Crowd Counting Via Multi-Level Regression With Latent Gaussian Maps

Abstract

Crowd counting still confronts two primary challenges: limited ability to deal with cross density levels caused by fixed density maps and lack of fine-grained or coarse-grained guidance for density estimation. In this paper, a novel end-to-end crowd counting framework via multi-level regression with latent Gaussian maps is proposed, which is consisted of GaussianNet, EstimateNet and Discriminator. GaussianNet is composed of masked Gaussian convolutional blocks and vanillia convolutional layers, to generate latent Gaussian maps adaptively for various density levels. The latent Gaussian maps are then treated as the ground truth density maps for EstimateNet, which outputs density estimations and follows the principle of adversarial learning with Discriminator. Moreover, multi-level losses are combined for density map regression guidance. Extensive experiments on the major public datasets outperform state-of-the-art ones, illustrating the superior validity of the proposed framework.

Research on Local Counting and Object Detection of Multiscale Crowds in Video Based on Time-Frequency Analysis

“…Since detection performance can be severely affected in overcrowded real-time scenes, detection-based methods are often outperformed by density map regression-based methods. The success of density map-based regression methods can be attributed to their ability to bypass explicit detection and map input images directly to scalar values [49][50][51]. However, although the method based on density regression can perceive the distribution of the crowd, it loses the ability to generate the individual localization of the crowd, so it is difficult to further study the dense crowd tracking and reidentification technology in surveillance.…”

Enhancement of Local Crowd Location and Count: Multiscale Counting Guided by Head RGB-Mask

“…erefore, the counting problem of visually indistinguishable crowded images cannot be completely solved. [8,[43][44][45][46][47][48][49]. Powerful CNNs play an important role in the density map regression process, and Wang et al [43] show that features extracted from deep models are more effective than handcrafted features.…”

“…Methods based on regression density maps have achieved a breakthrough in addressing indistinguishable crowd counting [ 8 , 43 – 49 ]. Powerful CNNs play an important role in the density map regression process, and Wang et al [ 43 ] show that features extracted from deep models are more effective than handcrafted features.…”

“…Current crowd counting methods can be divided into two categories: methods based on object detection and feature regression [6][7][8][9]. Early work is to use some kind of object detection model to detect individual objects.…”

Gaussian map predictions for 3D surface feature localisation and counting

“…This density prediction is later used in [18], where different deep learning architectures where employed to predict density maps and use the same integration method to predict object counts. In [9], the authors propose to combine Gaussian maps and density maps across different losses, to refine predictions of the different network parts. While improvements in counting performance compared to state-of-the-art methods are reported, the method still relies on density maps to predict the count, and requires complex training with multiple networks and loss functions involved.…”