An Adaptive Multi-Scale Network Based on Depth Information for Crowd Counting
Author:
Zhang Peng1, Lei Weimin1, Zhao Xinlei2, Dong Lijia2, Lin Zhaonan1
Affiliation:
1. School of Computer Science and Engineering, Northeastern University, Shenyang 110167, China 2. Artificial Intelligence Research Institute Shenyang, 213 Electronic Technology Co., Ltd., Shenyang 110023, China
Abstract
Crowd counting, as a basic computer vision task, plays an important role in many fields such as video surveillance, accident prediction, public security, and intelligent transportation. At present, crowd counting tasks face various challenges. Firstly, due to the diversity of crowd distribution and increasing population density, there is a phenomenon of large-scale crowd aggregation in public places, sports stadiums, and stations, resulting in very serious occlusion. Secondly, when annotating large-scale datasets, positioning errors can also easily affect training results. In addition, the size of human head targets in dense images is not consistent, making it difficult to identify both near and far targets using only one network simultaneously. The existing crowd counting methods mainly use density plot regression methods. However, this framework does not distinguish the features between distant and near targets and cannot adaptively respond to scale changes. Therefore, the detection performance in areas with sparse population distribution is not good. To solve such problems, we propose an adaptive multi-scale far and near distance network based on the convolutional neural network (CNN) framework for counting dense populations and achieving a good balance between accuracy, inference speed, and performance. However, on the feature level, in order to enable the model to distinguish the differences between near and far features, we use stacked convolution layers to deepen the depth of the network, allocate different receptive fields according to the distance between the target and the camera, and fuse the features between nearby targets to enhance the feature extraction ability of pedestrians under nearby targets. Secondly, depth information is used to distinguish distant and near targets of different scales and the original image is cut into four different patches to perform pixel-level adaptive modeling on the population. In addition, we add density normalized average precision (nAP) indicators to analyze the accuracy of our method in spatial positioning. This paper validates the effectiveness of NF-Net on three challenging benchmarks in Shanghai Tech Part A and B, UCF_ CC_50, and UCF-QNRF datasets. Compared with SOTA, it has more significant performance in various scenarios. In the UCF-QNRF dataset, it is further validated that our method effectively solves the interference of complex backgrounds.
Funder
National Key R&D Program of China Special Fund for Basic Research Business Fees of Central Universities 2022 Key Science and Technology Project of Liaoning Province
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference66 articles.
1. Mundhenk, T.N., Konjevod, G., Sakla, W.A., and Boakye, K. (2016, January 10–16). A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning. Proceedings of the 14th European Conference on Computer Vision, Amsterdam, The Netherlands. 2. Zhang, S., Wu, G., Costeira, J.P., and Moura, J.M. (2017, January 21–26). Understanding traffic density from large-scale web camera data. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA. 3. Xue, Y., Ray, N., Hugh, J., and Bigras, G. (2016). Computer Vision–ECCV 2016 Workshops: Amsterdam, The Netherlands, 8–10 and 15–16 October 2016, Springer International Publishing. 4. Arteta, C., Lempitsky, V., and Zisserman, A. (2016, January 11–14). Counting in the wild. Proceedings of the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. 5. Anomaly detection and localization in crowded scenes;Li;IEEE Trans. Pattern Anal. Mach. Intell.,2013
|
|