Standard cameras can now track plant growth in 3D

What if measuring plant growth didn’t require cutting leaves or investing in costly tools? A new plant technique makes that possible – using nothing more than a standard video camera.

This method turns simple footage into detailed 3D models that can accurately estimate a plant’s total leaf area. It’s low-cost, easy to apply, and precise enough to handle even small crops like dwarf tomatoes.

Reconstructing plants in 3D

The study was led by Dmitrii Usenko, a Ph.D. candidate at the Institute of Environmental Sciences at Hebrew University, working with Dr. David Helman of Hebrew University and Dr. Chen Giladi of Sami Shamoon College of Engineering.

The method uses structure-from-motion (SfM), a technique from computer vision that reconstructs 3D shapes from video. It’s a smart workaround for the expensive equipment usually required to measure plant traits in detail.

Rather than relying on LiDAR or multispectral cameras, the team used simple video clips filmed from different angles. These were then transformed into 3D point clouds.

From that, the researchers extracted features and trained machine learning models to estimate leaf area.

Cameras to help protect plant growth

“Accurate measurement of total leaf area is crucial for understanding plant growth, photosynthesis, and water use,” explained Dr. Helman. “But traditional approaches often require destructive sampling or costly, inaccessible equipment.”

“Our model brings accessibility and accuracy together in a way that could benefit both smallholder farmers and large‑scale agricultural operations.”

To test their method, the team collected over 300 video clips of dwarf tomato plants grown under controlled greenhouse conditions.

Each clip captured the plant from multiple angles, allowing the software to reconstruct a detailed 3D model of its structure. They then trained machine learning models to connect that 3D data to real measurements of leaf area.

The results were impressive. The best-performing model achieved a coefficient of determination (R²) of 0.96 – a strong indicator of predictive accuracy. Even when leaves overlapped or the plant moved slightly during filming, the model remained reliable.

That kind of consistency is critical if the method is going to be used outside the lab, where conditions are far less controlled.

Smart tech for any farmer

The new method isn’t limited to tomatoes. Since it only requires a standard RGB camera and structure-from-motion techniques, it can be adapted to many other crops with similar results.

That makes it a flexible solution for farms growing everything from leafy greens to fruiting plants—especially in places where access to advanced imaging tools is limited or too costly.

Even more promising, the software developed for the study is open source. That means researchers, agronomists, and even tech-savvy farmers can modify it, build on it, and tailor it to their own crops or growing conditions.

It opens the door to community-driven improvements and broader adoption in both research and real-world farming.

Affordable tools for better farming

“By reducing the cost barrier to accurate plant monitoring, we hope to democratize access to precision agriculture,” said Usenko. “This is a small but meaningful step toward smarter, more sustainable farming.”

That human perspective underlines the goal: make precision agriculture – once reserved for big, high-tech operations – available to everyone.

Until now, tools that help monitor crops closely have often been out of reach for smallholder farmers or those in lower-income regions. But by cutting costs and simplifying the process, this method brings advanced monitoring within reach for more people.

It’s about leveling the playing field so that better farming decisions aren’t limited by access to expensive tools – but guided by practical, affordable solutions.

The future of plant monitoring

Plant monitoring doesn’t have to be expensive or complicated. This research demonstrates that with the right method, even basic tools such as video cameras can reveal in-depth information regarding plant health and growth.

The study brings us one step closer to a future where monitoring crops is easier, more affordable, and more accurate -regardless of farm size or budget.

As more growers and researchers adopt and adapt this technique across different crops, it could transform how plant data is collected on a global scale.

Better insights into plant growth mean smarter, more sustainable cultivation – and that benefits farms, food systems, and communities worldwide.

The full study was published in the journal Computers and Electronics in Agriculture.

—–

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates. 

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

—–