Lina Han

Lina Han

Auto-generated profile, based on publicly available information

Lina Han

Jiangsu Province Engineering Research Center of Knowledge Management and Intelligent Service, College of Information Engineering (College of Artificial Intelligence), Yangzhou University, Yangzhou, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 February 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
XZXinfeng Zhang
Xinfeng Zhang
LHLina Han
Lina Han
WSWencong Shan
Wencong Shan
XWXiaohu Wang
Xiaohu Wang
SCShuhan Chen
Shuhan Chen
BLBin Li
Bin Li
Counting the number of people in public places has received much attention, and researchers have devoted much effort to the task. However, the existing crowd counting approaches are mainly trained and tested in similar scenarios. The performance of crowd counting approaches degrades sharply when the test scenarios of the models are of different types from its training scenes. In practice, the crowd scenes are highly variable, and the lack of cross-scene capability could seriously limit the application of the existing approaches. We attribute the improvement in cross-scene crowd counting capability to the necessity of accommodating large changes in the scale of individuals and the ability to suppress the interference of cluttered backgrounds. To this end, we propose a multi-scale feature fusion network (MFFNet) with cascaded supervision. The multi-scale features extracted from the crowd images are upsampled and then combined into several feature blocks, followed by convolution and deconvolution operations on the feature blocks to derive feature matrices of different resolutions. The feature matrices are fused from bottom to top. In the process of feature fusion, the crowd density maps corresponding to the feature matrices of different resolutions are predicted separately. We devise cascaded supervision to synchronously optimize the network of different resolution density map prediction during training. The cross-scene crowd counting experiments are conducted on four types of scenes: SHT A with high-density crowd scenes and small-scale individuals, SHT B with sparse crowd distribution and medium-scale individuals, UCF_CC_50 dataset with extremely dense scenes and tiny scale individuals, and UCF-QNRF dataset with extreme variations. MFFNet exhibits the strongest scene adaptability relative to the state-of-the-art approaches, with an average decrease of 17.1% and 8.4% in MAE and MSE, respectively. The contributions of different components in our method are verified in the ablation study using the devised evaluation metrics. Our implementation will be available at https://github.com/learnsharing/MFFNet.