Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks—Counting, Detection, and Tracking

Abstract

For crowded scenes, the accuracy of object-based computer vision methods declines when the images are lowresolution and objects have severe occlusions. Taking counting methods for example, almost all the recent state-of-the-art counting methods bypass explicit detection and adopt regressionbased methods to directly count the objects of interest. Among regression-based methods, density map estimation, where the number of objects inside a subregion is the integral of the density map over that subregion, is especially promising because it preserves spatial information, which makes it useful for both counting and localization (detection and tracking). With the power of deep convolutional neural networks (CNNs) the counting performance has improved steadily. The goal of this paper is to evaluate density maps generated by density estimation methods on a variety of crowd analysis tasks, including counting, detection, and tracking. Most existing CNN methods produce density maps with resolution that is smaller than the original images, due to the downsample strides in the convolution/pooling operations. To produce an original-resolution density map, we also evaluate a classical CNN that uses a sliding window regressor to predict the density for every pixel in the image. We also consider a fully convolutional (FCNN) adaptation, with skip connections from lower convolutional layers to compensate for loss in spatial information during upsampling. In our experiments, we found that the lower-resolution density maps sometimes have better counting performance. In contrast, the original-resolution density maps improved localization tasks, such as detection and tracking, compared to bilinear upsampling the lower-resolution density maps. Finally, we also propose several metrics for measuring the quality of a density map, and relate them to experiment results on counting and localization.

Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting

“…Computer vision-based crowd counting [8,17,26,27,36,44,48,56,68,69,74,77] has witnessed tremendous progress in the recent years. Algorithms developed for crowd counting have found a variety of applications such as video and traffic surveillance [15,21,38,59,64,71,72], agriculture monitoring (plant counting) [35], cell counting [22], scene understanding, urban planning and environmental survey [11,68].…”

Design Principles for Autonomous Illumination Control in Localization Microscopy

“…Previous models for density map regression have utilized an ad-hoc MESA distance [24] refined with ridge-regression [25], a random forest with hand-crafted features [27], or fully convolutional neural networks (FCNNs) [26,28,29]. FCNNs are particularly attractive because they do not require hand-crafted features and the model can be trained directly from images.…”

“…Next, its weights are frozen and the combined segmentation/density network is trained in full, this time with ground truth density maps also generated from simulated data. As in [28], the loss function that is used for backpropagation while training the full network is comprised of two terms.…”

Crowd Counting on Images with Scale Variation and Isolated Clusters

“…Crowd counting is to estimate the number of objects (such as people or vehicles) in unconstrained congested environments, where the image is often taken by a surveillance camera or unmanned aerial vehicle (UAV). Crowd counting has attracted widespread attention due to its application in public safety, congestion monitoring and traffic management [30], [11].…”