Real-time high density people counter using morphological tools

Albiol, Antonio; Naranjo, Valery; Mora, I.

doi:10.1109/icpr.2000.903002

Cited by 22 publications

(12 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Since the cameras are fixed, the object segmentation and the single-view tracking can be exploited using the background suppression: differently from the perimeter layer, the vision in this layer is indoor therefore simpler statistical approaches like [15] could be equally effective but more efficient; to deal with object occlusions within the same view, some appearance models (based on color, texture, contour, etc) can be exploited [17,23]. Vision-based people counting at gates has been widely explored in the literature [29,2,6], but, apart from ad-hoc approaches, it could be interpreted also as the outcome of a correct people tracker (see [31] for a survey) which observes all the entrance/exit gates of an environment, that is our case. To increase the accuracy of the counting, additional sensors could be deployed, as will be detailed in our case study in section 3.…”

Section: Figure 2: Scheme Of the Perimeter Vision Layermentioning

confidence: 99%

Enabling technologies on hybrid camera networks for behavioral analysis of unattended indoor environments and their surroundings

Gualdi

Prati

Cucchiara

et al. 2008

Proceedings of the 1st ACM Workshop on Vision Networks for Behavior Analysis

View full text Add to dashboard Cite

This paper presents a layered network architecture and the enabling technologies for accomplishing vision-based behavioral analysis of unattended environments. Specifically the vision network covers both the attended environment and its surroundings by means of hybrid cameras. The layer overlooking at the surroundings is laid outdoor and tracks people, monitoring entrance/exit points. It recovers the geometry of the site under surveillance and communicates people positions to a higher level layer. The layer monitoring the unattended environment undertakes similar goals, with the addition of maintaining a global mosaic of the observed scene for further understanding. Moreover, it merges information coming from sensors beyond the vision to deepen the understanding or increase the reliability of the system. The behavioral analysis is demanded to a third layer that merges the information received from the two other layers and infers knowledge about what happened, happens and will be likely happening in the environment. The paper also describes a case study that was implemented in the Engineering Campus of the University of Modena and Reggio Emilia, where our surveillance system has been deployed in a computer laboratory which was often unaccessible due to lack of attendance.

show abstract

Section: Figure 2: Scheme Of the Perimeter Vision Layermentioning

confidence: 99%

Enabling technologies on hybrid camera networks for behavioral analysis of unattended indoor environments and their surroundings

Gualdi

Prati

Cucchiara

et al. 2008

Proceedings of the 1st ACM Workshop on Vision Networks for Behavior Analysis

View full text Add to dashboard Cite

show abstract

“…[1] z Optical flow [2] According the different position of pixels, to extract the moving object. Its calculation is complexity, but its accuracy is higher.…”

Section: Relative Researchesmentioning

confidence: 99%

“…z Accompanying the development of computer and image processing technique, satisfy these method's demands of real time, reliability and security. In many applications, a camera mounted vertically at the top of the door, and capture the moving object which passing this specific area [1] [10].…”

Section: Introductionsmentioning

confidence: 99%

Real-Time Counting Method for a Crowd of Moving People

Chen

Wang

et al. 2010

2010 Sixth International Conference on Intelligent Information Hiding and Multimedia Signal Processing

View full text Add to dashboard Cite

Currently, the video processing is broadly adopted to deal with the moving crowd counting issue in many literatures, and an acceptable accuracy was obtained under the situation that the crowd is loose, on the contrary, the accuracy will decrease. The method with higher accuracy, even under crowded situation, was proposed. We film the crowd people while them entering or leaving, a camera was mounted vertically above them. Then, the proposed algorithm of motion object detection and segmentation is applied to the film. It applied the frame difference algorithm based on the morphological processing to solve the light changing problem. According to the rate of height and width, we can solve the crowd overlap problem, and the accuracy of our algorithm increases.

show abstract

“…The main problem of tracking in crowds is a permanent strong occlusion of pedestrians. To avoid them, one could use top-view camera positions, like in [7] or [8]. However, this approach has severe restrictions: camera installation is often not possible in real-world situations due to architectural constraints, the observing area is quite small, and the perspective is unusual and non-informative for a human.…”

Section: Introductionmentioning

confidence: 98%

Robust pedestrian detection and tracking in crowded scenes

Lypetskyy¹

2007

SPIE Proceedings

View full text Add to dashboard Cite

This paper presents a vision based tracking system developed for very crowded situations like underground or railway stations. Our system consists on two main parts -searching of people candidates in single frames, and tracking them frame to frame over the scene. This paper concentrates mostly on the tracking part and describes its core components in detail. These are trajectories predictions using KLT vectors or Kalman filter, adaptive active shape model adjusting and texture matching. We show that combination of presented algorithms leads to robust people tracking even in complex scenes with permanent occlusions.

show abstract

Real-time high density people counter using morphological tools

Cited by 22 publications

References 5 publications

Enabling technologies on hybrid camera networks for behavioral analysis of unattended indoor environments and their surroundings

Enabling technologies on hybrid camera networks for behavioral analysis of unattended indoor environments and their surroundings

Real-Time Counting Method for a Crowd of Moving People

Robust pedestrian detection and tracking in crowded scenes

Contact Info

Product

Resources

About