Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network

Abstract

Crowd counting has recently attracted increasing interest in computer vision but remains a challenging problem. In this paper, we propose a trellis encoder-decoder network (TEDnet) for crowd counting, which focuses on generating high-quality density estimation maps. The major contributions are four-fold. First, we develop a new trellis architecture that incorporates multiple decoding paths to hierarchically aggregate features at different encoding stages, which can handle large variations of objects. Second, we design dense skip connections interleaved across paths to facilitate sufficient multi-scale feature fusions and to absorb the supervision information. Third, we propose a new combinatorial loss to enforce local coherence and spatial correlation in density maps. By distributedly imposing this combinatorial loss on intermediate outputs, gradient vanishing can be largely alleviated for better back-propagation and faster convergence. Finally, our TEDnet achieves new state-of-the art performance on four benchmarks, with an improvement up to 14% in terms of MAE.

CVPR 2019, Accepted

References in corpus (3)

• A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation
• Stacked Deconvolutional Network for Semantic Segmentation
• Mixture of Counting CNNs: Adaptive Integration of CNNs Specialized to Specific Appearance for Crowd Counting

Cited by in corpus (9)

• Ambient Sound Helps: Audiovisual Crowd Counting in Extreme Conditions
• Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting
• Plug-and-Play Rescaling Based Crowd Counting in Static Images
• Towards Using Count-level Weak Supervision for Crowd Counting
• Weighing Counts: Sequential Crowd Counting by Reinforcement Learning
• Multi-Level Attentive Convoluntional Neural Network for Crowd Counting
• Multi-channel Deep Supervision for Crowd Counting
• Active Crowd Counting with Limited Supervision
• Interlayer and Intralayer Scale Aggregation for Scale-invariant Crowd Counting