PHD filter as birth target. In this way, we relieve the insensitive of GM-PHD filter for new entering vehicle. Combining with the advanced vehicle detection and data association techniques, this multiple vehicle tracking method is used to identify traffic congestion. It can be implemented in real-time with high accuracy and robustness. The advantages of our proposed method are validated on four real traffic data.

Damage identification of vehicle-track coupling system from dynamic responses of moving vehicles

Zhu, Hong-Ping,Ye, Ling,Weng, Shun,Tian, Wei Techno-Press 2018 Smart Structures and Systems, An International Jou Vol.21 No.5

The structural responses are often used to identify the structural local damages. However, it is usually difficult to gain the responses of the track, as the sensors cannot be installed on the track directly. The vehicles running on a track excite track vibration and can also serve as response receivers because the vehicle dynamic response contains the vibration information of the track. A damage identification method using the vehicle responses and sensitivity analysis is proposed for the vehicle-track coupling system in this paper. Different from most damage identification methods of vehicle-track coupling system, which require the structural responses, only the vehicle responses are required in the proposed method. The local damages are identified by a sensitivity-based model updating process. In the vehicle-track coupling system, the track is modeled as a discrete point supported Euler-Bernoulli beam, and two vehicle models are proposed to investigate the accuracy and efficiency of damage identification. The measured track irregularity is considered in the calculation of vehicle dynamic responses. The measurement noises are also considered to study their effects to the damage identification results. The identified results demonstrate that the proposed method is capable to identify the local damages of the track accurately in different noise levels with only the vehicle responses.

A Comparison Study of Kinematic and Dynamic Models for Trajectory Tracking of Autonomous Vehicles Using Model Predictive Control

Bao-Lin Ye,Shaofeng Niu,Lingxi Li,Weimin Wu 제어·로봇·시스템학회 2023 International Journal of Control, Automation, and Vol.21 No.9

Efficient trajectory tracking approaches can enable autonomous vehicles not only to get a smooth trajectory but to achieve a lower energy dissipation. Since vehicle model plays an important role in trajectory tracking, this paper investigates and compares the performance of two classical vehicle models for trajectory tracking of autonomous vehicles using model predictive control (MPC). Firstly, a two-degree-of-freedom kinematic model and a three-degree-of-freedom yaw dynamic model are established for autonomous vehicles. Meanwhile, in order to carry out tracking control more effectively and smoothly, the tire slip angle has been taken into account by the dynamic model. Then, we design two MPC controllers for trajectory tracking, which are based on the kinematic model and the dynamic model, respectively. The performances of two MPC controllers are evaluated and compared on the Carsim/Matlab joint simulation platform. Experimental results demonstrated that, under low-speed working conditions, both two MPC controllers can follow the reference trajectory with high accuracy and stability. However, under high-speed working conditions, the tracking error of the kinematic model is too large to be used in the real trajectory tracking problem. On the contrary, the controller based on the dynamic model still performs a good tracking effect. In addition, this study offers guidance on how to select a suitable vehicle model for autonomous vehicles under different speed working conditions.

궤도-지반 상호작용 이론을 활용한 해저궤도차량의 구동성능 평가

백성하,신규범,권오순,정충기 한국지반공학회 2018 한국지반공학회논문집 Vol.34 No.2

Underwater tracked vehicle is employed to perform underwater heavy works on saturated seafloor. When an underwater tracked vehicle travels on the seafloor, shearing action and ground settlement take place on the soil-track interface, which develops the soil thrust and soil resistance, respectively, and they restrict the tractive performance of an underwater tracked vehicle. Thus, unlike the paved road, underwater tracked vehicle performance does not solely rely on its engine thrust, but also on the soil-track interaction. This paper aimed at evaluating the tractive performance of an underwater tracked vehicle with respect to ground conditions (soil type, and relative density or consistency) and vehicle conditions (weight of vehicle, and geometry of track system), based on the soil-track interaction theory. The results showed that sandy ground and silty sandy ground generally provide sufficient tractions for an underwater tracked vehicle whereas tractive performance is very much restricted on clayey ground, especially for a heavy-weighted underwater tracked vehicle. Thus, it is concluded that an underwater tracked vehicle needs additional equipment to enhance the tractive performance on the clayey ground.

Automatic Multi-Vehicle Tracking using Video Cameras: An Improved CAMShift Approach

Jingxin Xia,Wenming Rao,Wei Huang,Zhenbo Lu 대한토목학회 2013 KSCE JOURNAL OF CIVIL ENGINEERING Vol.17 No.6

Video cameras play an important role in achieving the potentials promised by Intelligent Transportation Systems. In particular,video tracking systems have been widely applied in traffic flow data collection and incident detection by tracking and analyzing vehicle trajectories through video image processing. Focusing on current vehicle tracking methods that are limited to complex traffic scenes such as target non-uniqueness and color distraction in real traffic situations, this paper proposes an improved Continuously Adaptive Mean Shift (CAMShift) method for automatic multi-vehicle tracking using video cameras. The proposed method firstly uses a background subtraction method for automatically detecting, selecting, and initializing targets, i.e., vehicles. Moreover, a motion estimation method is proposed for estimating vehicle motion states and predicting the new locations of the vehicles. Finally,both the color and edge feature distributions of the vehicles are extracted and a mixed model is established for searching the matching vehicles in the next image frame. The proposed method was comparatively evaluated with the traditional CAMShift method using the same video sequences captured from real traffic situations. Evaluation results showed that the proposed method is efficient for accurately tracking vehicle movements, and is promising for practical applications.

스마트 전조등을 위한 비전 기반 야간 차량 인식

박정민,송진규,이준웅 제어·로봇·시스템학회 2024 제어·로봇·시스템학회 논문지 Vol.30 No.1

Recently, there has been an increasing need for algorithms capable of precisely and rapidly recognizing vehicles at night via smart control of headlamps. In this study, we constructed an algorithm that could detect vehicles approaching the main vehicle and vehicles moving in the same direction as the main vehicle through images taken in front of the vehicle on a road at night. The algorithm mainly involved 1) the generation of vehicle candidates (VCs), 2) the classification of VCs, and 3) the tracking of VCs. VC generation generally begins with the extraction of light-blobs from an image and the pairing of these blobs. However, because various lights are mixed, it is difficult to identify which of these lights originate from vehicles. To solve this problem, we constructed multiple feature maps that are likely to closely relate to the light emitted from head and tail lamps and calculated the stereo disparity. The feature maps and stereo disparity were used for light-blob pairing to generate VCs. Subsequently, VC classification and tracking were performed. VC classification was performed using a convolutional neural network. The classifier indicated with probability whether the VC was a vehicle approaching the main vehicle, a vehicle going in the same direction as the main vehicle, or a non-vehicle. VC tracking performed via a KanadeLucasTomasi-based feature tracker enabled robust vehicle detection between consecutive input images. We showed that the proposed algorithm can be applied to the control of smart headlamps through real vehicle experiments.

실시간 영상처리를 이용한 개별차량 추적시스템 개발

오주택,민준영 한국도로학회 2008 한국도로학회논문집 Vol.10 No.3

Video image processing systems (VIPS) offer numerous benefits to transportation models and applications, due to their ability to monitor traffic in real time. VIPS based on wide-area detection, i.e., multi-lane surveillance algorithm provide traffic parameters with single camera such as flow and velocity, as well as occupancy and density. However, most current commercial VIPS utilize a tripwire detection algorithm that examines image intensity changes in the detection regions to indicate vehicle presence and passage, i.e., they do not identify individual vehicles as unique targets. If VIPS are developed to track individual vehicles and thus trace vehicle trajectories, many existing transportation models will benefit from more detailed information of individual vehicles. Furthermore, additional information obtained from the vehicle trajectories will improve incident detection by identifying lane change maneuvers and acceleration/deceleration patterns. The objective of this research was to relate traffic safety to VIPS tracking and this paper has developed a computer vision system of monitoring individual vehicle trajectories based on image processing, and offer the detailed information, for example, volumes, speed, and occupancy rate as well as traffic information via tripwire image detectors. Also the developed system has been verified by comparing with commercial VIP detectors Video image processing systems (VIPS) offer numerous benefits to transportation models and applications, due to their ability to monitor traffic in real time. VIPS based on wide-area detection, i.e., multi-lane surveillance algorithm provide traffic parameters with single camera such as flow and velocity, as well as occupancy and density. However, most current commercial VIPS utilize a tripwire detection algorithm that examines image intensity changes in the detection regions to indicate vehicle presence and passage, i.e., they do not identify individual vehicles as unique targets. If VIPS are developed to track individual vehicles and thus trace vehicle trajectories, many existing transportation models will benefit from more detailed information of individual vehicles. Furthermore, additional information obtained from the vehicle trajectories will improve incident detection by identifying lane change maneuvers and acceleration/deceleration patterns. The objective of this research was to relate traffic safety to VIPS tracking and this paper has developed a computer vision system of monitoring individual vehicle trajectories based on image processing, and offer the detailed information, for example, volumes, speed, and occupancy rate as well as traffic information via tripwire image detectors. Also the developed system has been verified by comparing with commercial VIP detectors

온라인 학습을 이용한 비전 기반의 차량 검출 및 추적

길성호(Sung-Ho Gil),김경환(Gyeong-Hwan Kim) 한국통신학회 2014 韓國通信學會論文誌 Vol.39 No.1(통신이론)

본 논문에서는 추적중인 차량의 외형 변화에 대해 온라인 학습 능력이 있는 비전 기반의 차량 검출 및 추적 시스템을 제안한다. 제안하는 시스템은 새로 검출된 차량의 연속된 프레임 간 움직임을 빠르고 강건하게 추정하기 위해 특징점 기반 추적 방법을 사용한다. 동시에 추적중인 차량에 대해 온라인 차량 검출기를 훈련시키고, 일시적인 차량 추적 실패 시 검출기의 결과를 이용해 추적기를 재초기화하여 강건한 추적을 가능하게 한다. 특히 차량 외형 모델의 업데이트 방법을 개선하여 시스템의 추적 성능을 높이고 처리시간을 단축시켰다. 다양한 주행환경에서 획득한 데이터세트를 사용하여 제안하는 시스템의 차량 검출 및 추적 성능을 평가하였다. 특히 우천 및 터널통과와 같은 악조건에서 기존의 방법에 비해 차량 추적 성능이 상당히 개선된 것을 증명하였다. In this paper we propose a system for vehicle detection and tracking which has the ability to learn on-line appearance changes of vehicles being tracked. The proposed system uses feature-based tracking method to estimate rapidly and robustly the motion of the newly detected vehicles between consecutive frames. Simultaneously, the system trains an online vehicle detector for the tracked vehicles. If the tracker fails, it is re-initialized by the detection of the online vehicle detector. An improved vehicle appearance model update rule is presented to increase a tracking performance and a speed of the proposed system. Performance of the proposed system is evaluated on the dataset acquired on various driving environment. In particular, the experimental results proved that the performance of the vehicle tracking is significantly improved under bad conditions such as entering a tunnel and passing rain.

형태와 확률 모델을 이용한 다중 차량 검출 후 추적 방법

임영철(Young-Chul Lim),이충희(Chung-Hee Lee),권순(Soon Kwon),김종환(Jonghwan Kim) 한국자동차공학회 2011 한국자동차공학회 부문종합 학술대회 Vol.2011 No.5

In this paper, we present a multi-vehicle tracking-by-detection method with single mono camera. No state-of-the-art vehicle detection method can detect all the vehicles on the road and remove all false positive alarms. False negative and false positive alarms are caused by an imperfect detection algorithm. Therefore, a robust tracking-by-detection algorithm is necessary to minimize the number of false positive and false negative alarms. Many false positive alarms are removed during track initialization procedure in Pre-Track state due to their sparseness. Particle prediction can minimize the number of false negative alarms in Cur-Track and Post-Track states. The experimental results demonstrate that our multi-vehicle detection-bytracking method remarkably reduces false positive and false negative alarms when comparing with the vehicle detection algorithm.