|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
By minimizing the mutual information, each column is guided to learn features with different image scales.
Although the Maximum Excess over SubArrays (MESA) loss has been previously proposed to address the above issues by finding the rectangular subregion whose predicted density map has the maximum difference from the ground truth, it cannot be solved by gradient descent, thus can hardly be integrated into the deep learning framework.
In this paper, we propose a novel perspective-guided convolution (PGC) for convolutional neural network (CNN) based crowd counting (i. e. PGCNet), which aims to overcome the dramatic intra-scene scale variations of people due to the perspective effect.
Designing a general crowd counting algorithm applicable to a wide range of crowd images is challenging, mainly due to the possibly large variation in object scales and the presence of many isolated small clusters.
These issues are further exacerbated in highly congested scenes.
Automatic estimation of the number of people in unconstrained crowded scenes is a challenging task and one major difficulty stems from the huge scale variation of people.
A dense region can always be divided until sub-region counts are within the previously observed closed set.
Recently, convolutional neural networks (CNNs) are the leading defacto method for crowd counting.
The latter attempts to extract more discriminative features among different channels, which aids model to pay attention to the head region, the core of crowd scenes.