Cascaded Residual Density Network for Crowd Counting

• URL: http://arxiv.org/abs/2107.13718v1
• Date: Thu, 29 Jul 2021 03:07:11 GMT
• Title: Cascaded Residual Density Network for Crowd Counting
• Authors: Kun Zhao, Luchuan Song, Bin Liu, Qi Chu, Nenghai Yu
• Abstract summary: We propose a novel Cascaded Residual Density Network (CRDNet) in a coarse-to-fine approach to generate the high-quality density map for crowd counting more accurately. A novel additional local count loss is presented to refine the accuracy of crowd counting.
• Score: 63.714719914701014
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Crowd counting is a challenging task due to the issues such as scale variation and perspective variation in real crowd scenes. In this paper, we propose a novel Cascaded Residual Density Network (CRDNet) in a coarse-to-fine approach to generate the high-quality density map for crowd counting more accurately. (1) We estimate the residual density maps by multi-scale pyramidal features through cascaded residual density modules. It can improve the quality of density map layer by layer effectively. (2) A novel additional local count loss is presented to refine the accuracy of crowd counting, which reduces the errors of pixel-wise Euclidean loss by restricting the number of people in the local crowd areas. Experiments on two public benchmark datasets show that the proposed method achieves effective improvement compared with the state-of-the-art methods.

Related papers

• Diffusion-based Data Augmentation for Object Counting Problems [62.63346162144445]
  We develop a pipeline that utilizes a diffusion model to generate extensive training data. We are the first to generate images conditioned on a location dot map with a diffusion model. Our proposed counting loss for the diffusion model effectively minimizes the discrepancies between the location dot map and the crowd images generated.
  arXiv  Detail & Related papers  (2024-01-25T07:28:22Z)
• Progressive Multi-resolution Loss for Crowd Counting [126.01887803981619]
  We propose to predict the density map at one resolution but measure the density map at multiple resolutions. We mathematically prove it is superior to a single-resolution L2 loss.
  arXiv  Detail & Related papers  (2022-12-08T07:55:13Z)
• Semi-supervised Crowd Counting via Density Agency [57.3635501421658]
  We build a learnable auxiliary structure, namely the density agency to bring the recognized foreground regional features close to corresponding density sub-classes. Second, we propose a density-guided contrastive learning loss to consolidate the backbone feature extractor. Third, we build a regression head by using a transformer structure to refine the foreground features further.
  arXiv  Detail & Related papers  (2022-09-07T06:34:00Z)
• Redesigning Multi-Scale Neural Network for Crowd Counting [68.674652984003]
  We introduce a hierarchical mixture of density experts, which hierarchically merges multi-scale density maps for crowd counting. Within the hierarchical structure, an expert competition and collaboration scheme is presented to encourage contributions from all scales. Experiments show that our method achieves the state-of-the-art performance on five public datasets.
  arXiv  Detail & Related papers  (2022-08-04T21:49:29Z)
• Reciprocal Distance Transform Maps for Crowd Counting and People Localization in Dense Crowd [16.224760698133462]
  We propose a novel Reciprocal Distance Transform (R-DT) map for crowd counting. Compared with the density maps, the R-DT maps accurately describe the people location, without overlap between nearby heads in dense regions. We simultaneously implement crowd counting and people localization with a simple network by replacing density maps with R-DT maps.
  arXiv  Detail & Related papers  (2021-02-16T02:25:55Z)
• A Strong Baseline for Crowd Counting and Unsupervised People Localization [2.690502103971799]
  We explore a strong baseline for crowd counting and an unsupervised people localization algorithm based on estimated density maps. We collect different backbones and training tricks and evaluate the impact of changing them. We propose a clustering algorithm named isolated KMeans to locate the heads in density maps.
  arXiv  Detail & Related papers  (2020-11-07T08:29:03Z)
• Coarse- and Fine-grained Attention Network with Background-aware Loss for Crowd Density Map Estimation [2.690502103971799]
  CFANet is a novel method for generating high-quality crowd density maps and people count estimation. We devise a from-coarse-to-fine progressive attention mechanism by integrating Crowd Region Recognizer (CRR) and Density Level Estimator (DLE) branch. Our method can not only outperform previous state-of-the-art methods in terms of count accuracy but also improve the image quality of density maps as well as reduce the false recognition ratio.
  arXiv  Detail & Related papers  (2020-11-07T08:05:54Z)
• JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method [92.15895515035795]
  We introduce a new large scale unconstrained crowd counting dataset (JHU-CROWD++) that contains "4,372" images with "1.51 million" annotations. We propose a novel crowd counting network that progressively generates crowd density maps via residual error estimation.
  arXiv  Detail & Related papers  (2020-04-07T14:59:35Z)
• PDANet: Pyramid Density-aware Attention Net for Accurate Crowd Counting [7.02081613648832]
  Crowd counting remains an open real-world problem due to the vast scale variations in crowd density within the interested area. We propose a novel Pyramid Density-Aware Attention-based network, abbreviated as PDANet, that leverages the attention, pyramid scale feature and two branch decoder modules for density-aware crowd counting.
  arXiv  Detail & Related papers  (2020-01-16T04:26:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.