Creating a visible-thermal multimodal tomato detection dataset

Share
Creating a visible-thermal multimodal tomato detection dataset

Source: HD.com

Creating a visible-thermal multimodal tomato detection dataset The rapid development of machine vision has promoted the automation of crop monitoring, providing technical support for planting management. For this purpose, this paper constructs a visible light-thermal infrared multimodal image dataset for the detection of owers and fruits of facility tomatoes: it includes 300 images of the owering period and 343 images of the fruiting period collected by the H982 visible light camera, as well as 145 images of the fruiting period collected by the HIKMIC thermal infrared camera.

Based on the evaluation of YOLOv11 (n/s/l) and YOLOv13 (n/s/l), the optimal mAP50 for the ower subset can reach 89.86%, while the optimal mAP50 for the fruit subset and the entire dataset is above 84%. The overall detection accuracy is excellent, indicating that the dataset is practical.

The multimodal fusion experiment shows that compared with single visible light, the fusion strategy signicantly improves the detection performance without sacricing the inference eciency almost at all, verifying the complementarity of thermal infrared and visible light, and providing data support for the research and deployment of intelligent monitoring algorithms for facility tomatoes. A visible light-thermal infrared multimodal image dataset collected from a real greenhouse tomato cultivation scene for flower and fruit detection.

Why this matters: For operators, this is a water-management story. The useful signal is that direct substrate measurements can help cut drain loss materially without giving up yield or fruit quality, which is exactly the kind of controllable efficiency gain a facility can build on.

Read the full article →


Frequently Asked Questions

Why does substrate sensing matter in free-drain strawberry systems?

Because drain percentage tells a grower what already happened, while substrate moisture and EC data show root-zone conditions directly. That makes it easier to cut water loss without guessing.

What is the operator takeaway from this trial?

If the thresholds are understood well enough, growers can reduce drain water materially while protecting yield and fruit quality, which makes sensing an operational tool instead of a reporting tool.

Read more