Learning a perspective-embedded deconvolution network for crowd counting
We present a novel deep learning framework for crowd counting by learning a perspective-embedded deconvolution network. Perspective is an inherent property of most surveillance scenes. Unlike the traditional approaches that exploit the perspective as a separate normalization, we propose to fuse the perspective into a deconvolution network, aiming to obtain a robust, accurate and consistent crowd density map. Through layer-wise fusion, we merge perspective maps at different resolutions into the deconvolution network. With the injection of perspective, our network is driven to learn to combine the underlying scene geometric constraints adaptively, thus enabling an accurate interpretation from high-level feature maps to the pixel-wise crowd density map. In addition, our network allows generating density map for arbitrary-sized input in an end-to-end fashion. The proposed method achieves competitive result on the WorldExpo2010 crowd dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Crowd CountingSimilar Papers 제목 키워드 기반
Crowd Counting by Adapting Convolutional Neural Networks with Side Information
Computer vision tasks often have side information available that is helpful to solve the task. For example, for crowd counting, the camera perspective (e.g., camera angle and height) gives a clue about the appearance and…
Crowd CountingImage DeconvolutionPCC Net: Perspective Crowd Counting via Spatial Convolutional Network
Crowd counting from a single image is a challenging task due to high appearance similarity, perspective changes and severe congestion. Many methods only focus on the local appearance features and they cannot handle the a…
Crowd CountingExploiting Sample Correlation for Crowd Counting With Multi-Expert Network
Crowd counting is a difficult task because of the diversity of scenes. Most of the existing crowd counting methods adopt complex structures with massive backbones to enhance the generalization ability. Unfortunately,…
Crowd CountingRevisiting Perspective Information for Efficient Crowd Counting
Crowd counting is the task of estimating people numbers in crowd images. Modern crowd counting methods employ deep neural networks to estimate crowd counts via crowd density regressions. A major challenge of this task li…
Crowd CountingregressionReal-Time Crowd Counting for Embedded Systems with Lightweight Architecture
Crowd counting is a task of estimating the number of the crowd through images, which is extremely valuable in the fields of intelligent security, urban planning, public safety management, and so on. However, the existing…
Crowd Counting