A Semi-Self-Supervised Approach for Dense-Pattern Video Object Segmentation

TL;DR

This paper introduces a semi-self-supervised, diffusion-based method for dense video object segmentation, effectively reducing the need for extensive manual annotations in agricultural scenarios with densely packed, occluded objects.

Contribution

The proposed approach combines synthetic data and pseudo-labeling with diffusion models to improve dense VOS performance with minimal manual annotations.

Findings

Achieved a Dice score of 0.79 on drone-captured wheat head videos.

Effective in diverse agricultural settings and different growth stages.

Reduces reliance on large-scale manual annotations for dense object segmentation.

Abstract

Video object segmentation (VOS) -- predicting pixel-level regions for objects within each frame of a video -- is particularly challenging in agricultural scenarios, where videos of crops include hundreds of small, dense, and occluded objects (stems, leaves, flowers, pods) that sway and move unpredictably in the wind. Supervised training is the state-of-the-art for VOS, but it requires large, pixel-accurate, human-annotated videos, which are costly to produce for videos with many densely packed objects in each frame. To address these challenges, we proposed a semi-self-supervised spatiotemporal approach for dense-VOS (DVOS) using a diffusion-based method through multi-task (reconstruction and segmentation) learning. We train the model first with synthetic data that mimics the camera and object motion of real videos and then with pseudo-labeled videos. We evaluate our DVOS method for wheat head segmentation from a diverse set of videos (handheld, drone-captured, different field locations, and different growth stages -- spanning from Boot-stage to Wheat-mature and Harvest-ready). Despite using only a few manually annotated video frames, the proposed approach yielded a high-performing model, achieving a Dice score of 0.79 when tested on a drone-captured external test set. While our method was evaluated on wheat head segmentation, it can be extended to other crops and domains, such as crowd analysis or microscopic image analysis.