Counting of People in the Extremely Dense Crowd using Genetic Algorithm and Blobs Counting
نویسندگان
چکیده
Received Nov 13, 2012 Revised Accepted In this paper, we have proposed a framework to count the moving person in the video automatically in a very dense crowd situation. Median filter is used to segment the foreground from the background and blob analysis is done to count the people in the current frame. Optimization of different parameters is done by using genetic algorithm. This framework is used to count the people in the video recorded in the mattaf area where different crowd densities can be observed. An overall people counting accuracy of more than 96% is obtained. Keyword:
منابع مشابه
Counting of People in the Extremely Dense Crowd
Received Nov 13,2012 Revised Jan 05, 2013 Accepted Jan 12,2013 In this paper, we have proposed a framework to count the moving person in the video automatically in a very dense crowd situation. Median filter is used to segment the foreground from the background and blob analysis is done to count the people in the current frame. Optimization of different parameters is done by using genetic algor...
متن کاملBackground Modeling and Subtraction Based People Counting for Real Time Video Surveillance
This paper presents a multiple people counting using only single camera, entering or exiting in a region of interest. Sigma-Delta background modeling and subtraction is used to segment the people from region. Background subtraction provides blobs as a result with connected component. CG of blobs was used to track and count the entry and exit of people. This paper also proposed method for counti...
متن کاملCounting in High Density Crowd Videos
We propose a method for getting an estimate count of people in very high-dense crowd videos by extending a static crowd count method. Due to the challenging problem of perspective, occlusion, clutter, and low resolution counting by detection is not possible. Therefore, existing methods use dense features to get an estimate count. We propose using the extra information of motion in videos to con...
متن کاملCrowd Counting via Weighted VLAD on Dense Attribute Feature Maps
Crowd counting is an important task in computer vision, which has many applications in video surveillance. Although the regression-based framework has achieved great improvements for crowd counting, how to improve the discriminative power of image representation is still an open problem. Conventional holistic features used in crowd counting often fail to capture semantic attributes and spatial ...
متن کاملScene Invariant Crowd Segmentation and Counting Using Scale-Normalized Histogram of Moving Gradients (HoMG)
The problem of automated crowd segmentation and counting has garnered significant interest in the field of video surveillance. This paper proposes a novel scene invariant crowd segmentation and counting algorithm designed with high accuracy yet low computational complexity in mind, which is key for widespread industrial adoption. A novel low-complexity, scale-normalized feature called Histogram...
متن کامل