Search

Bluetooth is a technology widely used in device pairing. Everybody has got a device with Bluetooth: a mobile phone, headphones, a smart watch¿ Therefore, this technology can be used in order to detect these devices. The aim of this work is to apply people detection with a drone detecting Bluetooth devices. One of the main problems is when the police forces need to control a huge crowd. An important information for them is the number of people. Nowadays image sensing is used with drones, but other possibilities can be studied. In this investigation, Bluetooth technology will be used in order to count how many people are in a specific place. Running races are the main tests performed in order to conclude if it is possible to know how many people are concentrated. Another problem is when people get lost in forests. The search and rescue teams nowadays use helicopters and drones equipped with cameras in order to search people, but it is difficult to distinguish people if the aircraft is flying in high altitudes. Bluetooth detection can be a solution for this problem. The RSSI from a device will be used in order to know if the drone is near or far from it, and therefore, from the person. There are many factors that must be taken into account such as transmission power, drone speed, altitude¿ The devices that are detected can be divided into two categories. The passive search is the one using people's devices like mobile phones, smart watches and other personal devices. The active search is the one done using devices specially designed for this task and carried by the people. The conclusion is that Bluetooth is a technology that can not be used in order to count how many people are in a specific area as devices change their addresses very frequently and there are many devices detected, resulting in erroneous people counting. However, Bluetooth can be used in order to detect people in remote areas without the need of the internet. The precision and accuracy of the detectio, Objectius de Desenvolupament Sostenible::9 - Indústria, Innovació i Infraestructura

This thesis is about exploring the possibility to make a system that could be implemented in e-scooters to help their users to use them in a secure manner. The objective of this thesis is to find if it is possible to train a detector to distinguish between pedestrians, bikes and e-scooters and being able to track them. I trained an object detector that classifies between the 3 categories mentioned above and used a multi-object tracking algorithm. The results from the Yolov5 detector results were 0.97 of map0.5 and 0.80 of map0.5:0.95, which for this case are good results. The result from the StrongSORT tracker regarding the HOTA metric was 90.87. We can conclude that the results are good. It is possible to detect, classify and track pedestrians, cyclists, and e-scooter users, but the time taken is too large for an implementation in real-time., Esta tesis es sobre explorar la posibilidad de crear un sistema se pudiese implementar en patinetes eléctricos para ayudar a sus usuarios a hacer un uso seguro de ellos. El objetivo de esta tesis es descubrir si es posible entrenar un detector para que sea capaz de distinguir entre peatones, ciclistas y usuarios de patinete eléctrico y realizar un seguimiento entre imágenes (tracker). He entrenado un detector de objetos que clasifica entre las 3 categorías mencionadas anteriormente y he usado un algoritmo de seguimiento de objetos. Los resultados del detector Yolov5 han sido el map0.5 0,97 y el map0.5:0.95 0,80, los cuales en este caso son buenos resultados. El resultado del tracker StrongSORT respecto a la métrica HOTA fue 90,87. Podemos concluir que los resultados han sido buenos. Es posible detectar, clasificar y realizar un track de peatones, ciclistas y usuarios de patinete eléctrico, pero el tiempo requerido es demasiado largo para una implementación en tiempo real., Amb aquesta tesi es vol explorar la possibilitat de fer un sistema que es pugui implementar en patinets elèctrics per ajudar els seus usuaris a utilitzar-los de forma més segura. L'objectiu d'aquesta tesi és trobar si és possible entrenar un detector per tal que distingeixi entre vianants, bicis i patinets elèctrics i fer un seguiment (tracker). He entrenat un detector d'objectes que classifica entre les tres categories mencionades abans i he fet servir un algorisme de seguiment d'objectes. Els resultats del detector Yolov5 han sigut 0,97 de map0.5 i 0,80 de map0.5:0.95, els quals en aquest cas són bons resultats. El resultat del tracker StrongSORT, respecte a la mètrica HOTA ha sigut 90.87. Podem concloure que els resultats són bons. És possible detectar, classificar i fer un seguiment de vianants, ciclistes i usuaris de patinets elèctrics, però el temps requerit és massa llarg per una implementació en temps real.

In image detection processes where there is a variation in brightness between pixels, techniques are required to obtain optimal and adaptable threshold values for these variations. Therefore, a comparison between the binary thresholding technique and the adaptive method of Otsu is made, in videos with dynamic and static background, weighing the response time of the algorithm, memory used, requirement of the central processing unit and hits in the detections, in the languages of Python and M (Matlab). The techniques in Python present better results in terms of response time and memory space; while, when using Matlab, the lowest percentage of machine requirement is presented. Also, the Otsu method improves the percentage of hits in 12.89 % and 11.3 % for videos with dynamic and static background, with respect to the binary thresholding technique., En procesos de detección por imágenes en las que existe variación de luminosidad entre pixeles, se requieren técnicas que permitan obtener valores óptimos y adaptables de umbral ante dichas variaciones. Por ello, se realiza una comparativa entre la técnica de umbralización binaria y el método adaptativo de Otsu, en videos con fondo dinámico y estático, ponderando el tiempo de respuesta del algoritmo, memoria utilizada, requerimiento de la unidad central de procesos y aciertos en las detecciones, en los lenguajes de Python y M (Matlab). Las técnicas en Python presentan mejores resultados en cuanto a tiempo de respuesta y espacio de memoria; mientras que, al utilizar Matlab, se presenta el menor porcentaje de requerimiento de máquina. Asimismo, el método de Otsu mejora el porcentaje de aciertos en 12.89 % y 11.3 % para videos con fondo dinámico y estático, respecto a la técnica de umbralización binaria.

Die Einsatzbedingungen fahrerloser Transportfahrzeuge (FTF) werden zunehmend dynamischer und deren Anzahl in Umgebungen, in denen sich auch Personen aufhalten nimmt stetig zu. Um eine sichere Zusammenarbeit zwischen FTF und Personen zu gewährleisten, bedarf es Sensorsysteme, die eine explizite Erkennung von Personen ermöglichen. In diesem Beitrag soll ein solches sicherheitsbezogenes Sensorsystem anhand eines Konzeptes und eines Demonstrators vorgestellt werden., The operating conditions of Automated Guided Vehicles (AGVs) are becoming increasingly dynamic and their number in environments where people are present is constantly increasing. In order to ensure safe cooperation be-tween AGVs and people, sensor systems are required that enable the explicit recognition of people. In this paper such a safety related sensor system will be presented by means of a concept and a demonstrator.

Die Einsatzbedingungen fahrerloser Transportfahrzeuge (FTF) werden zunehmend dynamischer und deren Anzahl in Umgebungen, in denen sich auch Personen aufhalten nimmt stetig zu. Um eine sichere Zusammenarbeit zwischen FTF und Personen zu gewährleisten, bedarf es Sensorsysteme, die eine explizite Erkennung von Personen ermöglichen. In diesem Beitrag soll ein solches sicherheitsbezogenes Sensorsystem anhand eines Konzeptes und eines Demonstrators vorgestellt werden., The operating conditions of Automated Guided Vehicles (AGVs) are becoming increasingly dynamic and their number in environments where people are present is constantly increasing. In order to ensure safe cooperation be-tween AGVs and people, sensor systems are required that enable the explicit recognition of people. In this paper such a safety related sensor system will be presented by means of a concept and a demonstrator.

Die Einsatzbedingungen fahrerloser Transportfahrzeuge (FTF) werden zunehmend dynamischer und deren Anzahl in Umgebungen, in denen sich auch Personen aufhalten nimmt stetig zu. Um eine sichere Zusammenarbeit zwischen FTF und Personen zu gewährleisten, bedarf es Sensorsysteme, die eine explizite Erkennung von Personen ermöglichen. In diesem Beitrag soll ein solches sicherheitsbezogenes Sensorsystem anhand eines Konzeptes und eines Demonstrators vorgestellt werden., The operating conditions of Automated Guided Vehicles (AGVs) are becoming increasingly dynamic and their number in environments where people are present is constantly increasing. In order to ensure safe cooperation be-tween AGVs and people, sensor systems are required that enable the explicit recognition of people. In this paper such a safety related sensor system will be presented by means of a concept and a demonstrator.

Die Einsatzbedingungen fahrerloser Transportfahrzeuge (FTF) werden zunehmend dynamischer und deren Anzahl in Umgebungen, in denen sich auch Personen aufhalten nimmt stetig zu. Um eine sichere Zusammenarbeit zwischen FTF und Personen zu gewährleisten, bedarf es Sensorsysteme, die eine explizite Erkennung von Personen ermöglichen. In diesem Beitrag soll ein solches sicherheitsbezogenes Sensorsystem anhand eines Konzeptes und eines Demonstrators vorgestellt werden., The operating conditions of Automated Guided Vehicles (AGVs) are becoming increasingly dynamic and their number in environments where people are present is constantly increasing. In order to ensure safe cooperation be-tween AGVs and people, sensor systems are required that enable the explicit recognition of people. In this paper such a safety related sensor system will be presented by means of a concept and a demonstrator.

Large cities in the Netherlands, like Rotterdam, have hundreds of playgrounds, but local governments have little information on how children and adults use them. Usage data can help create playgrounds that better fit with the residents' needs by identifying what elements of a playground are the most popular, and which do not get used. The AMS Institute and municipality of Rotterdam have asked us to develop a system to collect usage information of playgrounds without recording personally identifiable information. The system requirements are to record the locations of individual users and to estimate if a user is a child or an adult. It must do this without requiring an external power source and without a broadband internet connection. After considering different types of sensors (including computer vision, radio, sound, and mechanical acoustic signals), We decided to use a mmWave radar sensor due to its ability to provide accurate localization, easy installation, and low energy usage without recording identifiable information. We use a commercially available mmWave radar sensor that we configure to localize people in a 30m by 20m area when placed at the perimeter. We use the radar point cloud output from the device for classification by calculating statistics that we use as features for our classifier. We evaluate classifiers based on SVM, Random Forrest, fully connected and recurrent neural nets. We also analyze different methods for combining radar point clouds captured over time from the same person. We collected 100.000 radar point clouds of adults, children, and bicyclists at real playgrounds, split into a training and validation data set. We show that our SVM classifier achieves an accuracy of 79% on single radar frames, and 93% on the combined results of 10 second long sequences of our validation dataset. The classifier requires <1KB of memory and little processing power. Meaning it can execute on an embedded platform powered by a solar panel., Electrical Engineer | Embedded Systems

Large cities in the Netherlands, like Rotterdam, have hundreds of playgrounds, but local governments have little information on how children and adults use them. Usage data can help create playgrounds that better fit with the residents' needs by identifying what elements of a playground are the most popular, and which do not get used. The AMS Institute and municipality of Rotterdam have asked us to develop a system to collect usage information of playgrounds without recording personally identifiable information. The system requirements are to record the locations of individual users and to estimate if a user is a child or an adult. It must do this without requiring an external power source and without a broadband internet connection. After considering different types of sensors (including computer vision, radio, sound, and mechanical acoustic signals), We decided to use a mmWave radar sensor due to its ability to provide accurate localization, easy installation, and low energy usage without recording identifiable information. We use a commercially available mmWave radar sensor that we configure to localize people in a 30m by 20m area when placed at the perimeter. We use the radar point cloud output from the device for classification by calculating statistics that we use as features for our classifier. We evaluate classifiers based on SVM, Random Forrest, fully connected and recurrent neural nets. We also analyze different methods for combining radar point clouds captured over time from the same person. We collected 100.000 radar point clouds of adults, children, and bicyclists at real playgrounds, split into a training and validation data set. We show that our SVM classifier achieves an accuracy of 79% on single radar frames, and 93% on the combined results of 10 second long sequences of our validation dataset. The classifier requires <1KB of memory and little processing power. Meaning it can execute on an embedded platform powered by a solar panel., Electrical Engineering | Embedded Systems

Die Einsatzbedingungen fahrerloser Transportfahrzeuge (FTF) werden zunehmend dynamischer und deren Anzahl in Umgebungen, in denen sich auch Personen aufhalten nimmt stetig zu. Um eine sichere Zusammenarbeit zwischen FTF und Personen zu gewährleisten, bedarf es Sensorsysteme, die eine explizite Erkennung von Personen ermöglichen. In diesem Beitrag soll ein solches sicherheitsbezogenes Sensorsystem anhand eines Konzeptes und eines Demonstrators vorgestellt werden., The operating conditions of Automated Guided Vehicles (AGVs) are becoming increasingly dynamic and their number in environments where people are present is constantly increasing. In order to ensure safe cooperation be-tween AGVs and people, sensor systems are required that enable the explicit recognition of people. In this paper such a safety related sensor system will be presented by means of a concept and a demonstrator.

During the last decades, people detection has received great attention in computer vision and pattern recognition because of its various applications. Though there are thousands of papers provide approaches for people detection, most of them focus on datasets from side view. People detection from overhead cameras, as an important situation for surveillance, is essential to research. This work based on annotated videos from MatchNMingle dataset, which are taken by overhead cameras. The videos were taken in a mingle after a speed-dating event. People are annotated by bounding boxes contain their body. In this crowded social scene, people occlusion is one of the challenge barriers for detection. In this work, we study the relation between people occlusion and detecting performance by experiments. Based on a deep network consisting of GoogLeNet and Overfeat, we analyze the performance of detectors trained with various occlusion distribution at different occlusion level. On the ground of experiment results, we attempt to promote the performance by selection of training data. Apart from this, as an attempt for promotion, we train head detectors by newly collected head annotation. The performance evaluation of these two methods indicates their potential for people detection in crowded scene., Electrical Engineer | Embedded Systems

During the last decades, people detection has received great attention in computer vision and pattern recognition because of its various applications. Though there are thousands of papers provide approaches for people detection, most of them focus on datasets from side view. People detection from overhead cameras, as an important situation for surveillance, is essential to research. This work based on annotated videos from MatchNMingle dataset, which are taken by overhead cameras. The videos were taken in a mingle after a speed-dating event. People are annotated by bounding boxes contain their body. In this crowded social scene, people occlusion is one of the challenge barriers for detection. In this work, we study the relation between people occlusion and detecting performance by experiments. Based on a deep network consisting of GoogLeNet and Overfeat, we analyze the performance of detectors trained with various occlusion distribution at different occlusion level. On the ground of experiment results, we attempt to promote the performance by selection of training data. Apart from this, as an attempt for promotion, we train head detectors by newly collected head annotation. The performance evaluation of these two methods indicates their potential for people detection in crowded scene., Electrical Engineering | Embedded Systems

This paper presents a robust and real-time method for people detection in urban and crowed environments. Unlike other conventional methods which either focus on single features or compute multiple and independent classifiers specialized in a particular feature space, the proposed approach creates a synergic combination of appearance and depth cues in a unique classifier. The core of our method is a Boosted Random Ferns classifier that selects automatically the most discriminative local binary features for both the appearance and depth image spaces. Based on this classifier, a fast and robust people detector which maintains high detection rates in spite of environmental changes is created. The proposed method has been validated in a challenging RGB-D database of people in urban scenarios and has shown that outperforms state-of-the-art approaches in spite of the difficult environment conditions. As a result, this method is of special interest for real-time robotic applications where people detection is a key matter, such as human-robot interaction or safe navigation of mobile robots for example.

This chapter presents a novel possible solution for people detection and estimation of their 3D position in challenging shared environments. Addressing safety critical applications in industrial environments, we make the basic assumption that people wear reflective vests. In order to detect these vests and to discriminate them from other reflective material, we propose an approach based on a single camera equipped with an IR flash. The camera acquires pairs of images, one with and one without IR flash, in short succession. The images forming a pair are then related to each other through feature tracking, which allows to discard features for which the relative intensity difference is small and which are thus not believed to belong to a reflective vest. Next, the local neighbourhood of the remaining features is further analysed. First, a Random Forest classifier is used to discriminate between features caused by a reflective vest and features caused by some other reflective materials. Second, the distance between the camera and the vest features is estimated using a Random Forest regressor. The proposed system was evaluated in one indoor and two challenging outdoor scenarios. Our results indicate very good classification performance and remarkably accurate distance estimation especially in combination with the SURF descriptor, even under direct exposure to sunlight., SAVIE

Detecting people is a key capability for robots that operate in populated environments. In this paper, we have adopted a hierarchical approach that combines classifiers created using supervised learning in order to identify whether a person is in the view-scope of the robot or not. Our approach makes use of vision, depth and thermal sensors mounted on top of a mobile platform. The set of sensors is set up combining the rich data source offered by a Kinect sensor, which provides vision and depth at low cost, and a thermopile array sensor. Experimental results carried out with a mobile platform in a manufacturing shop floor and in a science museum have shown that the false positive rate achieved using any single cue is drastically reduced. The performance of our algorithm improves other well-known approaches, such as C-4 and histogram of oriented gradients (HOG).

In most cases today when a specific person's whereabouts is monitored through video surveillance it is done manually and his or her location when not seen is based on assumptions on how fast he or she can move. Since humans are good at recognizing people this can be done accurately, given good video data, but the time needed to go through all data is extensive and therefore expensive. Because of the rapid technical development computers are getting cheaper to use and therefore more interesting to use for tedious work. This thesis is a part of a larger project that aims to see to what extent it is possible to estimate a person of interest's time dependent 3D position, when seen in surveillance videos. The surveillance videos are recorded with non overlapping monocular cameras. Furthermore the project aims to see if the person of interest's movement, when position data is unavailable, could be predicted. The outcome of the project is a software capable of following a person of interest's movement with an error estimate visualized as an area indicating where the person of interest might be at a specific time. This thesis main focus is to implement and evaluate a people detector meant to be used in the project, reduce noise in position measurement, predict the position when the person of interest's location is unknown, and to evaluate the complete project. The project combines known methods in computer vision and signal processing and the outcome is a software that can be used on a normal PC running on a Windows operating system. The software implemented in the thesis use a Hough transform based people detector and a Kalman filter for one step ahead prediction. The detector is evaluated with known methods such as Miss-rate vs. False Positives per Window or Image (FPPW and FPPI respectively) and Recall vs. 1-Precision. The results indicate that it is possible to estimate a person of interest's 3D position with single monocular cameras. It is also possible to follow the m

Detecting people is a key capability for robots that operate in populated environments. In this paper, we have adopted a hierarchical approach that combines classifiers created using supervised learning in order to identify whether a person is in the view-scope of the robot or not. Our approach makes use of vision, depth and thermal sensors mounted on top of a mobile platform. The set of sensors is set up combining the rich data source offered by a Kinect sensor, which provides vision and depth at low cost, and a thermopile array sensor. Experimental results carried out with a mobile platform in a manufacturing shop floor and in a science museum have shown that the false positive rate achieved using any single cue is drastically reduced. The performance of our algorithm improves other well-known approaches, such as C-4 and histogram of oriented gradients (HOG).

[ES] El objetivo de esta tesina es realizar un estudio de algoritmos y paquetes software existentes en la plataforma ROS (Robot Operating System) para la detección de personas, y comprobar el funcionamiento de alguno de ellos. El estudio se centrará principalmente en algoritmos que se basen en visión artificial y sensores de rango para sistemas de tipo ADAS (Advanced Driving Assistance Systems), en los que la detección de personas se utiliza para evitar accidentes. Se ha probado uno de los detectores existentes (Histrogram of Oriented Gradients o HOG) y se ha combinado con una técnica de detección de objetos verticales, reduciendo el tiempo de ejecución, [EN] In this project a survey of people detection algorithms and software in ROS framework is made. The survey is focused on algorithms using computer vision and range sensors for Advanced Driving Assistance Systems (ADAS), in wich people detection is used to avoid traffic accidents. One of the state-of-the-art methods (Histogram of Oriented Gradients or HOG) has been tested separatedly and with a vertical object detection algorithm, reducing the execution time

[ES] El objetivo de esta tesina es realizar un estudio de algoritmos y paquetes software existentes en la plataforma ROS (Robot Operating System) para la detección de personas, y comprobar el funcionamiento de alguno de ellos. El estudio se centrará principalmente en algoritmos que se basen en visión artificial y sensores de rango para sistemas de tipo ADAS (Advanced Driving Assistance Systems), en los que la detección de personas se utiliza para evitar accidentes. Se ha probado uno de los detectores existentes (Histrogram of Oriented Gradients o HOG) y se ha combinado con una técnica de detección de objetos verticales, reduciendo el tiempo de ejecución, [EN] In this project a survey of people detection algorithms and software in ROS framework is made. The survey is focused on algorithms using computer vision and range sensors for Advanced Driving Assistance Systems (ADAS), in wich people detection is used to avoid traffic accidents. One of the state-of-the-art methods (Histogram of Oriented Gradients or HOG) has been tested separatedly and with a vertical object detection algorithm, reducing the execution time

[ES] El objetivo de esta tesina es realizar un estudio de algoritmos y paquetes software existentes en la plataforma ROS (Robot Operating System) para la detección de personas, y comprobar el funcionamiento de alguno de ellos. El estudio se centrará principalmente en algoritmos que se basen en visión artificial y sensores de rango para sistemas de tipo ADAS (Advanced Driving Assistance Systems), en los que la detección de personas se utiliza para evitar accidentes. Se ha probado uno de los detectores existentes (Histrogram of Oriented Gradients o HOG) y se ha combinado con una técnica de detección de objetos verticales, reduciendo el tiempo de ejecución, [EN] In this project a survey of people detection algorithms and software in ROS framework is made. The survey is focused on algorithms using computer vision and range sensors for Advanced Driving Assistance Systems (ADAS), in wich people detection is used to avoid traffic accidents. One of the state-of-the-art methods (Histogram of Oriented Gradients or HOG) has been tested separatedly and with a vertical object detection algorithm, reducing the execution time

Detecting people is a key capability for robots that operate in populated environments. In this paper, we have adopted a hierarchical approach that combines classifiers created using supervised learning in order to identify whether a person is in the view-scope of the robot or not. Our approach makes use of vision, depth and thermal sensors mounted on top of a mobile platform. The set of sensors is set up combining the rich data source offered by a Kinect sensor, which provides vision and depth at low cost, and a thermopile array sensor. Experimental results carried out with a mobile platform in a manufacturing shop floor and in a science museum have shown that the false positive rate achieved using any single cue is drastically reduced. The performance of our algorithm improves other well-known approaches, such as C-4 and histogram of oriented gradients (HOG).

In most cases today when a specific person's whereabouts is monitored through video surveillance it is done manually and his or her location when not seen is based on assumptions on how fast he or she can move. Since humans are good at recognizing people this can be done accurately, given good video data, but the time needed to go through all data is extensive and therefore expensive. Because of the rapid technical development computers are getting cheaper to use and therefore more interesting to use for tedious work. This thesis is a part of a larger project that aims to see to what extent it is possible to estimate a person of interest's time dependent 3D position, when seen in surveillance videos. The surveillance videos are recorded with non overlapping monocular cameras. Furthermore the project aims to see if the person of interest's movement, when position data is unavailable, could be predicted. The outcome of the project is a software capable of following a person of interest's movement with an error estimate visualized as an area indicating where the person of interest might be at a specific time. This thesis main focus is to implement and evaluate a people detector meant to be used in the project, reduce noise in position measurement, predict the position when the person of interest's location is unknown, and to evaluate the complete project. The project combines known methods in computer vision and signal processing and the outcome is a software that can be used on a normal PC running on a Windows operating system. The software implemented in the thesis use a Hough transform based people detector and a Kalman filter for one step ahead prediction. The detector is evaluated with known methods such as Miss-rate vs. False Positives per Window or Image (FPPW and FPPI respectively) and Recall vs. 1-Precision. The results indicate that it is possible to estimate a person of interest's 3D position with single monocular cameras. It is also possible to follow the m

[ES] El objetivo de esta tesina es realizar un estudio de algoritmos y paquetes software existentes en la plataforma ROS (Robot Operating System) para la detección de personas, y comprobar el funcionamiento de alguno de ellos. El estudio se centrará principalmente en algoritmos que se basen en visión artificial y sensores de rango para sistemas de tipo ADAS (Advanced Driving Assistance Systems), en los que la detección de personas se utiliza para evitar accidentes. Se ha probado uno de los detectores existentes (Histrogram of Oriented Gradients o HOG) y se ha combinado con una técnica de detección de objetos verticales, reduciendo el tiempo de ejecución, [EN] In this project a survey of people detection algorithms and software in ROS framework is made. The survey is focused on algorithms using computer vision and range sensors for Advanced Driving Assistance Systems (ADAS), in wich people detection is used to avoid traffic accidents. One of the state-of-the-art methods (Histogram of Oriented Gradients or HOG) has been tested separatedly and with a vertical object detection algorithm, reducing the execution time

[ES] Los sistemas de conteo de personas son extensamente utilizados en aplicaciones de vigilancia. En este artículo se presenta una aplicación para realizar conteo de personas a través de un sistema de estereovisión. Este sistema obtiene tasas de conteo de las personas en movimiento que atraviesan la zona de conteo recogida por el sistema estéreo distinguiendo entrada y salida. Para realizar este conteo se precisan dos fases fundamentales: detección y seguimiento. La detección se basa en la búsqueda de las cabezas de las personas por medio de una correlación de la imagen preprocesada con distintos patrones circulares, filtrando dichas detecciones por estereovisión en función de la altura. El seguimiento se lleva a cabo mediante una algoritmo de múltiples hipótesis basado en filtro de Kalman. Por último, se realiza el conteo según el camino seguido por las trayectorias. Se ha experimentado con un conjunto de vídeos reales tomados en distintas zonas de tránsito en interiores de edificios, alcanzando tasas que oscilan entre un 87% y un 98% de acierto según la cantidad de flujo de personas que atraviesan la zona de conteo de forma simultánea. En los distintos vídeos utilizados como prueba se han reproducido todo tipo de situaciones adversas, como oclusiones, personas en grupo en diferentes sentidos, cambios de iluminación, etc., [EN] The people counting systems are widely used in surveillance applications. This article presents an application for counting people through a stereovision system. This system obtains counting rates of people moving through the counting area, distinguishing between input and output. To achieve this aim is required two basic steps: detection and tracking. The detection step is based on correlation through a pre-processed image with various circular patterns in order to search people's heads, filtering these detections by stereovision depending on the height. The people tracking is carried out through a multiple hypothesis algorithm based on the Kalman filter. Finally, people counting is done according to the trajectory followed by the person. To validate the algorithm have been used several real videos taken from different transit areas inside buildings, reaching rates ranging between 87% and 98% accuracy depending on the number of people crossing the counting zone simultaneously. In these videos occur several adverse situations, such as occlusions, people in groups in different directions, lighting changes, etc.

[ES] Los sistemas de conteo de personas son extensamente utilizados en aplicaciones de vigilancia. En este artículo se presenta una aplicación para realizar conteo de personas a través de un sistema de estereovisión. Este sistema obtiene tasas de conteo de las personas en movimiento que atraviesan la zona de conteo recogida por el sistema estéreo distinguiendo entrada y salida. Para realizar este conteo se precisan dos fases fundamentales: detección y seguimiento. La detección se basa en la búsqueda de las cabezas de las personas por medio de una correlación de la imagen preprocesada con distintos patrones circulares, filtrando dichas detecciones por estereovisión en función de la altura. El seguimiento se lleva a cabo mediante una algoritmo de múltiples hipótesis basado en filtro de Kalman. Por último, se realiza el conteo según el camino seguido por las trayectorias. Se ha experimentado con un conjunto de vídeos reales tomados en distintas zonas de tránsito en interiores de edificios, alcanzando tasas que oscilan entre un 87% y un 98% de acierto según la cantidad de flujo de personas que atraviesan la zona de conteo de forma simultánea. En los distintos vídeos utilizados como prueba se han reproducido todo tipo de situaciones adversas, como oclusiones, personas en grupo en diferentes sentidos, cambios de iluminación, etc., [EN] The people counting systems are widely used in surveillance applications. This article presents an application for counting people through a stereovision system. This system obtains counting rates of people moving through the counting area, distinguishing between input and output. To achieve this aim is required two basic steps: detection and tracking. The detection step is based on correlation through a pre-processed image with various circular patterns in order to search people's heads, filtering these detections by stereovision depending on the height. The people tracking is carried out through a multiple hypothesis algorithm based on the Kalman filter. Finally, people counting is done according to the trajectory followed by the person. To validate the algorithm have been used several real videos taken from different transit areas inside buildings, reaching rates ranging between 87% and 98% accuracy depending on the number of people crossing the counting zone simultaneously. In these videos occur several adverse situations, such as occlusions, people in groups in different directions, lighting changes, etc.

[ES] Los sistemas de conteo de personas son extensamente utilizados en aplicaciones de vigilancia. En este artículo se presenta una aplicación para realizar conteo de personas a través de un sistema de estereovisión. Este sistema obtiene tasas de conteo de las personas en movimiento que atraviesan la zona de conteo recogida por el sistema estéreo distinguiendo entrada y salida. Para realizar este conteo se precisan dos fases fundamentales: detección y seguimiento. La detección se basa en la búsqueda de las cabezas de las personas por medio de una correlación de la imagen preprocesada con distintos patrones circulares, filtrando dichas detecciones por estereovisión en función de la altura. El seguimiento se lleva a cabo mediante una algoritmo de múltiples hipótesis basado en filtro de Kalman. Por último, se realiza el conteo según el camino seguido por las trayectorias. Se ha experimentado con un conjunto de vídeos reales tomados en distintas zonas de tránsito en interiores de edificios, alcanzando tasas que oscilan entre un 87% y un 98% de acierto según la cantidad de flujo de personas que atraviesan la zona de conteo de forma simultánea. En los distintos vídeos utilizados como prueba se han reproducido todo tipo de situaciones adversas, como oclusiones, personas en grupo en diferentes sentidos, cambios de iluminación, etc., [EN] The people counting systems are widely used in surveillance applications. This article presents an application for counting people through a stereovision system. This system obtains counting rates of people moving through the counting area, distinguishing between input and output. To achieve this aim is required two basic steps: detection and tracking. The detection step is based on correlation through a pre-processed image with various circular patterns in order to search people's heads, filtering these detections by stereovision depending on the height. The people tracking is carried out through a multiple hypothesis algorithm based on the Kalman filter. Finally, people counting is done according to the trajectory followed by the person. To validate the algorithm have been used several real videos taken from different transit areas inside buildings, reaching rates ranging between 87% and 98% accuracy depending on the number of people crossing the counting zone simultaneously. In these videos occur several adverse situations, such as occlusions, people in groups in different directions, lighting changes, etc.

[ES] Los sistemas de conteo de personas son extensamente utilizados en aplicaciones de vigilancia. En este artículo se presenta una aplicación para realizar conteo de personas a través de un sistema de estereovisión. Este sistema obtiene tasas de conteo de las personas en movimiento que atraviesan la zona de conteo recogida por el sistema estéreo distinguiendo entrada y salida. Para realizar este conteo se precisan dos fases fundamentales: detección y seguimiento. La detección se basa en la búsqueda de las cabezas de las personas por medio de una correlación de la imagen preprocesada con distintos patrones circulares, filtrando dichas detecciones por estereovisión en función de la altura. El seguimiento se lleva a cabo mediante una algoritmo de múltiples hipótesis basado en filtro de Kalman. Por último, se realiza el conteo según el camino seguido por las trayectorias. Se ha experimentado con un conjunto de vídeos reales tomados en distintas zonas de tránsito en interiores de edificios, alcanzando tasas que oscilan entre un 87% y un 98% de acierto según la cantidad de flujo de personas que atraviesan la zona de conteo de forma simultánea. En los distintos vídeos utilizados como prueba se han reproducido todo tipo de situaciones adversas, como oclusiones, personas en grupo en diferentes sentidos, cambios de iluminación, etc., [EN] The people counting systems are widely used in surveillance applications. This article presents an application for counting people through a stereovision system. This system obtains counting rates of people moving through the counting area, distinguishing between input and output. To achieve this aim is required two basic steps: detection and tracking. The detection step is based on correlation through a pre-processed image with various circular patterns in order to search people's heads, filtering these detections by stereovision depending on the height. The people tracking is carried out through a multiple hypothesis algorithm based on the Kalman filter. Finally, people counting is done according to the trajectory followed by the person. To validate the algorithm have been used several real videos taken from different transit areas inside buildings, reaching rates ranging between 87% and 98% accuracy depending on the number of people crossing the counting zone simultaneously. In these videos occur several adverse situations, such as occlusions, people in groups in different directions, lighting changes, etc.

[ES] Los sistemas de conteo de personas son extensamente utilizados en aplicaciones de vigilancia. En este artículo se presenta una aplicación para realizar conteo de personas a través de un sistema de estereovisión. Este sistema obtiene tasas de conteo de las personas en movimiento que atraviesan la zona de conteo recogida por el sistema estéreo distinguiendo entrada y salida. Para realizar este conteo se precisan dos fases fundamentales: detección y seguimiento. La detección se basa en la búsqueda de las cabezas de las personas por medio de una correlación de la imagen preprocesada con distintos patrones circulares, filtrando dichas detecciones por estereovisión en función de la altura. El seguimiento se lleva a cabo mediante una algoritmo de múltiples hipótesis basado en filtro de Kalman. Por último, se realiza el conteo según el camino seguido por las trayectorias. Se ha experimentado con un conjunto de vídeos reales tomados en distintas zonas de tránsito en interiores de edificios, alcanzando tasas que oscilan entre un 87% y un 98% de acierto según la cantidad de flujo de personas que atraviesan la zona de conteo de forma simultánea. En los distintos vídeos utilizados como prueba se han reproducido todo tipo de situaciones adversas, como oclusiones, personas en grupo en diferentes sentidos, cambios de iluminación, etc., [EN] The people counting systems are widely used in surveillance applications. This article presents an application for counting people through a stereovision system. This system obtains counting rates of people moving through the counting area, distinguishing between input and output. To achieve this aim is required two basic steps: detection and tracking. The detection step is based on correlation through a pre-processed image with various circular patterns in order to search people's heads, filtering these detections by stereovision depending on the height. The people tracking is carried out through a multiple hypothesis algorithm based on the Kalman filter. Finally, people counting is done according to the trajectory followed by the person. To validate the algorithm have been used several real videos taken from different transit areas inside buildings, reaching rates ranging between 87% and 98% accuracy depending on the number of people crossing the counting zone simultaneously. In these videos occur several adverse situations, such as occlusions, people in groups in different directions, lighting changes, etc.

[ES] Los sistemas de conteo de personas son extensamente utilizados en aplicaciones de vigilancia. En este artículo se presenta una aplicación para realizar conteo de personas a través de un sistema de estereovisión. Este sistema obtiene tasas de conteo de las personas en movimiento que atraviesan la zona de conteo recogida por el sistema estéreo distinguiendo entrada y salida. Para realizar este conteo se precisan dos fases fundamentales: detección y seguimiento. La detección se basa en la búsqueda de las cabezas de las personas por medio de una correlación de la imagen preprocesada con distintos patrones circulares, filtrando dichas detecciones por estereovisión en función de la altura. El seguimiento se lleva a cabo mediante una algoritmo de múltiples hipótesis basado en filtro de Kalman. Por último, se realiza el conteo según el camino seguido por las trayectorias. Se ha experimentado con un conjunto de vídeos reales tomados en distintas zonas de tránsito en interiores de edificios, alcanzando tasas que oscilan entre un 87% y un 98% de acierto según la cantidad de flujo de personas que atraviesan la zona de conteo de forma simultánea. En los distintos vídeos utilizados como prueba se han reproducido todo tipo de situaciones adversas, como oclusiones, personas en grupo en diferentes sentidos, cambios de iluminación, etc., [EN] The people counting systems are widely used in surveillance applications. This article presents an application for counting people through a stereovision system. This system obtains counting rates of people moving through the counting area, distinguishing between input and output. To achieve this aim is required two basic steps: detection and tracking. The detection step is based on correlation through a pre-processed image with various circular patterns in order to search people's heads, filtering these detections by stereovision depending on the height. The people tracking is carried out through a multiple hypothesis algorithm based on the Kalman filter. Finally, people counting is done according to the trajectory followed by the person. To validate the algorithm have been used several real videos taken from different transit areas inside buildings, reaching rates ranging between 87% and 98% accuracy depending on the number of people crossing the counting zone simultaneously. In these videos occur several adverse situations, such as occlusions, people in groups in different directions, lighting changes, etc.

Object Tracking has been a very active area in the field of C omputer Vision. Over the years, a variety of approaches have been put forth to solve this problem and though many of them have demonstrate considerable success none of them have been completely successful. With more methods being written each day, the evaluation of such systems becomes a very important task. If an evaluation system exists that is able to point out specific flaws in the stage of development, it can lead to a very robust and improved algorithm. This work attempts to create such an evaluation framework. Given an algorithm that detects people and simultaneously tracks them, we evaluate its output by considering the complexity of the input scene. Some videos used for the evaluation are recorded using the Kinect sensor and a benchmark dataset from the PETS workshop is also used. To analyze the performance of the tracking system,the reasons due to which the algorithm might fail are investigated and quantified over the entire video sequence. A set of features called Scene C omplexity Measures are obtained for each input frame. The variability in the algorithm performance is modeled by these complexity measures using various regression models. From the regression statistics, we show that we can compare the performance of two different algorithms and also quantify the relative influence of the scene complexity measures on a given algorithm., Media and Knowledge Engineering, Computer Science, Electrical Engineering, Mathematics and Computer Science

Object Tracking has been a very active area in the field of C omputer Vision. Over the years, a variety of approaches have been put forth to solve this problem and though many of them have demonstrate considerable success none of them have been completely successful. With more methods being written each day, the evaluation of such systems becomes a very important task. If an evaluation system exists that is able to point out specific flaws in the stage of development, it can lead to a very robust and improved algorithm. This work attempts to create such an evaluation framework. Given an algorithm that detects people and simultaneously tracks them, we evaluate its output by considering the complexity of the input scene. Some videos used for the evaluation are recorded using the Kinect sensor and a benchmark dataset from the PETS workshop is also used. To analyze the performance of the tracking system,the reasons due to which the algorithm might fail are investigated and quantified over the entire video sequence. A set of features called Scene C omplexity Measures are obtained for each input frame. The variability in the algorithm performance is modeled by these complexity measures using various regression models. From the regression statistics, we show that we can compare the performance of two different algorithms and also quantify the relative influence of the scene complexity measures on a given algorithm., Media and Knowledge Engineering, Computer Science, Electrical Engineering, Mathematics and Computer Science

This paper presents a vision-based approach for tracking people on a mobile robot using thermal images. The approach combines a particle filter with two alternative measurement models that are suitable for real-time tracking. With this approach a person can be detected independently from current light conditions and in situations where no skin colour is visible. In addition, the paper presents a comprehensive, quantitative evaluation of the different methods on a mobile robot in an office environment, for both single and multiple persons. The results show that the measurement model that was learned from local greyscale features could improve on the performance of the elliptic contour model, and that both models could be combined to further improve performance with minimal extra computational cost., Selected papers from the 2nd European Conference on Mobile Robots (ECMR ’05)

This thesis presents a general, trainable system for object detection in static images and video sequences. The core system finds a certain class of objects in static images of completely unconstrained, cluttered scenes without using motion, tracking, or handcrafted models and without making any assumptions on the scene structure or the number of objects in the scene. The system uses a set of training data of positive and negative example images as input, transforms the pixel images to a Haar wavelet representation, and uses a support vector machine classifier to learn the difference between in-class and out-of-class patterns. To detect objects in out-of-sample images, we do a brute force search over all the subwindows in the image. This system is applied to face, people, and car detection with excellent results. For our extensions to video sequences, we augment the core static detection system in several ways -- 1) extending the representation to five frames, 2) implementing an approximation to a Kalman filter, and 3) modeling detections in an image as a density and propagating this density through time according to measured features. In addition, we present a real-time version of the system that is currently running in a DaimlerChrysler experimental vehicle. As part of this thesis, we also present a system that, instead of detecting full patterns, uses a component-based approach. We find it to be more robust to occlusions, rotations in depth, and severe lighting conditions for people detection than the full body version. We also experiment with various other representations including pixels and principal components and show results that quantify how the number of features, color, and gray-level affect performance.

This thesis presents a general, trainable system for object detection in static images and video sequences. The core system finds a certain class of objects in static images of completely unconstrained, cluttered scenes without using motion, tracking, or handcrafted models and without making any assumptions on the scene structure or the number of objects in the scene. The system uses a set of training data of positive and negative example images as input, transforms the pixel images to a Haar wavelet representation, and uses a support vector machine classifier to learn the difference between in-class and out-of-class patterns. To detect objects in out-of-sample images, we do a brute force search over all the subwindows in the image. This system is applied to face, people, and car detection with excellent results. For our extensions to video sequences, we augment the core static detection system in several ways -- 1) extending the representation to five frames, 2) implementing an approximation to a Kalman filter, and 3) modeling detections in an image as a density and propagating this density through time according to measured features. In addition, we present a real-time version of the system that is currently running in a DaimlerChrysler experimental vehicle. As part of this thesis, we also present a system that, instead of detecting full patterns, uses a component-based approach. We find it to be more robust to occlusions, rotations in depth, and severe lighting conditions for people detection than the full body version. We also experiment with various other representations including pixels and principal components and show results that quantify how the number of features, color, and gray-level affect performance.

In this paper we present a component based person detection system that is capable of detecting frontal, rear and near side views of people, and partially occluded persons in cluttered scenes. The framework that is described here for people is easily applied to other objects as well. The motivation for developing a component based approach is two fold: first, to enhance the performance of person detection systems on frontal and rear views of people and second, to develop a framework that directly addresses the problem of detecting people who are partially occluded or whose body parts blend in with the background. The data classification is handled by several support vector machine classifiers arranged in two layers. This architecture is known as Adaptive Combination of Classifiers (ACC). The system performs very well and is capable of detecting people even when all components of a person are not found. The performance of the system is significantly better than a full body person detector designed along similar lines. This suggests that the improved performance is due to the components based approach and the ACC data classification structure.

In this paper we present a component based person detection system that is capable of detecting frontal, rear and near side views of people, and partially occluded persons in cluttered scenes. The framework that is described here for people is easily applied to other objects as well. The motivation for developing a component based approach is two fold: first, to enhance the performance of person detection systems on frontal and rear views of people and second, to develop a framework that directly addresses the problem of detecting people who are partially occluded or whose body parts blend in with the background. The data classification is handled by several support vector machine classifiers arranged in two layers. This architecture is known as Adaptive Combination of Classifiers (ACC). The system performs very well and is capable of detecting people even when all components of a person are not found. The performance of the system is significantly better than a full body person detector designed along similar lines. This suggests that the improved performance is due to the components based approach and the ACC data classification structure.

This thesis presents a general, trainable system for object detection in static images and video sequences. The core system finds a certain class of objects in static images of completely unconstrained, cluttered scenes without using motion, tracking, or handcrafted models and without making any assumptions on the scene structure or the number of objects in the scene. The system uses a set of training data of positive and negative example images as input, transforms the pixel images to a Haar wavelet representation, and uses a support vector machine classifier to learn the difference between in-class and out-of-class patterns. To detect objects in out-of-sample images, we do a brute force search over all the subwindows in the image. This system is applied to face, people, and car detection with excellent results. For our extensions to video sequences, we augment the core static detection system in several ways -- 1) extending the representation to five frames, 2) implementing an approximation to a Kalman filter, and 3) modeling detections in an image as a density and propagating this density through time according to measured features. In addition, we present a real-time version of the system that is currently running in a DaimlerChrysler experimental vehicle. As part of this thesis, we also present a system that, instead of detecting full patterns, uses a component-based approach. We find it to be more robust to occlusions, rotations in depth, and severe lighting conditions for people detection than the full body version. We also experiment with various other representations including pixels and principal components and show results that quantify how the number of features, color, and gray-level affect performance.

In this paper we present a component based person detection system that is capable of detecting frontal, rear and near side views of people, and partially occluded persons in cluttered scenes. The framework that is described here for people is easily applied to other objects as well. The motivation for developing a component based approach is two fold: first, to enhance the performance of person detection systems on frontal and rear views of people and second, to develop a framework that directly addresses the problem of detecting people who are partially occluded or whose body parts blend in with the background. The data classification is handled by several support vector machine classifiers arranged in two layers. This architecture is known as Adaptive Combination of Classifiers (ACC). The system performs very well and is capable of detecting people even when all components of a person are not found. The performance of the system is significantly better than a full body person detector designed along similar lines. This suggests that the improved performance is due to the components based approach and the ACC data classification structure.

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., This thesis aims to research the applicability of deep learning methods on point clouds generated by millimeter-wave radars, as a solution for people detection, and 3D scene understanding in general. Radar is a system that uses radio waves to determine the distance, azimuth, and velocity of surrounding objects. For each point of detection, Cartesian coordinates can be calculated, to produce a set of points in 3D space called a point cloud. Deep neural network architectures designed to operate on sparse 3D point clouds can be trained for point-wise segmentation, object detection, classification, and tracking. This can be used to greatly advance the 3D scene understanding by machines. A model based on the state-of-the-art methods for object detection and classification on sparse point clouds was trained as a part of this thesis, for the purpose of people detection. To showcase the robustness of the trained model and the straightforwardness of its applicability to solve prominent real-world tasks of scene understanding, a people counting application was developed. The employed methods were thoroughly evaluated on a dataset created as a part of this thesis, consisting of over 19,500 labels on 3D radar point clouds.

Tato práce se zaměřuje na problematiku sledování chodců kamerou. Představil jsem používané metody počítačového vidění, které jsou vhodné pro detekci a klasifikaci osob. Na základě detekce pohybu osob ve videozáznamu jsem navrhl algoritmus pro detekci a sledování chodců. Výsledná aplikace používá histogram orientovaných gradientů a SVM klasifikátor, pro identifikaci chodců jsou využity barevné histogramy. Zjištěné trajektorie jsou následně vykreslovány na výstup. V poslední části práce se zabývám testováním a vyhodnocením výsledků navrženého algoritmu., 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.

Tato bakalářská práce se zabývá detekcí postavy ve videu pomocí Kinectu. Detektor lidských postav je založený na metodě ComboHod, která využívá barevné i hloubkové informace z obrazu. Cílem práce bylo vytvořit detektor postav, jehož funkci ukáži na statistické aplikaci. Aplikace shromažďuje statistické informace o lidech, kteří prošli kolem výlohy obchodu. Závěrem práce jsou popsány experimenty s detektorem v různých prostředích a podmínkách., This bachelor's thesis deals with the person detection using RGB-D Microsoft Kinect sensor. Human body detector is based on the method Combohod which uses both color and depth information from Kinect sensor. The aim of the thesis was to create a person detector whose functionality is demonstrated by proposing a statistical application that collects statistical information about the people who passed the shop window. At the end of the thesis the experiments with the detector under varios different conditions are described.

Tato bakalářská práce se zabývá detekcí osob a sledováním trajektorií pohybu v zájmových zónách. Jsou rozebrány jednotlivé metody, pomocí nichž lze detekce osob dosáhnout. Pro implementaci funkce detekce osob a detekce trajektorie pohybu je vybrán mikrovlnný radarový snímač IWR6843AoPEVM od společnosti Texas Instruments. Je popsán využitý hardware a software. Následně je provedena simulace funkce sledováním trajektorie osob ve frontě a zhodnoceny výsledky. Jsou srovnány výhody a nevýhody jednotlivých metod pro detekci osob. Nakonec je shrnut výběr možných implementací tohoto zařízení a vybrána cílová platforma, na které je ověřena funkce., This bachelor ‘s thesis deals with a topic of people detection and tracking their movement in regions of interest. The individual methods that can achieve people detection are analyzed. To implement people detection and tracking their movement microwave radar sensor IWR6843AoPEVM from Texas Instruments is chosen for this task. This hardware and its software are described in detail. Then simulation is conducted to track people in a queue and its results are evaluated. Different advantages and disadvantages of individual methods are compared with each other. Finally, there’s a summary of possible implementations for this device and target platform is chosen to verify its functionality.

Tato bakalářská práce se zabývá detekcí osob a sledováním trajektorií pohybu v zájmových zónách. Jsou rozebrány jednotlivé metody, pomocí nichž lze detekce osob dosáhnout. Pro implementaci funkce detekce osob a detekce trajektorie pohybu je vybrán mikrovlnný radarový snímač IWR6843AoPEVM od společnosti Texas Instruments. Je popsán využitý hardware a software. Následně je provedena simulace funkce sledováním trajektorie osob ve frontě a zhodnoceny výsledky. Jsou srovnány výhody a nevýhody jednotlivých metod pro detekci osob. Nakonec je shrnut výběr možných implementací tohoto zařízení a vybrána cílová platforma, na které je ověřena funkce., This bachelor ‘s thesis deals with a topic of people detection and tracking their movement in regions of interest. The individual methods that can achieve people detection are analyzed. To implement people detection and tracking their movement microwave radar sensor IWR6843AoPEVM from Texas Instruments is chosen for this task. This hardware and its software are described in detail. Then simulation is conducted to track people in a queue and its results are evaluated. Different advantages and disadvantages of individual methods are compared with each other. Finally, there’s a summary of possible implementations for this device and target platform is chosen to verify its functionality.

Cílem této práce je získat informace o pohybu osob ve scéně ze záznamu ze stacionární kamery. Byl navržen postup, jak detekovat výjimečné události ve scéně. Výjimečné události mohou být rychle se pohybující osoby nebo osoby pohybující se jinde, než všichni ostatní ve scéně. Pro sledování pohybu osob byly použity a testovány dva algoritmy - Optical flow a CAMSHIFT. Analýza výsledných pohybů je prováděna sledováním průběhu pohybu a jeho porovnáním s ostatními pohyby ve scéně. Výsledkem analýzy jsou detekované výjimečné pohyby ve videu. Rovněž jsou označený oblasti, kde se ve scéně vyskytuje pohyb, oblasti kde je pohyb nejčastější a je provedena analýza směrů pohybů. Hlavním výsledkem jsou extrahované části videa, kde nastal výjimečný pohyb., The aim of this diploma thesis is to obtain information on the motion of people in a scene from the record of the stationary camera. The procedure to detect exceptional events in the scene was designed. Exceptional events can be fast-moving persons, or persons moving in di erent places than everyone else in the scene. To trace the motion of persons, two algorithms were applied and tested - Optical flow and CAMSHIFT. The analysis of the resulting motions is performed by monitoring the progress of motion, and its comparison with the other motions in the scene. The analysis result is represented by detected exceptional motions that can be found in the video. The areas where the motion occurs in the scene, and where the motion is the most common are also described together with the motion direction analysis. The exceptional motion parts extracted from the video represent the main result of the work.

Cílem této práce je získat informace o pohybu osob ve scéně ze záznamu ze stacionární kamery. Byl navržen postup, jak detekovat výjimečné události ve scéně. Výjimečné události mohou být rychle se pohybující osoby nebo osoby pohybující se jinde, než všichni ostatní ve scéně. Pro sledování pohybu osob byly použity a testovány dva algoritmy - Optical flow a CAMSHIFT. Analýza výsledných pohybů je prováděna sledováním průběhu pohybu a jeho porovnáním s ostatními pohyby ve scéně. Výsledkem analýzy jsou detekované výjimečné pohyby ve videu. Rovněž jsou označený oblasti, kde se ve scéně vyskytuje pohyb, oblasti kde je pohyb nejčastější a je provedena analýza směrů pohybů. Hlavním výsledkem jsou extrahované části videa, kde nastal výjimečný pohyb., The aim of this diploma thesis is to obtain information on the motion of people in a scene from the record of the stationary camera. The procedure to detect exceptional events in the scene was designed. Exceptional events can be fast-moving persons, or persons moving in di erent places than everyone else in the scene. To trace the motion of persons, two algorithms were applied and tested - Optical flow and CAMSHIFT. The analysis of the resulting motions is performed by monitoring the progress of motion, and its comparison with the other motions in the scene. The analysis result is represented by detected exceptional motions that can be found in the video. The areas where the motion occurs in the scene, and where the motion is the most common are also described together with the motion direction analysis. The exceptional motion parts extracted from the video represent the main result of the work.

Tato bakalářská práce se zabývá detekcí postavy ve videu pomocí Kinectu. Detektor lidských postav je založený na metodě ComboHod, která využívá barevné i hloubkové informace z obrazu. Cílem práce bylo vytvořit detektor postav, jehož funkci ukáži na statistické aplikaci. Aplikace shromažďuje statistické informace o lidech, kteří prošli kolem výlohy obchodu. Závěrem práce jsou popsány experimenty s detektorem v různých prostředích a podmínkách., This bachelor's thesis deals with the person detection using RGB-D Microsoft Kinect sensor. Human body detector is based on the method Combohod which uses both color and depth information from Kinect sensor. The aim of the thesis was to create a person detector whose functionality is demonstrated by proposing a statistical application that collects statistical information about the people who passed the shop window. At the end of the thesis the experiments with the detector under varios different conditions are described.

Tato práce se zaměřuje na problematiku sledování chodců kamerou. Představil jsem používané metody počítačového vidění, které jsou vhodné pro detekci a klasifikaci osob. Na základě detekce pohybu osob ve videozáznamu jsem navrhl algoritmus pro detekci a sledování chodců. Výsledná aplikace používá histogram orientovaných gradientů a SVM klasifikátor, pro identifikaci chodců jsou využity barevné histogramy. Zjištěné trajektorie jsou následně vykreslovány na výstup. V poslední části práce se zabývám testováním a vyhodnocením výsledků navrženého algoritmu., 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.

Táto práca sa zameriava na tému počítačového videnia, presnejšie, na binárnu klasifikáciu prítomnosti ľudí v obrazových dátach. Cieľom tejto práce je vytvoriť redukovanú neurónovú sieť s využitím metódy knowledge distillation. Klasifikácia a detekcia objektov je výpočtovo náročná operácia. Študentský model vytvorený pomocou knowledge distillation vykazuje ekvivalentnú presnosť, pričom je menší a má vyššiu inferenčnú rýchlosť v porovnaní s učiteľským modelom. Takýto model môže byť interdisciplinárne všestranný a to predovšetkým na koncových zariadeniach, ktoré majú relatívne slabé výpočtové schopnosti., This thesis focuses on the topic of computer vision, more specifically, on classifying people's presence in image data. The goal is to create a reduced neural network utilizing knowledge distillation. Object classification and detection is a computationally an expensive operation. A student model created utilizing knowledge distillation shows equivalent accuracy while being smaller and having better inferencing speed compared to the teacher model. Such model can be interdisciplinarily utilized on end devices having relatively low computational capabilities.