Journal
ELECTRONICS
Volume 12, Issue 8, Pages -Publisher
MDPI
DOI: 10.3390/electronics12081781
Keywords
deep learning; computer vision; object detection; pedestrian detection
Ask authors/readers for more resources
This paper proposes an anchor-free pedestrian detector called CAPNet to address the challenges in pedestrian detection. It introduces a feature extraction module, a global feature mining and aggregation network, and an attribute-guided multiple receptive field module to enhance the detection performance. Experimental results show that the context and attribute perception greatly improves the detection, and CAPNet achieves new state-of-the-art performance on Caltech and CityPersons datasets.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available