Iterative Optimization Annotation Pipeline and ALSS-YOLO-Seg for Efficient Banana Plantation Segmentation in UAV Imagery

TL;DR

This paper introduces an iterative annotation pipeline using SAM2 to efficiently generate high-quality labels and a lightweight segmentation model, ALSS-YOLO-Seg, optimized for UAV imagery of banana plantations, addressing annotation costs and segmentation challenges.

Contribution

It presents a novel annotation pipeline leveraging SAM2's zero-shot capabilities and a new lightweight segmentation model with modules tailored for UAV banana plantation imagery.

Findings

Reduced annotation time and cost significantly.

Achieved accurate segmentation with a lightweight model.

Improved segmentation performance on complex backgrounds.

Abstract

Precise segmentation of Unmanned Aerial Vehicle (UAV)-captured images plays a vital role in tasks such as crop yield estimation and plant health assessment in banana plantations. By identifying and classifying planted areas, crop area can be calculated, which is indispensable for accurate yield predictions. However, segmenting banana plantation scenes requires a substantial amount of annotated data, and manual labeling of these images is both time-consuming and labor-intensive, limiting the development of large-scale datasets. Furthermore, challenges such as changing target sizes, complex ground backgrounds, limited computational resources, and correct identification of crop categories make segmentation even more difficult. To address these issues, we proposed a comprehensive solution. Firstly, we designed an iterative optimization annotation pipeline leveraging SAM2's zero-shot capabilities to generate high-quality segmentation annotations, thereby reducing the cost and time associated with data annotation significantly. Secondly, we developed ALSS-YOLO-Seg, an efficient lightweight segmentation model optimized for UAV imagery. The model's backbone includes an Adaptive Lightweight Channel Splitting and Shuffling (ALSS) module to improve information exchange between channels and optimize feature extraction, aiding accurate crop identification. Additionally, a Multi-Scale Channel Attention (MSCA) module combines multi-scale feature extraction with channel attention to tackle challenges of varying target sizes and complex ground backgrounds.