scholarly journals A Fast Learning Method for Accurate and Robust Lane Detection Using Two-Stage Feature Extraction with YOLO v3

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4308 ◽  
Author(s):  
Xiang Zhang ◽  
Wei Yang ◽  
Xiaolin Tang ◽  
Jie Liu
Keyword(s):  
Learning Algorithm ◽  
Structural Parameters ◽  
Feature Learning ◽  
Automatic Generation ◽  
Detection Algorithm ◽  
Lane Detection ◽  
Stage Model ◽  
Two Stage ◽  
Label Data ◽  
Second Stage

To improve the accuracy of lane detection in complex scenarios, an adaptive lane feature learning algorithm which can automatically learn the features of a lane in various scenarios is proposed. First, a two-stage learning network based on the YOLO v3 (You Only Look Once, v3) is constructed. The structural parameters of the YOLO v3 algorithm are modified to make it more suitable for lane detection. To improve the training efficiency, a method for automatic generation of the lane label images in a simple scenario, which provides label data for the training of the first-stage network, is proposed. Then, an adaptive edge detection algorithm based on the Canny operator is used to relocate the lane detected by the first-stage model. Furthermore, the unrecognized lanes are shielded to avoid interference in subsequent model training. Then, the images processed by the above method are used as label data for the training of the second-stage model. The experiment was carried out on the KITTI and Caltech datasets, and the results showed that the accuracy and speed of the second-stage model reached a high level.

HAEMODYNAMIC CONTRIBUTIONS TO THE PATHOGENESIS OF PREECLAMPSIA AND ECLAMPSIA

2008 ◽  
Vol 19 (1) ◽  
pp. 85-104 ◽  
Author(s):  
IRA M BERNSTEIN ◽  
MARILYN J CIPOLLA
Keyword(s):  
Endothelial Injury ◽  
Trophoblast Invasion ◽  
Stage Model ◽  
Abnormal Placentation ◽  
Two Stage ◽  
Second Stage

Current hypotheses regarding the origins of preeclampsia have focused on the “Two stage model”. This model suggests that the primary steps in the pathophysiologic sequence of preeclampsia are initiated by abnormal placentation including the classic finding of abnormal trophoblast invasion of maternal decidual spiral arteries. The second stage of the sequence includes the elaboration of a single or multiple substances from these disordered placentas which contribute to the generalized maternal systemic illness, eventually manifesting as endothelial injury, hypertension and proteinuria. Recent studies have focused on the role of pro and anti-angiogenic peptides as potential placentally derived aetiologic agents in this pathophysiologic sequence, although other placental products have been highlighted in recent research. Despite the fact that this modeling of preeclampsia has widespread support significant limitations to this hypothesis can be identified.

scholarly journals Evidence for a two-stage model of microbial infection

1968 ◽  
Vol 66 (2) ◽  
pp. 273-280 ◽  
Author(s):  
G. G. Meynell ◽  
Joan Maw
Keyword(s):  
Standard Error ◽  
Stage Model ◽  
Microbial Infection ◽  
Two Stage ◽  
Second Stage ◽  
Initial Stage ◽  
The Mean ◽  
Pass Through

SUMMARYColony counts on mice given the same number ofSalmonellaalways differ considerably. However, the standard error of the mean log count does not increase after the first 1·5 hr. of infection until the 8th or 10th day. These infections therefore appear to pass through an initial stage lasting a few hours, in which a varying proportion of the inoculum is killed, followed by a prolonged second stage in which the scatter in individual colony counts remains constant.

The Role Experimentation of Intercollegiate Student Athletes

2003 ◽  
Vol 17 (2) ◽  
pp. 196-219 ◽  
Author(s):  
Patricia S. Miller ◽  
Gretchen A. Kerr
Keyword(s):  
Identity Formation ◽  
Student Athletes ◽  
Social Roles ◽  
Athletic Identity ◽  
University Student ◽  
Stage Model ◽  
Two Stage ◽  
Second Stage ◽  
Identity Foreclosure ◽  
Depth Interviews

This study examined the role experimentation of university student athletes using in-depth interviews. The results revealed participants’ role experimentation was limited to three spheres: athletic, academic, and social. Participants’ exploration of and commitment to roles revealed a two-stage model of identity formation. The first stage, Over-Identification with the Athlete Role, revealed a singular focus on athletics that persisted throughout much of the participants’ university careers. The second stage, Deferred Role Experimentation, reflected an increased investment in academic and social roles in the participants’ upper years. Results were consistent with previous findings of an athletic identity among intercollegiate student-athletes (Brewer, Van Raalte, & Linder, 1993), but supported Perna, Zaichkowsky, and Bocknek’s (1996) suggestion that identity foreclosure may have been overgeneralized.

Apparent Movement of Successively Generated Subjective Figures

Perception ◽  
1978 ◽  
Vol 7 (4) ◽  
pp. 371-383 ◽  
Author(s):  
J Timothy Petersik ◽  
Kenyon I Hicks ◽  
Allan J Pantle
Keyword(s):  
Internal Structure ◽  
Relative Intensity ◽  
Cross Correlation ◽  
Apparent Movement ◽  
Stage Model ◽  
Two Stage ◽  
Second Stage ◽  
Subjective Figure

In the present studies a pair of random-dot frames was constructed so that two areas in the first frame (f1) were correlated with two areas in the second frame (f2). The alternation of the pair of frames (an f1-f2 sequence) gave rise to two subjective figures. When two pairs of random-dot frames (an f1-f2 sequence and an f3-f4 sequence), each of which produced two subjective figures in different locations, were themselves alternated, the subjective figures from the f1-f2 sequence interacted with the subjective figures from the f3-f4 sequence to produce apparent movement. With any one of the four general kinds of displays which we constructed, subjects usually perceived only one of two types of subjective-figure movement. The type of movement that was perceived with a given display depended primarily upon the degree of change (across the interval between an f1-f2 and an f3-f4 sequence) of the internal structure of the successively generated subjective figures. Relative intensity differences between the subjective figures and their backgrounds influenced the type of apparent movement seen, whereas variations in the density of elements in a display did not. We tentatively propose a two-stage model to explain the apparent movement of the subjective figures: the first stage is assumed to generate the subjective figures by means of a cross-correlation of the intensity distributions of the two frames within an f1-f2 sequence and within an f3-f4 sequence; on the basis of inputs from the first stage, the second stage generates apparent movement signals for the subjective figures.

A Two-Stage Kalman Estimation Approach to Identify Parameters of a Nonlinear Elastic Structure

2010 ◽  
Vol 163-167 ◽  
pp. 2632-2636
Author(s):  
Ying Lei ◽  
Yong Qiang Jiang
Keyword(s):  
State Vector ◽  
Structural Damage ◽  
Structural Parameters ◽  
Two Stage ◽  
Nonlinear Parameters ◽  
Nonlinear Structure ◽  
Second Stage ◽  
Nonlinear Structural ◽  
Shear Beam ◽  
Nonlinear Elastic

When structural damage occurs, nonlinearity usually exists in damaged structures. So far, some progresses in the identification of nonlinearity in structures have been made. The extended Kalman filter (EKF) has been applied for the identification of nonlinear structural parameters. However, since the extended state vector contains both the state vector and the structural parameters, EKF approach can identify limited numbers of nonlinear structural parameters due to computational convergence difficulty. To overcome such problem, a two-stage Kalman estimator approach, which is not available in the previous literature, is proposed for the identification of nonlinear structural parameters. In the first stage, state vector of a nonlinear structure is considered as an implicit function of the nonlinear structural parameters, and the parametric vector is estimated directly based on the Kalman estimator. In the second stage, state vector of the nonlinear structure is updated by applying the Kalman estimator with the structural parameters being estimated in the first stage. Therefore, analytical recursive solutions for the structural nonlinear parameters and state vector are respectively derived and presented, by using the Kalman estimator method respectively. The proposed approach is straightforward. To demonstrate the accuracy and effectiveness of the proposed approach, numerical example of identifying the parameters of a 4-story nonlinear elastic Duffing-type shear-beam building is conducted. Simulation results show that the proposed approach is able to identify nonlinear structural systems.

scholarly journals A Two-Stage Deep Neural Network Framework for Precipitation Estimation from Bispectral Satellite Information

2018 ◽  
Vol 19 (2) ◽  
pp. 393-408 ◽  
Author(s):  
Yumeng Tao ◽  
Kuolin Hsu ◽  
Alexander Ihler ◽  
Xiaogang Gao ◽  
Soroosh Sorooshian
Keyword(s):  
Deep Learning ◽  
Binary Classification ◽  
Precipitation Amount ◽  
Skewed Distribution ◽  
Stage Model ◽  
Two Stage ◽  
Learning Framework ◽  
Second Stage ◽  
Satellite Information ◽  
Precipitation Estimation

Abstract Compared to ground precipitation measurements, satellite-based precipitation estimation products have the advantage of global coverage and high spatiotemporal resolutions. However, the accuracy of satellite-based precipitation products is still insufficient to serve many weather, climate, and hydrologic applications at high resolutions. In this paper, the authors develop a state-of-the-art deep learning framework for precipitation estimation using bispectral satellite information, infrared (IR), and water vapor (WV) channels. Specifically, a two-stage framework for precipitation estimation from bispectral information is designed, consisting of an initial rain/no-rain (R/NR) binary classification, followed by a second stage estimating the nonzero precipitation amount. In the first stage, the model aims to eliminate the large fraction of NR pixels and to delineate precipitation regions precisely. In the second stage, the model aims to estimate the pointwise precipitation amount accurately while preserving its heavily skewed distribution. Stacked denoising autoencoders (SDAEs), a commonly used deep learning method, are applied in both stages. Performance is evaluated along a number of common performance measures, including both R/NR and real-valued precipitation accuracy, and compared with an operational product, Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Cloud Classification System (PERSIANN-CCS). For R/NR binary classification, the proposed two-stage model outperforms PERSIANN-CCS by 32.56% in the critical success index (CSI). For real-valued precipitation estimation, the two-stage model is 23.40% lower in average bias, is 44.52% lower in average mean squared error, and has a 27.21% higher correlation coefficient. Hence, the two-stage deep learning framework has the potential to serve as a more accurate and more reliable satellite-based precipitation estimation product. The authors also provide some future directions for development of satellite-based precipitation estimation products in both incorporating auxiliary information and improving retrieval algorithms.

A Two-Stage Kalman Estimation Approach for the Identification of Structural Parameters under Unknown Inputs

2011 ◽  
Vol 243-249 ◽  
pp. 5394-5398 ◽  
Author(s):  
Ying Lei ◽  
Yong Qiang Jiang
Keyword(s):  
State Vector ◽  
Structural Parameters ◽  
Structural Identification ◽  
Frame Structure ◽  
Two Stage ◽  
Second Stage ◽  
Nonlinear Structural ◽  
Simulation Results ◽  
Shear Frame ◽  
Recursive Solutions

Detection of structural damages is critical to ensure the reliability and safety of structures. So far, some progresses in structural identification have been made. The extended Kalman filter (EKF) has been one of the classic time-domain approaches for the identification of structural parameters. However, since the extended state vector contains both the state vector and the structural parameters, EKF approach can identify limited numbers of nonlinear structural parameters due to computational convergence difficulty. To overcome such problem, a two-stage Kalman estimation approach, which is not available in the previous literature, is proposed for the identification of structural parameters. In the first stage, state vector of structures is considered as an implicit function of the structural parameters, and the parametric vector is estimated directly based on the Kalman estimator. In the second stage, state vector of the structure is updated by applying the Kalman estimator with the structural parameters being estimated in the first stage. Therefore, analytical recursive solutions for the structural parameters and state vector are respectively derived and presented, by using the Kalman estimator method in a two-stage approach. The proposed approach is straightforward. Moreover, it can identify more numbers of nonlinear structural parameters with less time of iteration calculation compared with the conventional EKF. A numerical example of identifying the parameters of an 8-storey shear-frame structure is conducted. Simulation results show that the proposed approach is effective and accurate.

Efficiency Improvement in Entrained Flow Gasification

2011 ◽  
Author(s):  
Ankit Bhatnagar ◽  
S. Pushpavanam
Keyword(s):  
Oxygen Consumption ◽  
Single Stage ◽  
Stage Model ◽  
Two Stage ◽  
Entrained Flow ◽  
Second Stage ◽  
Cold Gas Efficiency ◽  
Stage System ◽  
Gas Efficiency ◽  
Cold Gas

In this work a one dimensional steady state model is developed for a single stage and two-stage bottom fed entrained flow coal gasifier for. The single stage model was first analysed for two different oxidants (i) oxygen and (ii) air to study their effects on gasification. Analysis proved oxygen to be the better oxidant. The model is then extended to a two stage gasifier. Here 30 (70) percent of the coal is fed in the first stage (second stage). The first (second) stage operates in oxidant rich (lean) environment. The performances of single stage and two-stage models are compared in terms of their cold gas efficiencies for the same coal feed rates. It is observed that a two-stage system has better cold gas efficiency (77%) than a single stage system (72%) with lower oxygen consumption. The two-stage model is used to optimise the O2/Coal ratio as the H2O/Coal ratio is varied in the 2nd stage. The optimum yields the highest cold gas efficiency with minimum possible oxygen consumption.

scholarly journals A BERT-Based Two-Stage Model for Chinese Chengyu Recommendation

2021 ◽  
Vol 20 (6) ◽  
pp. 1-18
Author(s):  
Minghuan Tan ◽  
Jing Jiang ◽  
Bing Tian Dai
Keyword(s):  
State Of The Art ◽  
The State ◽  
Stage Model ◽  
Performance Gain ◽  
Two Stage ◽  
Second Stage ◽  
Fine Tune

In Chinese, Chengyu are fixed phrases consisting of four characters. As a type of idioms, their meanings usually cannot be derived from their component characters. In this article, we study the task of recommending a Chengyu given a textual context. Observing some of the limitations with existing work, we propose a two-stage model, where during the first stage we re-train a Chinese BERT model by masking out Chengyu from a large Chinese corpus with a wide coverage of Chengyu. During the second stage, we fine-tune the re-trained, Chengyu-oriented BERT on a specific Chengyu recommendation dataset. We evaluate this method on ChID and CCT datasets and find that it can achieve the state of the art on both datasets. Ablation studies show that both stages of training are critical for the performance gain.

scholarly journals Urban Railway Transit Timetable Optimisation Based on Passenger-and-Trains Matching – A Case Study of Beijing Metro Line

2021 ◽  
Vol 33 (5) ◽  
pp. 671-687
Author(s):  
Junsheng Huang ◽  
Tong Zhang ◽  
Runbin Wei
Keyword(s):  
Genetic Algorithm ◽  
Waiting Time ◽  
Stage Model ◽  
Two Stage ◽  
Left Behind ◽  
Second Stage ◽  
Decision Variables ◽  
Proposed Model ◽  
Railway System

Due to the congested scenarios of the urban railway system during peak hours, passengers are often left behind on the platform. This paper firstly brings a proposal to capture passengers matching different trains. Secondly, to reduce passengers’ total waiting time, timetable optimisation is put forward based on passengers matching different trains. This is a two-stage model. In the first stage, the aim is to obtain a match between passengers and different trains from the Automatic Fare Collection (AFC) data as well as timetable parameters. In the second stage, the objective is to reduce passengers’ total waiting time, whereby the decision variables are headway and dwelling time. Due to the complexity of our proposed model, an MCMC-GASA (Markov Chain Monte Carlo-Genetic Algorithm Simulated Annealing) hybrid method is designed to solve it. A real-world case of Line 1 in Beijing metro is employed to verify the proposed two-stage model and algorithms. The results show that several improvements have been brought by the newly designed timetable. The number of unique matching passengers increased by 37.7%, and passengers’ total waiting time decreased by 15.5%.

Sign in / Sign up

Export Citation Format

Share Document