Aoran Chen

Mr. Aoran Chen

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
10 April 2023 in Electronics
Verified
Journal Article
Open access
PDF file
YZYueyan Zhu
Yueyan Zhu
Hai HuangHai Huang
Hai Huang
YHyu huayan
yu huayan
ACAoran Chen
Aoran Chen
GZGuanliang Zhao
Guanliang Zhao
With a focus on practical applications in the real world, a number of challenges impede the progress of pedestrian detection. Scale variance, cluttered backgrounds and ambiguous pedestrian features are the main culprits of detection failures. According to existing studies, consistent feature fusion, semantic context mining and inherent pedestrian attributes seem to be feasible solutions. In this paper, to tackle the prevalent problems of pedestrian detection, we propose an anchor-free pedestrian detector, named context and attribute perception (CAPNet). In particular, we first generate features with consistent well-defined semantics and local details by introducing a feature extraction module with a multi-stage and parallel-stream structure. Then, a global feature mining and aggregation (GFMA) network is proposed to implicitly reconfigure, reassign and aggregate features so as to suppress irrelevant features in the background. At last, in order to bring more heuristic rules to the network, we improve the detection head with an attribute-guided multiple receptive field (AMRF) module, leveraging the pedestrian shape as an attribute to guide learning. Experimental results demonstrate that introducing the context and attribute perception greatly facilitates detection. As a result, CAPNet achieves new state-of-the-art performance on Caltech and CityPersons datasets.

27 April 2024 in Sensors
Verified
Journal Article
Open access
PDF file
ACAoran Chen
Aoran Chen
Hai HuangHai Huang
Hai Huang
YZYueyan Zhu
Yueyan Zhu
JXJunsheng Xue
Junsheng Xue
In order to enhance the matting performance in multi-person dynamic scenarios, we introduce a robust, real-time, high-resolution, and controllable human video matting method that achieves state of the art on all metrics. Unlike most existing methods that perform video matting frame by frame as independent images, we design a unified architecture using a controllable generation model to solve the problem of the lack of overall semantic information in multi-person video. Our method, called ControlMatting, uses an independent recurrent architecture to exploit temporal information in videos and achieves significant improvements in temporal coherence and detailed matting quality. ControlMatting adopts a mixed training strategy comprised of matting and a semantic segmentation dataset, which effectively improves the semantic understanding ability of the model. Furthermore, we propose a novel deep learning-based image filter algorithm that enforces our detailed augmentation ability on both matting and segmentation objectives. Our experiments have proved that prior information about the human body from the image itself can effectively combat the defect masking problem caused by complex dynamic scenarios with multiple people.

13 October 2022
Verified
Book Chapter
Closed access
PDF file
ACAoran Chen
Aoran Chen
Hai HuangHai Huang
Hai Huang
YYYang Yang
Yang Yang
BLBohan Li
Bohan Li
XJXiaojun Jing
Xiaojun Jing

13 October 2022
Verified
Book Chapter
Closed access
PDF file
SWSijie Wei
Sijie Wei
XJXiaojun Jing
Xiaojun Jing
ACAoran Chen
Aoran Chen
QCQianqian Chen
Qianqian Chen
JMJunsheng Mu
Junsheng Mu
BLBohan Li
Bohan Li