Classification of smart video surveillance systems for commercial applications

Sedky, Mohamed; Moniri, M.; Chibelushi, Claude C.

doi:10.1109/avss.2005.1577343

Cited by 33 publications

(22 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1). All the points are represented in homogenous coordinate form, and the ground coordinate system is defined by the x w -axis and the y w -axis in the world coordinate system.…”

Section: Domain Transformationmentioning

confidence: 99%

“…Region localization is defined, in a generic model of smart visual surveillance systems [1], as the transformation of the two-dimensional (2D) image coordinates of a detected region into the corresponding 3D world coordinates, which is considered one of the essential processes needed to meet the requirements for commercial application of smart visual surveillance systems. Usually, a specific point in the region (e.g., the center, the lowest point, or the bottom center of a bounding rectangle) is used to determine 3D location of the region.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of a 3D Bounding Box for a Segmented Object Region in a Single Image

Jung

Kim

2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper proposes a novel method for determining a three-dimensional (3D) bounding box to estimate pose (position and orientation) and size of a 3D object corresponding to a segmented object region in an image acquired by a single calibrated camera. The method is designed to work upon an object on the ground and to determine a bounding box aligned to the direction of the object, thereby reducing the number of degrees of freedom in localizing the bounding box to 5 from 9. Observations associated with the structural properties of back-projected object regions on the ground are suggested, which are useful for determining the object points expected to be on the ground. A suitable base is then estimated from the expected on-ground object points by applying to them an assumption of bilateral symmetry. A bounding box with this base is finally constructed by determining its height, such that back-projection of the constructed box onto the ground minimally encloses back-projection of the given object region. Through experiments with some 3D-modelled objects and real objects, we found that a bounding box aligned to the dominant direction estimated from edges with common direction looks natural, and the accuracy of the pose and size is enough for localizing actual on-ground objects in an industrial working space. The proposed method is expected to be used effectively in the fields of smart surveillance and autonomous navigation. key words: 3D bounding box estimation, object localization, dominant direction of object, back-projection of image region, smart surveillance

show abstract

“…(1). All the points are represented in homogenous coordinate form, and the ground coordinate system is defined by the x w -axis and the y w -axis in the world coordinate system.…”

Section: Domain Transformationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Estimation of a 3D Bounding Box for a Segmented Object Region in a Single Image

Jung

Kim

2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Developments of such techniques have become important in the past three decades. This is due to the fact that change detection is a key computer vision component which contributes to a wide spectrum of applications in diverse disciplines [1].…”

Section: Introductionmentioning

confidence: 99%

Spectral-360: A Physics-Based Technique for Change Detection

Sedky

Moniri

Chibelushi

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops

View full text Add to dashboard Cite

Abstract-This paper presents and assesses a novel physicsbased change detection technique, Spectral-360, which is based on the dichromatic color reflectance model. This approach, uses image formation models to computationally estimate, from the camera output, a consistent physics-based color descriptor of the spectral reflectance of surfaces visible in the image, and then to measure the similarity between the fullspectrum reflectance of the background and foreground pixels to segment the foreground from a static background. This method represents a new approach to change detection, using explicit hypotheses about the physics that create images. The assumptions which have been made are that diffuse-onlyreflection is applicable, and the existence of a dominant illuminant. The objective evaluation performed using the 'changedetection.net 2014' dataset shows that our Spectral-360 method outperforms most state-of-the-art methods.

show abstract

“…Studies are at the initial stage to deploy this system to the ubiquitous computing environment [13,15,23]. Some studies have investigated delivery of video streaming from a selected camera that is physically close to the target person using positional information of the target [5,18].…”

Section: Introductionmentioning

confidence: 99%

Ubiquitous Supervisory System Based on Social Contexts Using Ontology

Izumi

Yamanaka

Tokairin

et al. 2009

Mobile Information Systems

View full text Add to dashboard Cite

Abstract. As described in this paper, we propose a supervisory system that considers actual situations and social aspects of users in a ubiquitous computing environment. To realize gentle and safe supervision while providing efficient supervisory services, the system must recognize the situations of a watched person, such as the person's physical condition. To achieve this, we have proposed a ubiquitous supervisory system "uEyes", which introduces Social Context Awareness: a distinguishing feature for supervision. Using this feature, the system can combine environmental information acquired from sensors in the real world and common-sense knowledge related to human activities in daily life. As described in this paper, we specifically examine design of Social Context Awareness using ontology technologies. Based on this advanced feature, a live video streaming system is configured autonomously depending on the users' circumstances in runtime. We implemented a uEyes prototype for supervising elderly people and performed some experiments based on several scenarios. Based on those experimental results, we confirmed that the social contexts are handled effectively to support the supervision.

show abstract

Classification of smart video surveillance systems for commercial applications

Cited by 33 publications

References 16 publications

Estimation of a 3D Bounding Box for a Segmented Object Region in a Single Image

Estimation of a 3D Bounding Box for a Segmented Object Region in a Single Image

Spectral-360: A Physics-Based Technique for Change Detection

Ubiquitous Supervisory System Based on Social Contexts Using Ontology

Contact Info

Product

Resources

About