|
|
Perimeter Monitoring and Intrusion Detection Based on Camera Surveillance
Goldmann, Tomáš ; Drahanský, Martin (referee) ; Orság, Filip (advisor)
This bachelor thesis contains a description of the basic system for perimeter monitoring. The main part of the thesis introduces the methods of computer vision suitable for detection and classification of objects. Furthermore, I devised an algorithm based on background subtraction which uses a Histogram of Oriented Gradients for description of objects and an SVM classifier for their classification. The final part of the thesis consists of a comparison of the descriptor based on the Histogram of Oriented Gradients and the SIFT descriptor and an evaluation of precision of the detection algorithm.
|
|
|
Pedestrians Tracking in a Video Record from a Stationary Camera
Trnkal, Milan ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
This bachelor thesis focuses on pedestrians tracking from camera. In this work, I have introduced several methods of computer vision suitable for detection and classification of people. I proposed an algorithm for detecting and tracking pedestrians based on detection of movement. The application uses a Histogram of Oriented Gradients and SVM classifier together with color histograms for identification of pedestrians. Pedestrian's trajectories are then rendered to the output. Last part of the thesis deals with testing and evaluation of the results of the algorithm.
|
|
|
Detection of Anomalies in Pedestrian Walking
Pokorný, Ondřej ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
The goal of this work was to create a system that would be able to detect anomalies in pedestrian walking. As the core of my application, I have used OpenPose, which is an application for detecting human skeletons. Then I used a bidirectional LSTM neural network to detect anomalies in video sequences. This architecture was chosen during the experiment because it outperformed other solutions. I trained my model to detect three types of anomalies. The output of my application is a video with marked sequences of anomalies. The whole system is implemented in Python.
|
|
|
Monitoring Pedestrian by Drone
Dušek, Vladimír ; Goldmann, Tomáš (referee) ; Drahanský, Martin (advisor)
This thesis is focused on monitoring people in a video footage captured by drone. People are detected by trained model of detector RetinaNet. A feature vector is extracted for each detected person using color histograms. Identification of people is realized by comparing their feature vectors with respect to their distance in the frame. In the end the trajectories of all people are visualized in a panorama image. Accuracy of the trained RetinaNet detector on difficult validation data is 58.6 %. Error rate is partially reduced by the way of algorithm design for trajectory visualisation. It's not necessary to successfully detect person on every frame for correct visualization of its trajectories. At the same time, static objects which are detected as person but are not moving are not consider as people and are not visualized at all. There is a lot of algorithms dealing with people detection however only a few approaches are focused on detection people from an aerial footage.
|
|
|
Sensor fusion for detecting and locating people in a room
Vondráček, Jakub ; Dobossy, Barnabás (referee) ; Najman, Jan (advisor)
This diploma thesis deals with the problem of fusion of several sensors for the purpose of detecting and locating people in a room. It is primarily about using measured sensors and implementing them in such a way that their connection creates a system that has obvious advantages compared to more expensive single sensor solutions. In the first part of the work, research is carried out, which presents the basic issues of detection, localization and counting of people in rooms. To be used in the practical part of the work, it is also indicated here which specific sensors can be used to achieve these functions and which control units are suitable for such a system. Finally, it summarizes specific components and software tools, which are further supplemented in the practical part of the work. The rationale for this selection is also included. The second part of the thesis describes the specific design of the resulting system, which can perform the functions of detection, localization and counting of people in the room. This practical proposal is described including all starting points, connections and especially the algorithm that was used for sensor fusion. The entire system is subsequently tested, based on which its functioning is evaluated. In the last section of the thesis, the created system is supplemented with a model of a cover and wall mount.
|
|
|
Detection of Anomalies in Pedestrian Walking
Pokorný, Ondřej ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
The goal of this work was to create a system that would be able to detect anomalies in pedestrian walking. As the core of my application, I have used OpenPose, which is an application for detecting human skeletons. Then I used a bidirectional LSTM neural network to detect anomalies in video sequences. This architecture was chosen during the experiment because it outperformed other solutions. I trained my model to detect three types of anomalies. The output of my application is a video with marked sequences of anomalies. The whole system is implemented in Python.
|
|
|
Monitoring Pedestrian by Drone
Dušek, Vladimír ; Goldmann, Tomáš (referee) ; Drahanský, Martin (advisor)
This thesis is focused on monitoring people in a video footage captured by drone. People are detected by trained model of detector RetinaNet. A feature vector is extracted for each detected person using color histograms. Identification of people is realized by comparing their feature vectors with respect to their distance in the frame. In the end the trajectories of all people are visualized in a panorama image. Accuracy of the trained RetinaNet detector on difficult validation data is 58.6 %. Error rate is partially reduced by the way of algorithm design for trajectory visualisation. It's not necessary to successfully detect person on every frame for correct visualization of its trajectories. At the same time, static objects which are detected as person but are not moving are not consider as people and are not visualized at all. There is a lot of algorithms dealing with people detection however only a few approaches are focused on detection people from an aerial footage.
|
|
|
Pedestrians Tracking in a Video Record from a Stationary Camera
Trnkal, Milan ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
This bachelor thesis focuses on pedestrians tracking from camera. In this work, I have introduced several methods of computer vision suitable for detection and classification of people. I proposed an algorithm for detecting and tracking pedestrians based on detection of movement. The application uses a Histogram of Oriented Gradients and SVM classifier together with color histograms for identification of pedestrians. Pedestrian's trajectories are then rendered to the output. Last part of the thesis deals with testing and evaluation of the results of the algorithm.
|
|
|
Perimeter Monitoring and Intrusion Detection Based on Camera Surveillance
Goldmann, Tomáš ; Drahanský, Martin (referee) ; Orság, Filip (advisor)
This bachelor thesis contains a description of the basic system for perimeter monitoring. The main part of the thesis introduces the methods of computer vision suitable for detection and classification of objects. Furthermore, I devised an algorithm based on background subtraction which uses a Histogram of Oriented Gradients for description of objects and an SVM classifier for their classification. The final part of the thesis consists of a comparison of the descriptor based on the Histogram of Oriented Gradients and the SIFT descriptor and an evaluation of precision of the detection algorithm.
|
guest ::
