scholarly journals Guide Sign Analysis of Traffic Sign Data-Set Using Supervised Spiking Neuron Technique

2018 ◽  
Vol 7 (3.14) ◽  
pp. 221
Author(s):  
Mohd Safirin Karis ◽  
Nursabillilah Mohd Ali ◽  
Mohd Azamuddin Ali ◽  
Muhamad Raimi Sadiq Samsudin ◽  
Nurasmiza Selamat ◽  
...  
Keyword(s):  
Mean Value ◽  
Traffic Sign ◽  
Image Brightness ◽  
Data Set ◽  
Traffic Signs ◽  
Average Value ◽  
Mean Error ◽  
Stable Pattern ◽  
Early Hypothesis ◽  
Sign Analysis

In this paper, 20 guided traffic signs mostly displayed around Malacca area were selected as project databased. Early hypothesis was made as the error for each usable image will increased as more interference introduced to the original image used. Three types of conditions which are hidden region, image brightness and image rotation were selected as an experiment to analyze the performance of each sign used. Each condition will perform a specific error to generate their mean value and in the same, image recognition will take place in the matchup process. By focusing on the result, it produces hidden region critically ascending mean error value at 62.5% = 0.07 and has average value at others points. For image brightness effect, it shows a higher mean error value collected at less brightness points and non-stable pattern at 10% to 60% brightness. As for rotation upshot, the values show a critically ascending for error value at 22.5% and slightly increase at 2% to 5% rotation point. For the recognition process, at 6.25% hidden region, almost 70% of images are correctly matched to its own classes while at 62.5% hidden region only 40% of images are correctly matched to its own classes and leaving 2 images to outperform. For -40% brightness, 45% of images are correctly matched to its own classes while at 60% brightness 65% of images are correctly matched to its own classes and leaving 1 image to outperform. Lastly, at 2.5 degree rotation, 85% of images are correctly matched to its own classes while at 25° rotation, 45% of images are correctly matched to its own classes and leaving 2 images to outperform. Finally, the error forms will affect the final output response of the detected traffic signs used. 

scholarly journals Warning Sign Analysis of Traffic Sign Data-Set Using Supervised Spiking Neuron Technique

2018 ◽  
Vol 7 (3.14) ◽  
pp. 227
Author(s):  
Mohd Safirin Karis ◽  
Nursabillilah Mohd Ali ◽  
Muhammad Izzuddin Azahar ◽  
Shafrizal Nazreen Shaari ◽  
Nurasmiza Selamat ◽  
...  
Keyword(s):  
Neural Systems ◽  
Warning Sign ◽  
Traffic Sign ◽  
Data Set ◽  
Recognition Process ◽  
Mean Error ◽  
Rotational Effect ◽  
Early Hypothesis ◽  
Sign Analysis ◽  
The Mean

In this paper, two types of conditions have been applied to analyze the performance of SNN towards usable traffic sign, which are hidden region and rotational effect. There are 20 warning traffic signs being focused on where there are regularly seen around Malacca area. These traffic sign needed to be embedded in this system as a databased to counter the output for mean error and recognition process for both conditions applied. Early hypothesis was design as the mean error and recognition process will degraded its performance as more intrusion get introduced in the system. For hidden region, the values show a critically rising error value at 62.5% = 0.123. While for mean error rotational effect, the values show an increasing abruptly for error value between 80 ̊ to 90 ̊ with 0.087% to 0.130%. For recognition process at 6.25% hidden region, 100% of images are correctly matchup to its own image. At 50% of hidden region, there is only 10% of image that able to be recognize while at 56.25% and 62.5% are leaving to outperform. At 10 ̊ rotation, 100% of images are perfectly recognized to its own image. At 60%, there is 30% of image able to recognize leaving others at 70%, 80% and 90% degrees rotation of images were outperformed. In view of element occasion driven handling, they open up new skylines for creating models with a colossal sum limit of recollecting and a solid capacity to quick adjustment. SNNs include another component, the transient hub, to the representation limit and the handling capacities of neural systems. 

scholarly journals Cautionary Sign Analysis of Traffic Sign Data-Set Using Supervised Spiking Neuron Technique

2018 ◽  
Vol 7 (3.14) ◽  
pp. 233
Author(s):  
Mohd Safirin Karis ◽  
Nursabillilah Mohd Ali ◽  
Nur Aisyah Abdul Ghafor ◽  
Muhamad Aizuddin Akmal Che Jusoh ◽  
Nurasmiza Selamat ◽  
...  
Keyword(s):  
Mean Value ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Data Set ◽  
Traffic Signs ◽  
Recognition Process ◽  
Sign Recognition ◽  
Anticlockwise Rotation ◽  
The Impact ◽  
Detection And Recognition

In this paper, 19 cautionary traffic signs were selected as a database and 3 types of conditions have been proposed. The conditions are 5 different time of image taken; hidden region and anticlockwise rotation are all the experiments design that will shows all the errors in producing the it’s mean value and the performance of traffic sign recognition. Initial hypothesis was made as the error will become larger as the interruption getting bigger. Based on the results of the five-different time of image taken, the error gives the best performance; less error when time is between 8am to 12am due to the brightness factors and the sign can be recognize clearly during noon session. The hidden region conditions show good performances of the detection and recognition of the system depend on the lesser coverage of the hidden region introduce on traffic sign because if the hidden region coverage is huge the database will get confuse and take a longer time to do the recognition process. Lastly, in anticlockwise rotation shows that 90o gave large value of error causing the system unable to recognize sign perfectly rather than 135o angle. To sum-up, detection and recognition process are not depending on higher number of angle but the process solely depending on their value of sample for each traffic signs. The error will give the impact towards traffic sign recognition and detection process. In conclusion, SNN can perform the detection and recognition process to all objects as in the future the system will become more stable with the right technique on spiking models and well-developed technology in this field.  

On the Cross-Country Relationship between Poverty, Income Distribution, and Development

2014 ◽  
Author(s):  
Massoud Karshenas ◽  
Graham Pyatt
Keyword(s):  
Income Distribution ◽  
Household Survey ◽  
Well Being ◽  
Mean Value ◽  
Data Set ◽  
Average Value ◽  
Third Stage ◽  
Per Capita ◽  
Cross Country ◽  
The Lorenz Curve

The familiar cross-country relationship between the incidence of poverty and the level of development is derived via a three-stage process, which avoids restrictive parametric assumptions regarding the shape of income distribution. It starts with the relationship within a given household survey data set between the incidence of poverty and the mean value of the ratio m/z, where m is a measure of individual well-being and z is the critical value of m relative to which the poor are identified. It is then shown that there is a one-to-one relationship between this relationship and the Lorenz curve. In the second stage of our analysis we establish inter alia a sufficient condition for the incidence of poverty to be less in whichever of any two countries the average value of m/z is smaller. These conditions are tested empirically. Conditions under which this average value will be proportional to the Gross Domestic Product per capita (GDP) are identified in the third stage. Both the second and third stages of our procedure provide opportunities for improving on the 'explanation' of poverty offered by the GDP per capita. In particular, the Sen Index apparently provides a much better way of accounting for differences in the incidence of poverty across countries. The importance of economic growth for reducing poverty should be qualified accordingly.

scholarly journals A Multiscale Recognition Method for the Optimization of Traffic Signs Using GMM and Category Quality Focal Loss

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4850
Author(s):  
Mingyu Gao ◽  
Chao Chen ◽  
Jie Shi ◽  
Chun Sing Lai ◽  
Yuxiang Yang ◽  
...  
Keyword(s):  
Recognition Accuracy ◽  
Gaussian Mixture ◽  
Traffic Sign Recognition ◽  
Recognition Method ◽  
Traffic Sign ◽  
Data Set ◽  
Traffic Signs ◽  
Automatic Driving ◽  
Sign Recognition ◽  
Accuracy Tradeoff

Effective traffic sign recognition algorithms can assist drivers or automatic driving systems in detecting and recognizing traffic signs in real-time. This paper proposes a multiscale recognition method for traffic signs based on the Gaussian Mixture Model (GMM) and Category Quality Focal Loss (CQFL) to enhance recognition speed and recognition accuracy. Specifically, GMM is utilized to cluster the prior anchors, which are in favor of reducing the clustering error. Meanwhile, considering the most common issue in supervised learning (i.e., the imbalance of data set categories), the category proportion factor is introduced into Quality Focal Loss, which is referred to as CQFL. Furthermore, a five-scale recognition network with a prior anchor allocation strategy is designed for small target objects i.e., traffic sign recognition. Combining five existing tricks, the best speed and accuracy tradeoff on our data set (40.1% mAP and 15 FPS on a single 1080Ti GPU), can be achieved. The experimental results demonstrate that the proposed method is superior to the existing mainstream algorithms, in terms of recognition accuracy and recognition speed.

scholarly journals Real-Time Detection and Recognition of Road Traffic Signs using MSER and Random Forests

2018 ◽  
Vol 14 (03) ◽  
pp. 34 ◽  
Author(s):  
Xianyan Kuang ◽  
Wenbin Fu ◽  
Liu Yang
Keyword(s):  
Real Time ◽  
Random Forests ◽  
Road Traffic ◽  
Contrast Ratio ◽  
Region Of Interest ◽  
Traffic Sign ◽  
Data Set ◽  
Traffic Signs ◽  
Real Time Detection ◽  
Detection And Recognition

Real-time detection and recognition of road traffic signs plays an important role in advanced driving assistance system. Typically, the region of interest (ROI) method is effective in feature extraction but inefficient because it is sensitive to illumination changes. In this paper, we propose a maximally stable extremal regions (MSER) method with image enhancement to greatly improve ROI. Firstly, we employ gray world algorithm to process original images. And then potential areas of traffic signs are obtained through increasing the image contrast ratio and extracting the image-enhanced MSER. According to the characteristic variable and the geometry moment invariants, the geometric characteristics of traffic signs are extracted to obtain the ROIs. Finally, HSV-HOG-LBP feature is constructed and the random forests algorithm is used to identify the traffic signs. The experimental results show that our proposed method show strong robustness on illumination condition and rotation scale, and achieves a good performance by experiments with actual images and German traffic sign detection benchmark (GTSDB) data set.

The Traffic Sign Detection Algorithm Based on Region of Interest Extraction and Double Filter

2019 ◽  
Vol 13 ◽  
Author(s):  
Dongxian Yu ◽  
Jiatao Kang ◽  
Zaihui Cao ◽  
Neha Jain
Keyword(s):  
Region Of Interest ◽  
Detection Algorithm ◽  
Light Filter ◽  
Support Vector ◽  
Detection Accuracy ◽  
Traffic Light ◽  
Traffic Sign ◽  
Traffic Signs ◽  
Sign Detection ◽  
Traffic Sign Detection

In order to solve the current traffic sign detection technology due to the interference of various complex factors, it is difficult to effectively carry out the correct detection of traffic signs, and the robustness is weak, a traffic sign detection algorithm based on the region of interest extraction and double filter is designed.First, in order to reduce environmental interference, the input image is preprocessed to enhance the main color of each logo.Secondly, in order to improve the extraction ability Of Regions Of Interest, a Region Of Interest (ROI) detector based on Maximally Stable Extremal Regions (MSER) and Wave Equation (WE) was defined, and candidate Regions were selected through the ROI detector.Then, an effective HOG (Histogram of Oriented Gradient) descriptor is introduced as the detection feature of traffic signs, and SVM (Support Vector Machine) is used to classify them into traffic signs or background.Finally, the context-aware filter and the traffic light filter are used to further identify the false traffic signs and improve the detection accuracy.In the GTSDB database, three kinds of traffic signs, which are indicative, prohibited and dangerous, are tested, and the results show that the proposed algorithm has higher detection accuracy and robustness compared with the current traffic sign recognition technology.

scholarly journals Detecting Change between Urban Road Environments along a Route Based on Static Road Object Occurrences

2021 ◽  
Vol 11 (8) ◽  
pp. 3666
Author(s):  
Zoltán Fazekas ◽  
László Gerencsér ◽  
Péter Gáspár
Keyword(s):  
Change Detection ◽  
Traffic Safety ◽  
Recognition System ◽  
Driver Assistance Systems ◽  
Traffic Sign ◽  
Traffic Signs ◽  
Safety Risk ◽  
Urban Road ◽  
Environment Type ◽  
Cusum Method

For over a decade, urban road environment detection has been a target of intensive research. The topic is relevant for the design and implementation of advanced driver assistance systems. Typically, embedded systems are deployed in these for the operation. The environments can be categorized into road environment-types. Abrupt transitions between these pose a traffic safety risk. Road environment-type transitions along a route manifest themselves also in changes in the distribution of traffic signs and other road objects. Can the placement and the detection of traffic signs be modelled jointly with an easy-to-handle stochastic point process, e.g., an inhomogeneous marked Poisson process? Does this model lend itself for real-time application, e.g., via analysis of a log generated by a traffic sign detection and recognition system? How can the chosen change detector help in mitigating the traffic safety risk? A change detection method frequently used for Poisson processes is the cumulative sum (CUSUM) method. Herein, this method is tailored to the specific stochastic model and tested on realistic logs. The use of several change detectors is also considered. Results indicate that a traffic sign-based road environment-type change detection is feasible, though it is not suitable for an immediate intervention.

scholarly journals Thinner Sea Ice Contribution to the Remarkable Polynya Formation North of Greenland in August 2018

2021 ◽  
Author(s):  
Xiaoyi Shen ◽  
Chang-Qing Ke ◽  
Bin Cheng ◽  
Wentao Xia ◽  
Mengmeng Li ◽  
...  
Keyword(s):  
Sea Ice ◽  
Ice Cover ◽  
Reanalysis Data ◽  
Mean Value ◽  
Ocean Model ◽  
North Coast ◽  
Average Value ◽  
The North ◽  
Wind Sea ◽  
The One

AbstractIn August 2018, a remarkable polynya was observed off the north coast of Greenland, a perennial ice zone where thick sea ice cover persists. In order to investigate the formation process of this polynya, satellite observations, a coupled ice-ocean model, ocean profiling data, and atmosphere reanalysis data were applied. We found that the thinnest sea ice cover in August since 1978 (mean value of 1.1 m, compared to the average value of 2.8 m during 1978–2017) and the modest southerly wind caused by a positive North Atlantic Oscillation (mean value of 0.82, compared to the climatological value of −0.02) were responsible for the formation and maintenance of this polynya. The opening mechanism of this polynya differs from the one formed in February 2018 in the same area caused by persistent anomalously high wind. Sea ice drift patterns have become more responsive to the atmospheric forcing due to thinning of sea ice cover in this region.

scholarly journals On the Spectral and Polarimetric Signatures of a Bright Scatterer before and after Hardware Replacement

2021 ◽  
Vol 13 (5) ◽  
pp. 919
Author(s):  
Marco Gabella
Keyword(s):  
Low Noise ◽  
Low Noise Amplifiers ◽  
Doppler Velocity ◽  
Data Set ◽  
Differential Phase Shift ◽  
Spectral Signatures ◽  
Average Value ◽  
Before And After ◽  
Radar Calibration ◽  
Small Dispersion

A previous study has used the stable and peculiar echoes backscattered by a single “bright scatterer” (BS) during five winter days to characterize the hardware of C-band, the dual-polarization radar located at Monte Lema (1625 m altitude) in Southern Switzerland. The BS is the 90 m tall metallic tower on Cimetta (1633 m altitude, 18 km range). In this note, the statistics of the echoes from the BS were derived from other ten dry days with normal propagation conditions in winter 2015 and January 2019. The study confirms that spectral signatures, such as spectrum width, wideband noise and Doppler velocity, were persistently stable. Regarding the polarimetric signatures, the large values (with small dispersion) of the copolar correlation coefficient between horizontal and vertical polarization were also confirmed: the average value was 0.9961 (0.9982) in winter 2015 (January 2019); the daily standard deviations were very small, ranging from 0.0007 to 0.0030. The dispersion of the differential phase shift was also confirmed to be quite small: the daily standard deviation ranged from a minimum of 2.5° to a maximum of 5.3°. Radar reflectivities in both polarizations were typically around 80 dBz and were confirmed to be among the largest values observed in the surveillance volume of the Monte Lema radar. Finally, another recent 5-day data set from January 2020 was analyzed after the replacement of the radar calibration unit that includes low noise amplifiers: these five days show poorer characteristics of the polarimetric signatures and a few outliers affecting the spectral signatures. It was shown that the “historical” polarimetric and spectral signatures of a bright scatterer could represent a benchmark for an in-depth comparison after hardware replacements.

Resistance of a Ship Undergoing Oscillatory Motion

2010 ◽  
Vol 54 (02) ◽  
pp. 120-132
Author(s):  
Lawrence J. Doctors ◽  
Alexander H. Day ◽  
David Clelland
Keyword(s):  
Finite Depth ◽  
Mean Value ◽  
Wave Resistance ◽  
General Effect ◽  
Towing Tank ◽  
Ship Model ◽  
Average Value ◽  
Unsteady Effects ◽  
Oscillatory Cycle ◽  
Resistance Tests

In this paper, we describe extensions to the research of Doctors et al. (Doctors, L. J., Day, A. H., and Clelland, D., 2008, Unsteady effects during resistance tests on a ship model in a towing tank, Journal of Ship Research, 52, 4, 263–273) and Day et al. (Day, A. H., Clelland, D., and Doctors, L. J., 2009, Unsteady finite-depth effects during resistance tests in a towing tank, Journal of Marine Science and Technology, 14, 3, 387–397) in which the oscillations in the wave resistance during the constant-velocity phase of a towing-tank resistance test on a ship model were measured and predicted, in the cases of relatively deep and relatively shallow water. In the current study, the ship model was towed with a harmonic velocity component superimposed on the usual constant forward velocity. This work constitutes a first step in the understanding of the unsteady hydrodynamics of a racing shell (rowing boat). We show here that the unsteady wave resistance varies considerably from the traditional (steady) average value. Indeed, the wave resistance is frequently negative during part of the oscillatory cycle. However, the general effect is an increase in the temporal mean value of the wave resistance; this suggests that every effort should be made to reduce the unsteadiness of the motion. We also demonstrate that the unsteady wave-resistance theory provides an excellent prediction of the measured effects summarized here. These predictions are often within a few percent of the measured values of the resistance.

Sign in / Sign up

Export Citation Format

Share Document