A Growing Neural Gas Approach to Classify Vehicles in Traffic Environments

2017 ◽  
Vol 7 (3) ◽  
pp. 1-12 ◽  
Author(s):  
Miguel A. Molina-Cabello ◽  
Rafael Marcos Luque-Baena ◽  
Ezequiel López-Rubio ◽  
Juan Miguel Ortiz-de-Lazcano-Lobato ◽  
Enrique Domínguez
Keyword(s):  
Video Surveillance ◽  
Extraction Process ◽  
Traffic Monitoring ◽  
Point Of View ◽  
Growing Neural Gas ◽  
Feature Extraction Method ◽  
Vehicle Type ◽  
Neural Gas ◽  
Detection And Tracking ◽  
Tracking Object

Automated video surveillance presents a great amount of applications and one of them is traffic monitoring. Vehicle type detection can provide information about the characteristics of the traffic flow to human traffic controllers in order to facilitate their decision-making process. A video surveillance system is proposed in this work to execute such classification. First of all, a foreground detection and tracking object process has been carried out. Once the vehicles are detected, a feature extraction method obtains the most significant features of this detected vehicles. When the extraction process is done, the vehicle types are determined by employing a set of Growing Neural Gas neural networks. The performance of the proposal has been analyzed from a qualitative and quantitative point of view by using a set of benchmark traffic video sequences, with acceptable results.

scholarly journals Clustering of Trajectories in Video Surveillance Using Growing Neural Gas

2011 ◽  
pp. 461-470 ◽  
Author(s):  
Javier Acevedo-Rodríguez ◽  
Saturnino Maldonado-Bascón ◽  
Roberto López-Sastre ◽  
Pedro Gil-Jiménez ◽  
Antonio Fernández-Caballero
Keyword(s):  
Video Surveillance ◽  
Growing Neural Gas ◽  
Neural Gas

From Point Cloud to Triangular Mesh by Growing Neural Gas

2014 ◽  
Vol 24 (3) ◽  
pp. 651-662
Author(s):  
Feng ZENG ◽  
Tong YANG ◽  
Shan YAO
Keyword(s):  
Point Cloud ◽  
Triangular Mesh ◽  
Growing Neural Gas ◽  
Neural Gas

Growing Neural Gas Based on Data Density

2018 ◽  
pp. 314-323
Author(s):  
Lukáš Vojáček ◽  
Pavla Dráždilová ◽  
Jiří Dvorský
Keyword(s):  
Growing Neural Gas ◽  
Neural Gas ◽  
Data Density

scholarly journals Real-time 3D point cloud segmentation using Growing Neural Gas with Utility

2016 ◽  
Author(s):  
Yuichiro Toda ◽  
Zhaojie Ju ◽  
Hui Yu ◽  
Naoyuki Takesue ◽  
Kazuyoshi Wada ◽  
...  
Keyword(s):  
Real Time ◽  
Point Cloud ◽  
3D Point Cloud ◽  
Growing Neural Gas ◽  
Neural Gas ◽  
Point Cloud Segmentation

scholarly journals Emulsion Liquid Membrane Extraction of Turquoise Blue Reactive Dye–Study on Membrane Breakage and Swelling

2017 ◽  
Vol 11 (1) ◽  
Author(s):  
N. Othman ◽  
S. N. Zailani ◽  
N. Mili
Keyword(s):  
Liquid Membrane ◽  
Raw Materials ◽  
Extraction Process ◽  
Reactive Dye ◽  
Point Of View ◽  
Membrane Extraction ◽  
Hydrodynamic Condition ◽  
Emulsion Liquid Membrane ◽  
Liquid Membrane Extraction ◽  
Span 80

Reactive dyes are the principal dyes used in batik industry in Malaysia. From the environmental point of view the dyes should be removed from wastewater because they are toxic in nature. Therefore, the removal and recovery of dyes from batik industry wastewater is absolute necessity in order to save raw materials and to protect environment from hazardous compounds. An experiment was carried out using emulsion liquid membrane (ELM) process in batch system to study the extraction behaviour of Turquoise Blue which is commonly used in batik industry. Several parameters have been studied such as carrier and surfactant/emulsifier concentrations, stripping agent and extraction time. The liquid membrane was formulated using kerosene as diluent, SPAN 80 as emulsifier and tri-dodecylamine (TDA) as a carrier. Hydrodynamic condition to generate extraction process was at 1:3 treat ratio and 250 rpm stirring speed for 10 minutes while the emulsification was done at 12000 rpm for 5 minutes using homogenizer. The result obtained shows that, more than 70% of Turquoise Blue was extracted at favourable condition of 0.07 M TDA, 7% (w/v) SPAN 80 and 0.5 M Thiourea in 1 M NaOH.

scholarly journals Sztuczne sieci neuronowe i teledetekcja w ocenie porażenia pszenicy jarej fuzariozą kłosów

2020 ◽  
pp. 67-75
Author(s):  
Wiesław Golka ◽  
Edward Arseniuk ◽  
Adrian Golka ◽  
Tomasz Góral
Keyword(s):  
Fusarium Spp ◽  
Growing Neural Gas ◽  
Vegetation Control ◽  
Neural Gas

Celem prac badawczych było wykorzystanie teledetekcji oraz sztucznych sieci neuronowych w ocenie pszenicy jarej pod względem reakcji na fuzariozę kłosów wywoływaną przez grzyby z rodzaju Fusarium spp. Prace badawcze wykonano na roślinach 4 odmian pszenicy jarej. Były to: KWS Torridon i Izera – o wyższej odporności, Radocha i Nawra – o odporności niższej na ww. patogena. Wykonano zdjęcia zdrowych oraz porażonych kłosów wszystkich odmian, które następnie przetworzono przy użyciu programu Crops Vegetation Control Lab (CVC Lab.). Na podstawie uzyskanych obrazów utworzono ich reprezentacje w postaci sieci neuronowych Growing Neural Gas (GNG). W wyniku analizy zdjęć uzyskano 240 wzorców, z których wybrano po 6 bazowych wzorców choroby dla każdej odmiany. Następnie dokonano porównania próbek porażonych kłosów danej odmiany z bazowymi wzorcami chorobowymi tej samej odmiany pszenicy. W wyniku porównania wzorców roślin zdrowych i porażonych ze zdjęciami poletek roślin zdrowych i porażonych uzyskano zróżnicowanie wartości liczbowych dającej podstawę do konstrukcji mapy zdrowotności plantacji pszenicy z wyszczególnieniem ognisk choroby.

Sign in / Sign up

Export Citation Format

Share Document