Spatial Transformer Network YOLO Model for Agricultural Object Detection

TL;DR

This paper introduces an enhanced YOLO model integrated with spatial transformer networks to improve agricultural object detection, especially in cluttered or occluded scenes, demonstrating significant performance gains on benchmark and real-world datasets.

Contribution

The paper presents a novel STN-YOLO model that incorporates spatial transformer networks into YOLO to improve focus on relevant image regions and spatial invariance for better detection accuracy.

Findings

Improved detection accuracy on agricultural datasets

Enhanced robustness to spatial transformations

Effective focus on important image regions

Abstract

Object detection plays a crucial role in the field of computer vision by autonomously locating and identifying objects of interest. The You Only Look Once (YOLO) model is an effective single-shot detector. However, YOLO faces challenges in cluttered or partially occluded scenes and can struggle with small, low-contrast objects. We propose a new method that integrates spatial transformer networks (STNs) into YOLO to improve performance. The proposed STN-YOLO aims to enhance the model's effectiveness by focusing on important areas of the image and improving the spatial invariance of the model before the detection process. Our proposed method improved object detection performance both qualitatively and quantitatively. We explore the impact of different localization networks within the STN module as well as the robustness of the model across different spatial transformations. We apply the STN-YOLO on benchmark datasets for Agricultural object detection as well as a new dataset from a state-of-the-art plant phenotyping greenhouse facility. Our code and dataset are publicly available.