Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss

18 Nov 2019  ·  Qian Wang, Toby P. Breckon ·

Automatic crowd behaviour analysis is an important task for intelligent transportation systems to enable effective flow control and dynamic route planning for varying road participants. Crowd counting is one of the keys to automatic crowd behaviour analysis... Crowd counting using deep convolutional neural networks (CNN) has achieved encouraging progress in recent years. Researchers have devoted much effort to the design of variant CNN architectures and most of them are based on the pre-trained VGG16 model. Due to the insufficient expressive capacity, the backbone network of VGG16 is usually followed by another cumbersome network specially designed for good counting performance. Although VGG models have been outperformed by Inception models in image classification tasks, the existing crowd counting networks built with Inception modules still only have a small number of layers with basic types of Inception modules. To fill in this gap, in this paper, we firstly benchmark the baseline Inception-v3 model on commonly used crowd counting datasets and achieve surprisingly good performance comparable with or better than most existing crowd counting models. Subsequently, we push the boundary of this disruptive work further by proposing a Segmentation Guided Attention Network (SGANet) with Inception-v3 as the backbone and a novel curriculum loss for crowd counting. We conduct thorough experiments to compare the performance of our SGANet with prior arts and the proposed model can achieve state-of-the-art performance with MAE of 57.6, 6.3 and 87.6 on ShanghaiTechA, ShanghaiTechB and UCF\_QNRF, respectively. read more

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Crowd Counting ShanghaiTech A SGANet MAE 58 # 3
Crowd Counting ShanghaiTech A SGANet + CL MAE 57.6 # 2
Crowd Counting ShanghaiTech B SGANet MAE 6.3 # 1
Crowd Counting ShanghaiTech B SGANet + CL MAE 6.6 # 3
Crowd Counting UCF CC 50 SGANet MAE 224.6 # 4
Crowd Counting UCF CC 50 SGANet + CL MAE 221.9 # 3
Crowd Counting UCF-QNRF SGANet MAE 89.1 # 4
Crowd Counting UCF-QNRF SGANet + CL MAE 87.6 # 3