RootDown presents an end‑to‑end image‑based pipeline for detecting partially occluded sugar beets on loader conveyors, a key step toward automated quality inspection. The authors introduce a dedicated benchmark and an automatic annotation strategy that uses the SAM 3 foundation model to generate bounding boxes, comparing these labels with manually annotated ones. They also evaluate deployment on edge hardware, showing that a Raspberry Pi 5 with a Hailo accelerator can perform high‑performance, low‑power inference suitable for mobile outdoor use.
arXiv:2609.13551v1 Announce Type: new Abstract: Static-image benchmarks do not capture the computational and temporal requirements of practical orchard video analytics. This study presents an end-to-...
The paper evaluates how well Vision Transformers (ViTs) can handle token merging techniques—specifically ToMe and Mutual Pair Merging—across wheat phenotyping tasks such as growth-stage classification, wheat-head detection, and wheat-organ segmentation. It benchmarks task quality, throughput, token count, and GPU memory usage, including tests on a Raspberry Pi 5. Results show that classification is highly tolerant to token merging, whereas detection and segmentation suffer due to factors like repeated instances, thin organs, dense boundaries, and runtime overhead, and that optimized attention backends can negate apparent speed gains.
The paper introduces BalSAM, a model that combines the Segment Anything Model (SAM) with Digital Surface Model (DSM) elevation data to improve tree crown instance segmentation from high‑resolution drone imagery. Experiments across boreal plantations, temperate forests, and tropical forests show that while off‑the‑shelf SAM does not beat a custom Mask R-CNN, fine‑tuning SAM end‑to‑end and incorporating DSM information yield promising results, especially for plantation sites.
arXiv:2608.21254v1 Announce Type: cross Abstract: Accurate agricultural weed detection in real-world field conditions is essential for precision agriculture, enabling targeted intervention and reduci...
arXiv:2604. 26633v2 Announce Type: replace-cross Abstract: Industrial surface defect inspection suffers from a fundamental data bottleneck: defects are rare, annotations require expert knowledge, and collecting balanced training sets is slow and costly.
arXiv:2506. 03168v2 Announce Type: replace-cross Abstract: Amid the challenges posed by global population growth and climate change, traditional agricultural Internet of Things (IoT) systems is currently undergoing a significant digital transformation to facilitate efficient big data processing.
The paper demonstrates that object detection benchmarks suffer from incomplete annotations, with re-annotation of COCO, Pascal VOC, Cityscapes, and KITTI revealing up to a 60% increase in detected objects, especially small, occluded, or densely packed instances. The authors propose a scalable annotation pipeline that uses multiple annotators per object to capture uncertainty and improve recall, and they introduce two new large-scale benchmarks: an uncertainty-aware detection benchmark and a label error detection benchmark based on real errors. Their findings show that benchmark performance is highly sensitive to annotation quality, yet model rankings remain largely unchanged, highlighting the need for uncertainty-aware evaluation to better reflect real-world ambiguity.
arXiv:2609.13606v1 Announce Type: cross Abstract: Multi-arm robotic harvesting offers a promising path to improve harvesting efficiency and reduce reliance on manual labor. However, practical deploym...
arXiv:2603.16932v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) typically process images at a native high-resolution, forcing a trade-off between accuracy and computational ef...
arXiv:2610.34304v1 Announce Type: new Abstract: Conveyor belts are vital arteries in continuous bulk material handling, particularly in heavy process industries such as cement manufacturing. Undetect...
The paper introduces an edge‑deployable system that transforms photographs of bee hive frames into actionable inspection reports. It uses an object detector to identify comb‑cell classes, converts detections into a structured fact schema, and then generates constrained factual text that triggers a knowledge‑base for interpretation and recommendations. The authors also release the FAIRHiveText‑1K dataset, pairing images with facts and text, to support future LLM research in this domain.
arXiv:2607. 27065v2 Announce Type: cross Abstract: While automated defect detection such as the detection of surface scratched is an important aspect in industrial quality control, the scarcity of annotated defect data make this task challenging.