Enhanced Single-shot Detector for Small Object Detection in Remote Sensing Images

TL;DR

This paper introduces IPSSD, a novel single-shot detector that leverages an image pyramid network to improve small object detection in remote sensing images, achieving superior results over existing methods.

Contribution

The paper presents a new image pyramid single-shot detector (IPSSD) that enhances small object feature extraction for remote sensing images.

Findings

IPSSD outperforms state-of-the-art detectors on public datasets.

The method effectively enhances small-scale feature extraction.

Results demonstrate improved detection accuracy for small objects.

Abstract

Small-object detection is a challenging problem. In the last few years, the convolution neural networks methods have been achieved considerable progress. However, the current detectors struggle with effective features extraction for small-scale objects. To address this challenge, we propose image pyramid single-shot detector (IPSSD). In IPSSD, single-shot detector is adopted combined with an image pyramid network to extract semantically strong features for generating candidate regions. The proposed network can enhance the small-scale features from a feature pyramid network. We evaluated the performance of the proposed model on two public datasets and the results show the superior performance of our model compared to the other state-of-the-art object detectors.