|
|
People Detection Using Radar
Bartko, Jakub ; Zemčík, Pavel (referee) ; Maršík, Lukáš (advisor)
Cieľom tejto práce je výzkum použiteľnosti techník hlbokého učenia na mračnách bodov generovaných radarmi, ktoré operujú v pásme milimetrových vĺn; na účely porozumenia 3D scénam a rozpoznávania osôb. Radar je systém, ktorý využíva rádiové vlny na získavanie informácií o vzdiaľenosti a smere k objektu a o jeho rýchlosti. Na základe týchto dát je možné určiť pozíciu každého detekovaného bodu v priestore. Množina takýchto bodov sa nazýva mračno bodov. Hlboké neurónové siete navrhnuté na prácu s riedkymi mračnami bodov v 3D môžu byť natrénované na segmentáciu radarových mračien, detekciu a klasifikáciu objektov a sledovanie ich pohybu v priestore. Systémy, ktoré sú na nich postavené, môžu predstavovať veľký pokrok v oblasti interpretácie 3D scén autonómnymi strojmi. V rámci tejto práce bol model budujúci na súčasnom stave techniky natrénovaný na detekciu a klasifikáciu objektov a osôb, na základe radarových mračien bodov v 3D. Na ukážku robustnosti natrénovaného modelu a priamočiarosti jeho zapojenia na riešenie významných úloh z reálneho sveta, bola implementovaná aplikácia na počítanie a klasifiká ciu ľudí. Presnosť využitých metód aj výsledného systému bola dôkladne vyhodnotená na súbore dát vytvorenom v rámci tejto práce z radarových mračien bodov, ktorý pozostáva z viac, než 19 500 anotovaných objektov.
|
|
|
People counting and monitor tools
Till, Přemysl ; Kváš, Marek (referee) ; Valach, Soběslav (advisor)
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.
|
|
|
Ambient Intelligence
Ondruška, Jiří ; Pohl, Jan (referee) ; Jirsík, Václav (advisor)
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.
|
|
|
Automatic counting of people
Mitáček, Štěpán ; Číž, Radim (referee) ; Koutný, Martin (advisor)
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.
|
|
|
People Detection Using Radar
Bartko, Jakub ; Zemčík, Pavel (referee) ; Maršík, Lukáš (advisor)
Cieľom tejto práce je výzkum použiteľnosti techník hlbokého učenia na mračnách bodov generovaných radarmi, ktoré operujú v pásme milimetrových vĺn; na účely porozumenia 3D scénam a rozpoznávania osôb. Radar je systém, ktorý využíva rádiové vlny na získavanie informácií o vzdiaľenosti a smere k objektu a o jeho rýchlosti. Na základe týchto dát je možné určiť pozíciu každého detekovaného bodu v priestore. Množina takýchto bodov sa nazýva mračno bodov. Hlboké neurónové siete navrhnuté na prácu s riedkymi mračnami bodov v 3D môžu byť natrénované na segmentáciu radarových mračien, detekciu a klasifikáciu objektov a sledovanie ich pohybu v priestore. Systémy, ktoré sú na nich postavené, môžu predstavovať veľký pokrok v oblasti interpretácie 3D scén autonómnymi strojmi. V rámci tejto práce bol model budujúci na súčasnom stave techniky natrénovaný na detekciu a klasifikáciu objektov a osôb, na základe radarových mračien bodov v 3D. Na ukážku robustnosti natrénovaného modelu a priamočiarosti jeho zapojenia na riešenie významných úloh z reálneho sveta, bola implementovaná aplikácia na počítanie a klasifiká ciu ľudí. Presnosť využitých metód aj výsledného systému bola dôkladne vyhodnotená na súbore dát vytvorenom v rámci tejto práce z radarových mračien bodov, ktorý pozostáva z viac, než 19 500 anotovaných objektov.
|
|
|
People counting and monitor tools
Till, Přemysl ; Kváš, Marek (referee) ; Valach, Soběslav (advisor)
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.
|
|
|
Automatic counting of people
Mitáček, Štěpán ; Číž, Radim (referee) ; Koutný, Martin (advisor)
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.
|
|
|
Ambient Intelligence
Ondruška, Jiří ; Pohl, Jan (referee) ; Jirsík, Václav (advisor)
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.
|
guest ::
