The mainstream crowd counting methods usually utilize the convolution neural network (CNN) to regress a density map, requiring point-level annotations. However, annotating …
X Jiang, L Zhang, M Xu, T Zhang, P Lv… - Proceedings of the …, 2020 - openaccess.thecvf.com
Abstract Convolutional Neural Network (CNN) based methods generally take crowd counting as a regression task by outputting crowd densities. They learn the mapping …
D Liang, J Xie, Z Zou, X Ye, W Xu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Supervised crowd counting relies heavily on costly manual labeling, which is difficult and expensive, especially in dense scenes. To alleviate the problem, we propose a novel …
Semi-supervised approaches for crowd counting attract attention, as the fully supervised paradigm is expensive and laborious due to its request for a large number of images of …
Accurately estimating the number of objects in a single image is a challenging yet meaningful task and has been applied in many applications such as urban planning and …
S Bai, Z He, Y Qiao, H Hu, W Wu… - Proceedings of the …, 2020 - openaccess.thecvf.com
The counting problem aims to estimate the number of objects in images. Due to large scale variation and labeling deviations, it remains a challenging task. The static density map …
Y Tian, X Chu, H Wang - arXiv preprint arXiv:2109.14483, 2021 - arxiv.org
Most recent methods used for crowd counting are based on the convolutional neural network (CNN), which has a strong ability to extract local features. But CNN inherently fails …
Crowd counting and crowd density estimation methods are of great significance in the field of public security. Estimating crowd density and counting from single image or video frame …
X Liu, J Yang, W Ding, T Wang, Z Wang… - Computer Vision–ECCV …, 2020 - Springer
The crowd counting task aims at estimating the number of people located in an image or a frame from videos. Existing methods widely adopt density maps as the training targets to …