An Effective Lightweight Crowd Counting Method Based on an Encoder–Decoder Network for Internet of Video Things

Yi, Jun; Chen, Fan; Shen, Zhilong; Xiang, Yi; Xiao, Shan; Zhou, Wei

doi:10.1109/jiot.2023.3294727

Cited by 4 publications

(2 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Part_B dataset is a relatively sparse dataset of people, consisting of 716 images with a total of 88,488 people labeled. The existing methods ( Gao et al, 2021 , 2023 ; Wang et al, 2023 ; Yi et al, 2024 ) have achieved good counting performance. Our method is also robust in single-channel crowd counting.…”

Section: Methodsmentioning

confidence: 99%

“…In addition, Gao et al (2021) proposed a domain-adaptive style counting method, which mainly addresses the problem of model performance degradation caused by the domain gap between realistic images and synthetic images. To address the gap between complex network architectures pursuing high-precision counting and limited computing and storage resources, Yi et al (2024) propose a lightweight crowd counting network based on an encoder-decoder to achieve an optimal trade-off between counting performance and running speed. However, these methods count the crowd or dense vehicles separately in a single scene and do not consider the problem of counting multi-class objects in complex traffic scenes.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Counting dense object of multiple types based on feature enhancement

Fu,

Min,

Sheng

et al. 2024

Front. Neurorobot.

View full text Add to dashboard Cite

IntroductionAccurately counting the number of dense objects in an image, such as pedestrians or vehicles, is a challenging and practical task. The existing density map regression methods based on CNN are mainly used to count a class of dense objects in a single scene. However, in complex traffic scenes, objects such as vehicles and pedestrians usually exist at the same time, and multiple classes of dense objects need to be counted simultaneously.MethodsTo solve the above issues, we propose a new multiple types of dense object counting method based on feature enhancement, which can enhance the features of dense counting objects in complex traffic scenes to realize the classification and regression counting of dense vehicles and people. The counting model consists of the regression subnet and the classification subnet. The regression subnet is primarily used to generate two-channel predicted density maps, mainly including the initial feature layer and the feature enhancement layer, in which the feature enhancement layer can enhance the classification features and regression counting features of dense objects in complex traffic scenes. The classification subnet mainly supervises classifying dense vehicles and people into two feature channels to assist the regression counting task of the regression subnets.ResultsOur method is compared on VisDrone+ datasets, ApolloScape+ datasets, and UAVDT+ datasets. The experimental results show that the method counts two kinds of dense objects simultaneously and outputs a high-quality two-channel predicted density map. The counting performance is better than the state-of-the-art counting network in dense people and vehicle counting.DiscussionIn future work, we will further improve the feature extraction ability of the model in complex traffic scenes to classify and count a variety of dense objects such as cars, pedestrians, and non-motor vehicles.

show abstract