Privacy preserving crowd monitoring: Counting people without people models or tracking

By Antoni B. Chan, Zhang Liang, Nuno Vasconcelos. 2008

1,175 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Safety, Robustness & Interpretability

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

In Safety, Robustness & Interpretability

Citations in the corpus

DeepSetNet: Predicting Sets with Deep Neural Networks (2016, methodology): “To this end, we apply our approach on the widely used UCSD dataset [4] and compare our results to four state-of-the art approaches [1, 32, 35, 50].”
Representation Learning by Learning to Count (2017, methodology): “There are methods to count humans in crowds [4, 42, 8], cars [28], and penguins [2].”
A survey of data fusion in smart city applications (2019, background): “As privacy issue has been discussed extensively by the authors in [116], [237], [238], misuse of private information may lead to catastrophic events such as information theft, or identity fraud.”
ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding (2018, methodology): “We evaluate ADCrowdNet on four challenging datasets for crowd counting: ShanghaiTech dataset [37], the UCF CC 50 dataset [12], the WorldExpo’10 dataset [35], and the UCSD dataset [3].”
Counting in the Wild (2016, background): “As a consequence, models emerged which cast the problem as one where image features were mapped into a global object count [2, 3, 7], or local features mapped into pixel-wise object densities [4, 6, 8, 16, 24, 26] which can be integrated into the object count over”
CrowdNet: A Deep Convolutional Network for Dense Crowd Counting (2016, background): “Some works in the crowd counting literature experiment on datasets having sparse crowd scenes [2, 10], such as UCSD dataset [2], Mall dataset [3] and PETS dataset [7].”
Salient Object Subitizing (2015, background): “…large body of literature about automated object counting based on density estimation (Lempitsky and Zisserman, 2010; Arteta et al., 2014), object detection/segmentation (Subburaman et al., 2012; Nath et al., 2006; Anoraganingrum, 1999) and regression (Chan et al., 2008; Chan and Vasconcelos, 2009).”
Scale Aggregation Network for Accurate and Efficient Crowd Counting (2018, methodology): “UCSD.”
Crowd Analysis Using Computer Vision Techniques (2010, methodology): “It is also interesting to note that techniques that somehow explore camera information (such as [33], [28], and [29]) are more flexible regarding the camera setup used to monitor the scene, being also able to correct perspective distortions.”
Learning to Detect Partially Overlapping Instances (2013, methodology): “We apply our method to detect and count pedestrians in the UCSD surveillance camera dataset [6].”
Microscopy cell counting and detection with fully convolutional regression networks (2018, background): “…crowded images or videos is an extremely tedious and time-consuming task encountered in many real-world applications, including biology (Arteta et al. 2012, 2014, 2015; Fiaschi et al. 2012), surveillance (Chan et al. 2008; Lempitsky & Zisserman 2010) and other applications (Barinova et al. 2012).”
Synthetic Data for Deep Learning (2019, methodology): “, the UCSD dataset [89] and the Mall dataset [100] have both about 50,000 pedestrians but in each case collected from”
A comprehensive review on ensemble deep learning: Opportunities and challenges (2023, neutral): “UCF 50 crowd counting (Idrees et al., 2013), UCSD (Chan et al., 2008).”
Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds (2018, methodology): “For instance, UCSD dataset [4] contains 2, 000 video frames with 49, 885 annotated persons.”
Interactive Object Counting (2014, background): “Towards this goal, several computer vision approaches that use machine learning in order to automate such tasks have been suggested [5, 8, 10, 12].”
Towards Perspective-Free Object Counting with Deep Learning (2016, methodology): “For doing so, we use the popular UCSD pedestrian benchmark [4].”