Spelling suggestions: "subject:"[een] PEOPLE COUNTING"" "subject:"[enn] PEOPLE COUNTING""
1 |
Automatické počítání osob / Automatic counting of peopleMitáček, Štěpán January 2012 (has links)
This effort deals with the problem of effective counting of people in the room. Although more companies deal with this problem at present, but their systems are very expensive. For this reason I strive to find a cheaper solution for counting people using active infra- red sensors by which I want to perceive the passage of a person through the door or his presence in the room. In addition it is necessary to take into consideration the other various situations that may occur when a person comes into the room or when he/she leaves. These situations can be in many cases similar, but the output should be able correctly distinguish the possibilites. The result of this effort is detector which is able to detect correctly one person or more people passing the door. People can browse through a door one behind the other, but they also can pass in the doorway in random combinations.
|
2 |
Inteligentní prostředí / Ambient IntelligenceOndruška, Jiří January 2010 (has links)
Diploma thesis deals with Ambient intelligence issue. Represents its basic characteristic and demands for its realization. Describes actual stadium in this concept development and shows some present projects. Next focuses on Intelligent buildings issue. In connection with this addresses to so-called human behaviour patterns. Various methods of human behaviour patterns measurement are discussed there. Thesis then focuses on people counting system design, which is based on camera record. Such system represents way of human behaviour patterns measurement. Lastly, the using of this way obtained data is discussed.
|
3 |
[en] PEOPLE COUNTING SYSTEM / [pt] SISTEMA DE CONTAGEM DE PESSOASPRISCILA MARQUES DIAS 11 October 2005 (has links)
[pt] Atualmente, a preocupação com segurança vem crescendo dia
após dia.
Vários trabalhos abordando o desenvolvimento de sistemas
de supervisão já
foram realizados. Esta dissertação propõe um método
automático capaz de
determinar o número de pessoas em uma área monitorada por
uma câmera de
vídeo, assim como detectar mudanças na imagem
potencialmente causadas por
atitudes ilícitas. Uma aplicação típica seria a segurança
de galpões durante a
noite, em finais de semana ou em qualquer momento onde o
acesso de pessoas
é permitido, mas o movimento de cargas não. Mais
precisamente, a intenção é
detectar se uma pessoa que está passando pelo ambiente
carrega consigo um
objeto pertencente ao local ou deixa um objeto no local,
quando apenas o
movimento de pessoas é admitido na área. Além disto, o
sistema determina o
número de pessoas na cena. O método consiste na aplicação
de quatro etapas
em seqüências de vídeo: a) separação de fundo / primeiro
plano, b) atualização
dinâmica da estimativa de fundo, c) localização / contagem
de pessoas, e d)
detecção de atitudes suspeitas. Os algoritmos de separação
de fundo / primeiro
plano e de estimativa de fundo toleram variações pequenas
de iluminação e
efeitos de sombra. Já a contagem / localização de pessoas
explora informações
de cor e coerência de movimento. Soluções para atender
estes aspectos são
encontradas na literatura, porém nenhuma delas atende
todos eles juntos. O
método foi avaliado por experimentos realizados através de
um protótipo e
apresentou resultados encorajadores. / [en] There is worldwide an increasing concern about security
issues. A great
deal of efforts have been undertaken in order to provide
surveillance systems.
This work proposes an automatic method to determine the
number of people
moving in an area monitored by a video camera, as well as
to detect image
changes, which are potentially due to illicit attitudes. A
typical application is the
security of warehouses during the night, on weekends or at
any time when
people access is allowed but no load movement is
admissible. Specifically it
focuses on detecting when a person passing by the
environment carries any
object belonging to the background away or leaves any
object in the background,
while only people movement is allowed in the area. Besides
it estimates the
number of people on scene. The method consists of
performing four main tasks
on video sequences: a) background and foreground
separation, b) background
estimative dynamic update, c) people location and
counting, and d) suspicious
attitudes detection. The proposed background and
foreground separation and
background estimative update algorithms deal with
illumination fluctuation and
shade effects. People location and counting explores
colour information and
motion coherence. Solutions meeting these requirements are
proposed in the
literature, but no one deals with all of them together.
The method has been
validated by experiments carried out on a prototype and
produced encouraging results.
|
4 |
Nástroje pro počítání a monitorování osob / People counting and monitor toolsTill, Přemysl January 2021 (has links)
The paper details the usage of mmWave radars to track people and monitor their movement through predefined zones of interest. The theoretical part describes the physical nature of the technology and then describes algorithms which can be used to monitor using it to monitor the movement of people. In the practical part, I have developed a concrete algorithm which can be used to monitor customer queues and cash registers in shops and inform the cashiers when their presence is needed, as well as gather impersonal GDPR-compliant data about the customer's habits. Afterwards, I have developed a visualization for the Windows platform, which can be used to communicate with the radar, manage its configuration, visualize the events in real time and perform further analysis of the measured data.
|
5 |
Single pixel robust approach for background subtraction for fast people-counting and direction estimationAdegboye, Adedolapo Olaide 10 June 2013 (has links)
People counting system involves the process of counting and estimating the number of people in a scene. The counting system has a number of useful applications, ranging from pedestrian traffic surveillance and monitoring the number of people that enters and leaves shopping malls to commercial buildings, vehicles and a number of other security-related applications. Over the years, significant progress has been made. However, people counting systems still have not overcome a number of challenges such as occlusions, human pose and direction, multiple people detection, varying lighting and weather conditions. The aim of this research is to present an optimal solution that is invariant to the challenges. That is, the outcome of the results will not be affected by the challenges. Also, the solution will handle the trade-off between the counting accuracy and the time it takes to implement the counting process. As a result, a new background subtraction method known as single pixel method is proposed. This is where useful features are collected from each scene using frame difference method. Then, these features are reduced into single pixels. The single pixels are then used to estimate the total number of people in the scene. Furthermore, a virtual-line direction-estimation method is presented where the directions in which the people are heading are estimated prior to counting. AFRIKAANS : Mense-telstelsels behels die proses van die tel en die beraming van die aantal mense op ’n toneel. Die telstelsel het ’n aantal nuttige toepassings wat wissel van voetgangerverkeer toesig en die monitering van die aantal mense wat binnekom en verlaat tot winkelsentrums, kommersiële geboue, voertuie, en ’n aantal ander sekuriteit-verwante programme. Oor die jare is beduidende vordering gemaak. Daar is egter ’n aantal uitdagings wat mense-telstelsels nog nie oorkom het nie, soos afsluiting, menslike inhou en rigting, die opsporing van veelvoudige mense, wisselende beligting en weerstoestande. Die doel van hierdie navorsing is om ’n optimale oplossing aan te bied, wat invariant is teen die uitdagings. Met ander woorde, die uitdagings sal nie die resultate affekteer nie. Die oplossing sal ook die uitruil tussen die tel akkuraatheid en die implementeringstyd van die telproses hanteer. As gevolg hiervan, is ’n nuwe agtergrondaftrekkingsmetode, wat bekend staan as ’n enkele beeldelement metode, voorgestel. Dit is waar die nuttige funksies van elke toneel, met behulp van die raamverskilmetode ingesamel word. Dan word hierdie eienskappe in enkele beeldelemente verminder. Die enkele beeldelemente word dan gebruik om die totale aantal mense in die toneel te skat. Verder is daar van ’n virtuele-lyn rigting-skatting metode gebruik gemaak wat die rigtings waarin die mense beweeg vooraf beraam. / Dissertation (MEng)--University of Pretoria, 2013. / Electrical, Electronic and Computer Engineering / unrestricted
|
6 |
Utveckling av sensorbaserat system för personräkning i inomhusmiljö / Development of sensor-based system for indoor people countingSandström, Joakim January 2021 (has links)
I det här arbetet presenteras ett system som utvecklats i syfte att kunna räkna personer. Systemet är tänkt att användas i mötesrum för upp till tio personer och använder sig av infraröd teknik i form av thermopile arrayer. I arbetet har tre olika sensorer använts för utvärdering. Sensorerna som använts är Panasonic Grid-EYE med pixelupplösningen 8×8 och detekteringsvinkeln 60°×60° samt två stycken Heimann 32x32d, båda med upplösningen 32×32 pixlar, men med detekteringsvinkeln 90°×90° respektive 105°×105°. Systemet är programmerat med hjälp av utvecklingskortet STM32L476RG och är skrivet i språket C. I systemet används två metoder för att beräkna antalet personer. Den ena metoden jämför temperaturförändringen i ett rum i förhållande till då rummet är tomt och den andra metoden använder sig av bildbehandlingsmetoder som interpolering, filtrering och beräkning av area. Sensorerna utvärderas även individuellt utifrån egenskaper som noggrannhet, strömförbrukning och implementationskostnad. Script har även skapats i MATLAB som, i kombination med mikrokontrollern, används för att grafiskt presentera temperaturvärdena från sensorerna. Den sensor som visade sig vara bäst lämpad för att räkna personer är Heimann 32×32d med detekteringsvinkeln 105°×105°. Detta tack vare den större detekteringsvinkeln som resulterar i en större detekterbar yta samt upplösningen på totalt 1024 pixlar som sammantaget ger en högre noggrannhet för personräkning. Denna sensor kräver dock mer komplexa och tidskrävande beräkningar för behandling av data än Grid-EYE. Dessa skillnader är ändå marginella, där noggrannheten och den större detekterbara arean väger upp nackdelarna. De experimentella resultaten visar att Heimann 32×32d med 105°×105° ger en noggrannhet på c:a 98.3 % vid mätning på höjden 2.45 m. Detta motsvarar en yta på c:a 39.1 m2 och systemet kan räkna upp till minst 4 personer. För Grid-EYE och samma höjd har ej noggrannheten fastställts, men har endast en detekterbar yta på c:a 7.7 m2 där maximalt 4 personer bedöms kunna räknas. / In this work, a system is being developed with the purpose of counting people. The system is intended for use in meeting rooms for up to ten persons and utilizes infrared technique using thermopile arrays. For this work, three different sensor have been used for evaluation. A Panasonic Grid-EYE with a resolution of 8×8 and a Field of View (FoV) of 60°×60°, and two Heimann 32×32d sensors, both having a resolution of 32×32, but with the FoV 90°×90° and 105°×105° respectively. The system has been programmed using the microcontroller STM32L476RG, and with the programming language C. In this system, two methods for people counting has been implemented. The first method compares the total change in temperature of a room in relation to when the room is empty and the other method uses image processing methods, such as interpolation, filtering and area calculations. The sensors are also being evaluated individually, based on characteristics such as accuracy, current consumption and implementation cost. To graphically display the temperature values of the sensors, scripts has been made for MATLAB that uses information sent by the microcontroller. The sensor which seem to be best suited for counting people is the Heimann 32×32d with the FoV 105°×105°. The main advantage of this sensor is its wider FoV, covering a larger area, and its higher resolution, which overall yields a higher accuracy when counting people. However, this sensor requires more complex and time-consuming calculations when processing data than the Grid-EYE. Still, these differences are marginal where the accuracy and the larger detectable area for the HTPA outweighs its disadvantages. The experimental results shows that the Heimann sensor with 105°×105° FoV can achieve an accuracy of ≈98.3 % measuring at a height of 2.45 m. At this height, the detectable area for the sensor is ≈39.1 m2 and is being able to count up to at least 4 persons. As for the Grid-EYE and with the same scenario, the accuracy has not been determined, but has a detectable area of ≈7.7 m2 and is estimated being able to count up to a maximum of 4 persons.
|
7 |
Privacy-preserving Building Occupancy Estimation via Low-Resolution Infrared Thermal CamerasZhu, Shuai January 2021 (has links)
Building occupancy estimation has become an important topic for sustainable buildings that has attracted more attention during the pandemics. Estimating building occupancy is a considerable problem in computer vision, while computer vision has achieved breakthroughs in recent years. But, machine learning algorithms for computer vision demand large datasets that may contain users’ private information to train reliable models. As privacy issues pose a severe challenge in the field of machine learning, this work aims to develop a privacypreserved machine learningbased method for people counting using a lowresolution thermal camera with 32 × 24 pixels. The method is applicable for counting people in different scenarios, concretely, counting people in spaces smaller than the field of view (FoV) of the camera, as well as large spaces over the FoV of the camera. In the first scenario, counting people in small spaces, we directly count people within the FoV of the camera by Multiple Object Detection (MOD) techniques. Our MOD method achieves up to 56.8% mean average precision (mAP). In the second scenario, we use Multiple Object Tracking (MOT) techniques to track people entering and exiting the space. We record the number of people who entered and exited, and then calculate the number of people based on the tracking results. The MOT method reaches 47.4% multiple object tracking accuracy (MOTA), 78.2% multiple object tracking precision (MOTP), and 59.6% identification F-Score (IDF1). Apart from the method, we create a novel thermal images dataset containing 1770 thermal images with proper annotation. / Uppskattning av hur många personer som vistas i en byggnad har blivit ett viktigt ämne för hållbara byggnader och har fått mer uppmärksamhet under pandemierna. Uppskattningen av byggnaders beläggning är ett stort problem inom datorseende, samtidigt som datorseende har fått ett genombrott under de senaste åren. Algoritmer för maskininlärning för datorseende kräver dock stora datamängder som kan innehålla användarnas privata information för att träna tillförlitliga modeller. Eftersom integritetsfrågor utgör en allvarlig utmaning inom maskininlärning syftar detta arbete till att utveckla en integritetsbevarande maskininlärningsbaserad metod för personräkning med hjälp av en värmekamera med låg upplösning med 32 x 24 pixlar. Metoden kan användas för att räkna människor i olika scenarier, dvs. att räkna människor i utrymmen som är mindre än kamerans FoV och i stora utrymmen som är större än kamerans FoV. I det första scenariot, att räkna människor i små utrymmen, räknar vi direkt människor inom kamerans FoV med MOD teknik. Vår MOD-metod uppnår upp till 56,8% av den totala procentuella fördelningen. I det andra scenariot använder vi MOT-teknik för att spåra personer som går in i och ut ur rummet. Vi registrerar antalet personer som går in och ut och beräknar sedan antalet personer utifrån spårningsresultaten. MOT-metoden ger 47,4% MOTA, 78,2% MOTP och 59,6% IDF1. Förutom metoden skapar vi ett nytt dataset för värmebilder som innehåller 1770 värmebilder med korrekt annotering.
|
Page generated in 0.0412 seconds