Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks

By Xiaolong Jiang, Zehao Xiao, Baochang Zhang, Xiantong Zhen, Xianbin Cao, David S. Doermann, Ling Shao. Computer Vision and Pattern Recognition, 2019

354 citations recorded by the source corpus.

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 improves the representative capability of convolutional features for large variations in objects. Second, we employ dense skip connections interleaved across paths to facilitate sufficient multi-scale feature fusions, which also helps TEDnet to absorb the supervision information. Third, we propose a new combinatorial loss to enforce similarities in local coherence and spatial correlation between maps. By distributedly imposing this combinatorial loss on intermediate outputs, TEDnet can improve the back-propagation process and alleviate the gradient vanishing problem. Finally, on four widely-used benchmarks, our TEDnet achieves the best overall performance in terms of both density map quality and counting accuracy, with an improvement up to 14% in MAE metric. These results validate the effectiveness of TEDnet for crowd counting.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/567dfb6af80f62bbebbdecf46c1d56cc52c32a85

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Distribution Matching for Crowd Counting (2020, background): “Most recent works [20, 35, 15, 4, 31, 50, 27, 40, 29, 26, 54, 8, 25, 55, 61, 59, 17, 48, 21, 23, 30, 47, 53, 43, 37, 56, 18, 39, 24, 44, 42] are based on density map estimation, which has been shown to be more robust than detection-then-count and count regression approaches.”
JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method (2020, methodology): “The proposed method is compared with the following recent methods: Idrees et al.[3], MCNN [5], CMTL [24], SwitchingCNN [7], Idrees et al.[21], Jian et al.[64], CA-Net [76], BCC [70], DSSI-Net [76], MBTTBF [63] and LSC-CNN [69].”
Attention Scaling for Crowd Counting (2020, methodology): “In this section, we evaluate our approach against sixteen currently reported methods [36, 5, 12, 19, 40, 32, 38, 31, 42, 20, 43, 6, 37, 22, 18, 41, 10] on ShanghaiTech Part A dataset [49], UCF CCF 50 dataset [10], UCF-QNRF Dataset [11] and WorldExpo’10 dataset [46].”