FSD: Feature Skyscraper Detector for Stem End and Blossom End of Navel Orange

TL;DR

The paper introduces FSD, a novel feature skyscraper detector designed for precise, fast, and resource-efficient identification of stem end, blossom end, and black spots on navel oranges, outperforming existing detectors.

Contribution

It proposes a new feature skyscraper network architecture with dense connectivity and attention mechanisms, optimized for small object detection in agricultural quality control.

Findings

Achieves 87.479% mAP at 131 FPS

Uses only 5.812 million parameters

Outperforms state-of-the-art one-stage detectors

Abstract

To accurately and efficiently distinguish the stem end and the blossom end of navel orange from its black spots, we propose a feature skyscraper detector (FSD) with low computational cost, compact architecture and high detection accuracy. The main part of the detector is inspired from small object that stem (blossom) end is complex and black spot is densely distributed, so we design the feature skyscraper networks (FSN) based on dense connectivity. In particular, FSN is distinguished from regular feature pyramids, and which provides more intensive detection of high-level features. Then we design the backbone of the FSD based on attention mechanism and dense block for better feature extraction to the FSN. In addition, the architecture of the detector is also added Swish to further improve the accuracy. And we create a dataset in Pascal VOC format annotated three types of detection targets the stem end, the blossom end and the black spot. Experimental results on our orange data set confirm that FSD has competitive results to the state-of-the-art one-stage detectors like SSD, DSOD, YOLOv2, YOLOv3, RFB and FSSD, and it achieves 87.479%mAP at 131 FPS with only 5.812M parameters.