Real-time high density people counter using morphological tools

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

doi:10.1109/6979.969366

Cited by 52 publications

(13 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In comparison to the 90 • condition, the accuracy rates are from 99 to 98.4 % in [2] and from 100 to 90.4 in [21]. In the 90 • category of Table 4a, our LOI result is between 97.66 and 93.33 % under four different scenes, which are very competitive to [2,21]. However, our algorithm is an off-line learning method and can be used without retraining in new scenes.…”

Section: Loi Countingmentioning

confidence: 86%

“…The speed is 25 FPS (frames per second) for LOI counting and 17 FPS for ROI counting, which is faster than most stateof-the-art methods [2,19,21].…”

Section: Roi Countingmentioning

confidence: 97%

“…Feature regression and pedestrian detection are only applied to ROI detection. For LOI counting, most methods adopt feature tracking by clustered trajectories into object track [2,6,11,21,41,54], which are not robust and also time consuming under crowded environments.…”

Section: Application I: Crowd Counting Without Scene-specific Learningmentioning

confidence: 99%

See 2 more Smart Citations

Real-time one-dimensional motion estimation and its application in computer vision

Yang

Gong

Tang

et al. 2015

Machine Vision and Applications

View full text Add to dashboard Cite

Traditional optical flow methods are designed to generate two-dimensional (2D) motion fields. However in some applications, only the motion field along a predefined line is needed, while the rest of the redundant 2D region (Cong et al., CVPR, 2009) can be ignored. In this paper, we propose a general framework for estimating one-dimensional (1D) motion field using the L 1 norm metric, which can be flexible for adding any constraints depending on the specific intention. Compared with 2D methods in model calculation, which often obtain a local optimal solution, our 1D version has the advantage of real-time global optimization and sub-pixel accuracy with a large displacement capacity. The synthesized experiments have justified the effectiveness of our 1D model. Two vision applications are investigated: (i) for crowd counting, we design a novel unified framework for both line of interest and region of interest counting using our 1D motion model to mosaic the dynamic blobs. Such a framework can adapt to new site without scene-specific learning and overcome overfitting. (ii) For visual odometry, we apply our 1D model to estimate the linear velocity of the robot in real time and obtain a comparable result with the benchmark Encoder. Experiments verified that our proposed model can produce satisfactory results in real time.

show abstract

Section: Loi Countingmentioning

confidence: 86%

“…The speed is 25 FPS (frames per second) for LOI counting and 17 FPS for ROI counting, which is faster than most stateof-the-art methods [2,19,21].…”

Section: Roi Countingmentioning

confidence: 97%

See 1 more Smart Citation

Real-time one-dimensional motion estimation and its application in computer vision

Yang

Gong

Tang

et al. 2015

Machine Vision and Applications

View full text Add to dashboard Cite

show abstract

“…Therefore, the vertical dimension of the maps corresponds to depth (longitudinal dimension of the lane) and the horizontal to time. In [25], we also proposed the idea of spatio- temporal maps for counting people. However, the information embedded on those maps was completely different.…”

Section: B Raw Map Formationmentioning

confidence: 99%

Detection of Parked Vehicles Using Spatiotemporal Maps

Albiol

Sanchis

Albiol

et al. 2011

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

This paper presents a video-based approach to detect the presence of parked vehicles in street lanes.Potential applications include detection of illegally and double-parked vehicles in urban scenarios and incident detection on roads. The technique extracts information from low-level feature points (Harris corners) in order to create spatio-temporal maps that describe what is happening in the scene.The method does not rely on any background subtraction or perform any form of object tracking.The system has been evaluated using private and public data sets and has proven to be robust against common difficulties found in CCTV video such as varying illumination, camera vibration, presence of momentary occlusion by other vehicles, and high noise levels.

show abstract

“…Albiol et al [1] describe a technique based on the analysis of the derivate image constructed from a time sampled section of original image. Another method [2] uses statistical analysis of object corners detected while people move.…”

mentioning

confidence: 99%

A method for counting people attending large public events

Kopaczewski

Szczodrak

Czyżewski

et al. 2013

Multimed Tools Appl

View full text Add to dashboard Cite

The algorithm for people counting in crowded scenes, based on the idea of virtual gate which uses optical flow method is presented. The concept and practical application of the developed algorithm under real conditions is depicted. The aim of the work is to estimate the number of people passing through entrances of a large sport hall. The most challenging problem was the unpredicted behavior of people while entering the building. The examined flow of people fluctuated between individual persons and dense crowd. A series of experiments during sport and entertainment events was made. The results of the experiments show a high efficiency of the elaborated algorithm.

show abstract

Real-time high density people counter using morphological tools

Cited by 52 publications

References 5 publications

Real-time one-dimensional motion estimation and its application in computer vision

Real-time one-dimensional motion estimation and its application in computer vision

Detection of Parked Vehicles Using Spatiotemporal Maps

A method for counting people attending large public events

Contact Info

Product

Resources

About