Investigating Synthetic Data Sets for Crowd Counting in Cross-scene Scenarios

TitleInvestigating Synthetic Data Sets for Crowd Counting in Cross-scene Scenarios
Publication TypeConference Paper
Year of Publication2020
AuthorsDelussu, R, Putzu, L, Fumera, G
Conference NameProceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications VISAPP 2020
Date Published03/2020
Conference LocationValletta - Malta
ISSN Number2184-4321
ISBN Number978-989-758-402-2
KeywordsCross-scene, Crowd Analysis, Crowd Density Estimation, Regression, Synthetic Data Sets, Texture Features
Crowd counting and density estimation are crucial functionalities in intelligent video surveillance systems but
are also very challenging computer vision tasks in scenarios characterised by dense crowds, due to scale and
perspective variations, overlapping and occlusions. Regression-based crowd counting models are used for
dense crowd scenes, where pedestrian detection is infeasible. We focus on real-world, cross-scene application
scenarios where no manually annotated images of the target scene are available for training regression models,
but only images with different backgrounds and camera views can be used (e.g., from publicly available data
sets), which can lead to low accuracy. To overcome this issue, we propose to build the training set using
synthetic images of the target scene, which can be automatically annotated with no manual effort. This work
provides a preliminary empirical evaluation of the effectiveness of the above solution. To this aim, we carry
out experiments using real data sets as the target scenes (testing set) and using different kinds of synthetically
generated crowd images of the target scenes as training data. Our results show that synthetic training images
can be effective, provided that also their background, beside their perspective, closely reproduces the one of
the target scene.
Citation Key1457
VISAPP_2020_160_CR.pdf4.23 MB