U-ASD Net: Supervised Crowd Counting Based on Semantic Segmentation and Adaptive Scenario Discovery

Abstract

Crowd counting considers one of the most significant and challenging issues in computer vision and deep learning communities, whose applications are being utilized for various tasks. While this issue is well studied, it remains an open challenge to manage perspective distortions and scale variations. How well these problems are resolved has a huge impact on predicting a high-quality crowd density map. In this study, a hybrid and modified deep neural network (U-ASD Net), based on U-Net and adaptive scenario discovery (ASD), is proposed to get precise and effective crowd counting. The U part is produced by replacing the nearest upsampling in the encoder of U-Net with max-unpooling. This modification provides a better crowd counting performance by capturing more spatial information. The max-unpooling layers upsample the feature maps based on the max locations held from the downsampling process. The ASD part is constructed with three light pathways, two of which have been learned to reflect various densities of the crowd and define the appropriate geometric configuration employing various sizes of the receptive field. The third pathway is an adaptation path, which implicitly discovers and models complex scenarios to recalibrate pathway-wise responses adaptively. ASD has no additional branches to avoid increasing the complexity. The designed model is end-to-end trainable. This integration provides an effective model to count crowds in both dense and sparse datasets. It also predicts an elevated quality density map with a high structural similarity index and a high peak signal-to-noise ratio. Several comprehensive experiments on four popular datasets for crowd counting have been carried out to demonstrate the proposed method's promising performance compared to other state-of-the-art approaches. The proposed model achieves the lowest count error in terms of the MAE in ShanghaiTech Part A, Part B, and Mall datasets with 64.6, 7.5, and 1.8, respectively. Moreover, it achieves the lowest count error in terms of the MSE in ShanghaiTech Part B, UCF CC 50, UCSD, and Mall datasets with 12.4, 217.8, 2.1, 2.2, respectively. In addition, the proposed model accomplishes the best quality density maps on all the utilized datasets. Furthermore, a new dataset with its manual annotations, called Haramain with three different scenes and different densities, is introduced and used for evaluating the U-ASD Net.

A Dilated Convolutional Neural Network for Cross-Layers of Contextual Information for Congested Crowd Counting

“…Moreover, for PCC Net [ 25 ], its parameter space is as light as the Cascaded-MTL model, but its runtime is even higher due to the inferior running platform. As shown in Table 9 , the parameter number of the proposed CL-DCNN is one-third of the U-ASD network [ 12 ] and with a lower runtime. After considering the running platform and parameter quantity comprehensively, the effectiveness of the proposed CL-DCNN and U-ASD network is equivalent.…”

“…Furthermore, by integrating the U-net architecture with an Adaptive Scenario Discovery (ASD) module, Hafeezallah et al proposed the U-ASD-Net [ 12 ] for crowd counting. Specifically, the U-ASD-Net employs a max-unpooling layer to upsample feature maps based on maximum locations, thereby replacing the nearest upsampling method in the U-part.…”

A Deep Learning Approach for Crowd Counting in Highly Congested Scene

“…6 compares the results of MAE with MSE. [5] 467.0 498.5 MCNN [15] 377.6 509.1 Hydra 2's [17] 333.7 425.2 Hydra 3's [17] 465.7 371.8 Learning to count [71] 364.4 341.4 Fully convolutional [45] 338.6 424.5 Cascaded-MTL [69] 322.8 397.9 Switching-CNN [4] 318.1 439.2 CP-CNN [13] 295.8 320.9 CSRNet [2] 266.1 397.5 Transform dilated [72] 250.1 342.1 U-ASD Net [73] 232.3 217.8 S-DCNet [51] 204.2 301.3 CSCC-Net (Ours) 199.1 243.2…”

Motion Pattern-Based Scene Classification Using Adaptive Synthetic Oversampling and Fully Connected Deep Neural Network

“…Crowd behaviour analysis [3], [4] examines the movement and interactions within crowds to improve safety. Crowd density estimation and crowd counting [5] are focused on assessing the number of people and the compactness of a crowd, which have applications in public safety and event management. Crowd anomaly detection [6] identifies unusual patterns that may indicate danger or suspicious activities, while group detection [7] explores the formation and behavior of smaller groups within the crowd.…”