Counting Crowded Moving Objects

By Vincent Rabaud, Serge J. Belongie. Computer Vision and Pattern Recognition, 2006

463 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/568c9f604f0ed4e1549ed58102c59874d56bc30e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Understanding Transit Scenes: A Survey on Human Behavior-Recognition Algorithms (2010, unknown): “Recent crowd behavior analysis methods include tracking of moving objects [124], motion models using optical flow [125]–[128], and crowd-density measurement using background reference images [129].”
Estimating the number of people in crowded scenes by MID based foreground segmentation and head-shoulder detection (2008, methodology): “Rabaud et al [8] propose a method to count crowded moving objects based on clustering a set of extended tracked features.”
Optical flow patterns in broiler chicken flocks as automated measures of behaviour and gait (2009, background): “While this approach has had considerable success with dealing with a small number of easily identifiable animals (Rabaud and Belongie, 2006; Wills et al., 2003), it runs into problems with groups consisting of tens or hundreds of individuals, those problems including occlusion and computational over”
Towards Perspective-Free Object Counting with Deep Learning (2016, methodology): “Following the taxonomy introduced in [8], the algorithms can be classified into three groups: counting by detection [1, 2, 11–16], counting by clustering [17, 18], and counting by regression [3–7, 19, 20].”
Feature Mining for Localised Crowd Counting (2012, background): “In counting by clustering [4, 20], a crowd is assumed to be composed of individual entities, each of which has unique yet coherent motion patterns”
COUNT Forest: CO-Voting Uncertain Number of Targets Using Random Forest for Crowd Density Estimation (2015, methodology): “Existing counting methods can be classified into three categories: counting by detection [19, 30], counting by clustering [8, 25] and counting by regression [10, 11, 21, 16, 9, 23].”
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network (2016, methodology): “For instance, [24] has used highly parallelized version of the KLT tracker and agglomerative clustering to estimate the number of moving people.”
Where are the Blobs: Counting by Localization with Point Supervision (2018, background): “Object counting has received signiﬁcant attention over the past years [19,9,8].”
Density-aware person detection and tracking in crowds (2011, background): “Crowd density estimation has been addressed in a number of works [5,6,18,20,24].”
Multi-source Multi-scale Counting in Extremely Dense Crowd Images (2013, background): “Brostow and Cipolla [3] and Rabaud and Belongie [19] count moving objects by estimating contiguous regions of coherent motion.”
Learning Short-Cut Connections for Object Counting (2018, methodology): “In summary, different type of counting techniques have been applied such as counting by detection [7, 8, 9, 19, 21, 27, 39, 40], counting by clustering [30, 37], and counting by regression [3, 6, 10, 20, 28, 31, 44].”
Crowd Analysis Using Computer Vision Techniques (2010, methodology): “Cheriyadat and Radke [40] proposed an approach for clustering a set of low-level motion features into trajectories, similarly to [34] and [35], but using additional rules in the clustering process, such as the dominant movements that are computed based on the longest common subsequences.”
A Lagrangian Particle Dynamics Approach for Crowd Flow Segmentation and Stability Analysis (2007, methodology): “A dew approaches [13][ 8 ] which explicitly count the number of people in the crowd have also been proposed.”
Long-Term Occupancy Analysis Using Graph-Based Optimisation in Thermal Imagery (2013, unknown): “Rabaud and Belongie [34] * 6.”
Counting Vehicles with Cameras (2018, background): “The clustering by motion similarities approach relies instead on the assumption that a pair of points that appears to move together is likely to be part of the same individual, hence coherent feature trajectories can be grouped together to represent independently moving-entities, like in [13].”
Learning To Count Objects in Images (2010, background): “A number of approaches tackle counting problems in an unsupervised way, performing grouping based on self-similarities [3] or motion similarities [27].”
Counting People With Low-Level Features and Bayesian Regression (2012, methodology): “Examples of this formulation include [7], which uses the KLT tracker and agglomerative clustering, and [8], which relies on an unsupervised Bayesian approach.”
Vision-Based Analysis of Small Groups in Pedestrian Crowds (2012, methodology): “Even the affine motion check in [69] assumes more nodes per cluster than are typically present in a small”
Context-Aware Crowd Counting (2018, background): “Even though approaches relying on low-level features [9, 6, 4, 27, 7, 14] can yield good results, they have now mostly been superseded by CNN-based methods [42, 31, 5], a survey of which can be found in [36].”