Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network
This addresses the challenging problem of crowd counting in computer vision, with incremental improvements in accuracy for applications like surveillance and public safety.
The paper tackles crowd counting and density estimation by proposing a trellis encoder-decoder network (TEDnet) that generates high-quality density maps, achieving state-of-the-art performance with up to 14% improvement in MAE on four benchmarks.
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.