Selective Cotton Boll Localization for Robotic Harvesting: Evaluation of Deep Learning Vision Models Under Field Conditions

arXiv:2609.19592 · cs.CV, cs.RO · Submitted 2026-09-17 · Read on arXiv

cs.CV, cs.RO

Submitted: 2026-09-17

Updated: 2026-09-17

Code: https://github.com/imtheva/CottonBoll_Harvest

Terminology

• Accuracy — 46× in this paper · explained in 1 episode
• F1 Score — 15× in this paper · explained in 3 episodes
• Robustness — 14× in this paper · explained in 5 episodes
• Consistency — 13× in this paper · explained in 3 episodes
• Segmentation Masks — 11× in this paper · explained in 2 episodes
• Instance Segmentation — 7× in this paper · explained in 3 episodes
• Frames Per Second — 6× in this paper
• Segment Anything Model — 6× in this paper
• Average Precision — 5× in this paper
• Segment Anything Model (SAM) — 5× in this paper · explained in 2 episodes
• Artificial Intelligence — 4× in this paper
• Benchmark — 4× in this paper · explained in 2 episodes
• Feature Extraction — 4× in this paper · explained in 2 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Programmable Gradient Information — 3× in this paper
• Artificial Intelligence (AI) — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• False Positive — 2× in this paper
• Generalization — 2× in this paper · explained in 13 episodes
• Generalized Efficient Layer Aggregation Network — 2× in this paper
• Grounding — 2× in this paper · explained in 3 episodes
• Hypergraph — 2× in this paper · explained in 2 episodes
• Mask Generation — 2× in this paper · explained in 2 episodes
• Multi-Receptive Field — 2× in this paper
• Transfer Learning — 2× in this paper · explained in 10 episodes
• Actionability — 1× in this paper · explained in 3 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Efficient Area Attention — 1× in this paper
• Embeddings — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• False Negative — 1× in this paper
• Generative AI — 1× in this paper · explained in 2 episodes
• Grounded-SAM with the Recognize Anything Model — 1× in this paper
• Physical Constraints — 1× in this paper · explained in 7 episodes
• True Positive — 1× in this paper
• Unified Framework — 1× in this paper · explained in 5 episodes
• Verification — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes
• Zero-Shot Transfer — 1× in this paper · explained in 4 episodes

Sources

• Intelligent Robotic Control System Based on Computer Vision Technology
• YOLOv12: Attention-Centric Real-Time Object Detectors
• YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception
• YOLOX: Exceeding YOLO Series in 2021
• YOLOv11: An Overview of the Key Architectural Enhancements
• Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
• SAM 2: Segment Anything in Images and Videos
• Fast Segment Anything
• Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
• YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
• YOLOv10: Real-Time End-to-End Object Detection
• Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
• Open-Set Image Tagging with Multi-Grained Text Supervision
• Recognize Anything: A Strong Image Tagging Model
• Tag2Text: Guiding Vision-Language Model via Image Tagging

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models