Background subtraction in people detection framework for RGB-D cameras

Nghiem, Anh-Tuan; Brémond, François

doi:10.1109/avss.2014.6918675

Cited by 16 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…People detection is performed using the depth-based framework of [28] that extends the standard detection range of color-depth sensors from 3-4 meters (Microsoft and Prime-Sense) to 7-9 meters away. It works as follows: first, it performs background subtraction in the depth image to identify foreground regions that contains both moving objects and potential noise.…”

Section: People Detectionmentioning

confidence: 99%

Semantic Event Fusion of Different Visual Modality Concepts for Activity Recognition

Crispim-Junior

Buso

Avgerinakis

et al. 2016

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

Combining multimodal concept streams from heterogeneous sensors is a problem superficially explored for activity recognition. Most studies explore simple sensors in nearly perfect conditions, where temporal synchronization is guaranteed. Sophisticated fusion schemes adopt problem-specific graphical representations of events that are generally deeply linked with their training data and focused on a single sensor. This paper proposes a hybrid framework between knowledge-driven and probabilistic-driven methods for event representation and recognition. It separates semantic modeling from raw sensor data by using an intermediate semantic representation, namely concepts. It introduces an algorithm for sensor alignment that uses concept similarity as a surrogate for the inaccurate temporal information of real life scenarios. Finally, it proposes the combined use of an ontology language, to overcome the rigidity of previous approaches at model definition, and a probabilistic interpretation for ontological models, which equips the framework with a mechanism to handle noisy and ambiguous concept observations, an ability that most knowledge-driven methods lack. We evaluate our contributions in multimodal recordings of elderly people carrying out IADLs. Results demonstrated that the proposed framework outperforms baseline methods both in event recognition performance and in delimiting the temporal boundaries of event instances.

show abstract

Section: People Detectionmentioning

confidence: 99%

Semantic Event Fusion of Different Visual Modality Concepts for Activity Recognition

Crispim-Junior

Buso

Avgerinakis

et al. 2016

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Otra de las diferencias de la suspensión Rocker bogie original es que los ejes que soportan el eslabón principal no se encuentran conectados mediante una relación diferencial sino que cada uno dispone de un servomotor que controla su movimiento independientemente [5,6,9]. El sistema de transmisión del servomotor al eje se realiza mediante engranajes como se puede ver en la Fig.…”

Section: Fig 2 Vistas Del Modelo 3dunclassified

Diseño de un robot rescatista para terremotos en México

Cedillo¹,

Sánchez²,

Sandoval³

et al. 2019

RCS

View full text Add to dashboard Cite

Resumen. La República Mexicana está situada en una de las regiones sísmicamente más activas del mundo, enclavada dentro del área conocida como el Cinturón Circumpacífico donde se concentra la mayor actividad sísmica del planeta. En los últimos 5 años se han producido terremotos de magnitud muy considerable afectando estados como Oaxaca, Puebla, Morelos, Guerrero, Michoacán y la Ciudad de México. El número de personas que murieron atrapadas dentro de los escombros fue muy alta y en los próximos años se seguirá teniendo actividad sísmica constante. La necesidad de desarrollar un robot que permita detectar personas atrapadas no como un prototipo si no como una herramienta profesional de rescate es una prioridad. En este trabajo se propone el desarrollo de un robot rescatista diseñado con diversos sensores para detectar la temperatura, ruidos, detectar respiración de personas en los escombros. El robot propuesto se moverá entre los desechos para detectar a los humano.Palabras clave: robótica, aplicaciones de robótica, algoritmos de navegación, robot rescatista.Abstract. The Mexican Republic is located in one of the most seismically active regions in the world, nestled within the area known as the Circumpacific Belt where the largest seismic activity on the planet is concentrated. In the last 5 years, there have been earthquakes of very considerable magnitude affecting states such as Oaxaca, Puebla, Morelos, Guerrero, Michoacán and Mexico City. The number of people who died trapped inside the rubble was very high and in the coming years, there will continue to be constant seismic activity. The need to develop a robot that allows detecting people trapped not as a prototype but as a professional rescue tool is a priority. This work proposes the development of a rescue robot designed with various sensors to detect temperature, noise, detect breathing of people in the rubble. The proposed robot will move through the waste to detect humans.

show abstract

“…Background subtraction has been shown to be an effective approach for segmenting objects in depth images [25]. It can also be used in a more general application setup of the proposed system when integrated with the wearable head-gear configuration of Figure 1 for segmenting people as they move in front of the depth sensor [26]. The grayscale images obtained from the depth sensor are encoded to represent distances between objects and the camera plane (Figure 19((a) and (b))).…”

Section: Locating Thementioning

confidence: 99%

Multimodal Sensing Interface for Haptic Interaction

Díaz

Payandeh

2017

Journal of Sensors

View full text Add to dashboard Cite

This paper investigates the integration of a multimodal sensing system for exploring limits of vibrato tactile haptic feedback when interacting with 3D representation of real objects. In this study, the spatial locations of the objects are mapped to the work volume of the user using a Kinect sensor. The position of the user’s hand is obtained using the marker-based visual processing. The depth information is used to build a vibrotactile map on a haptic glove enhanced with vibration motors. The users can perceive the location and dimension of remote objects by moving their hand inside a scanning region. A marker detection camera provides the location and orientation of the user’s hand (glove) to map the corresponding tactile message. A preliminary study was conducted to explore how different users can perceive such haptic experiences. Factors such as total number of objects detected, object separation resolution, and dimension-based and shape-based discrimination were evaluated. The preliminary results showed that the localization and counting of objects can be attained with a high degree of success. The users were able to classify groups of objects of different dimensions based on the perceived haptic feedback.

show abstract

Background subtraction in people detection framework for RGB-D cameras

Cited by 16 publications

References 10 publications

Semantic Event Fusion of Different Visual Modality Concepts for Activity Recognition

Semantic Event Fusion of Different Visual Modality Concepts for Activity Recognition

Diseño de un robot rescatista para terremotos en México

Multimodal Sensing Interface for Haptic Interaction

Contact Info

Product

Resources

About