Crowd counting via joint SASNet and a guided batch normalization network

Haldız, Cengizhan and Ismael, Sarmad F. and Çelebi, Hasari and Aptoula, Erchan (2023) Crowd counting via joint SASNet and a guided batch normalization network. In: 31st Signal Processing and Communications Applications Conference (SIU), Istanbul, Turkiye

[thumbnail of Crowd_Counting_via_Joint_SASNet_and_a_Guided_Batch_Normalization_Network.pdf] PDF
Restricted to Registered users only

Download (9MB) | Request a copy


Recent studies on crowd counting have achieved promising results by using convolutional neural network (CNN) architectures. However, due to the large variation in scene distribution in real-world crowd datasets, it remains a challenge to achieve high performance using standard CNN methods. Such methods often suffer from performance drops. To address this challenge, this paper proposes a new crowd-counting approach that combines three state-of-the-art methods: Guided-Batch-Normalization, which adapts the model using unseen dataset normalization parameters; the Scale Adaptive Selection Network, which uses a multi-level network to obtain variation feature representations; and Distribution-Matching-Count, which uses a new loss function between prediction and ground truth maps. Combining these methods results in improved performance. Extensive experiments across multiple datasets have demonstrated that the proposed approach outperforms state-of-the-art methods.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: Distribution Matching loss; Batch-Normalization; Crowd Counting; Density Map Estimation; multi-level network
Divisions: Faculty of Engineering and Natural Sciences
Depositing User: Erchan Aptoula
Date Deposited: 04 Oct 2023 15:05
Last Modified: 07 Feb 2024 14:37

Actions (login required)

View Item
View Item