SSRDet: Small Object Detection Based on Feature Pyramid Network

Lijuan Zhang

doi:10.1109/ACCESS.2023.3306242

2023-01-01

DOI：10.1109/ACCESS.2023.3306242

原文链接

原文求助

摘要

En 中文

Due to the increasing presence of small objects in videos or images from practical applications, small object identification is currently an extremely popular topic in the field of machine vision. Additionally, small object detection is still a difficult process because to small objects' issues with fuzzy appearance, limited information, occlusion, and noise present. Most existing methods mainly use feature pyramid networks to enrich shallow features using contextual features. However, due to the inconsistency of gradients between different layers of the feature pyramid network, the shallow features cannot be fully utilized resulting in the slow improvement of small object detection accuracy. To effectively improve the small object detection algorithm, we propose a new feature pyramid network-based small object detection algorithm, SSRDet. To effectively assign positive and negative sample labels and address the issue of sample scale imbalance, we first present RFLA. Then, to overcome the gradient inconsistency between various layers and enable the full utilization of the shallow features, we extend the feature pyramid network by including a scale enhancement module (SEM) and a scale selection module (SSM). Finally, we introduced the attention module (SPAM) to filter out the background noise in the shallow feature extraction to better extract small object features. We validated our method on VisDrone2019 and AI-TOD, and our method outperformed the state-of-the-art detectors.

Keyword:

Object detection

Feature extraction

Detectors

Training

Semantics

Data augmentation

Gaussian distribution

Labeling

Small object detection

attention module

feature pyramid network