Field imagery
Locate and count visible produce
Object detection and segmentation can locate fruit or other visible targets in images and video. Counts can help assess a workflow, but field estimates must account for occlusion, lighting, camera viewpoint, and sampling.
This apple detection clip is a demonstration, not a validated yield estimate. See the tomato and apple inference demos for Hailo HEF and ONNX comparisons; a production estimate requires validation against ground truth in the target crop and conditions.
Spectral analysis
Investigate differences beyond visible color
Multispectral and hyperspectral images can carry information useful for plant and produce assessment. In Vision Studio, inspect bands and signatures, annotate regions, and train spectral classifiers or regressors where labeled data supports the task.
Indices such as NDVI require the appropriate wavelength bands and metadata. Their relevance to a crop or condition should be tested with representative measurements. Explore the spectral workflow.
Produce inspection
Combine shape and spectral evidence
A pipeline can locate items in an RGB view, then use corresponding spectral crops to classify each detected object. This is a useful pattern to investigate for sorting or quality tasks when surface appearance alone is insufficient.
Studio demonstrates that pattern on a strawberries scene. The result does not establish grading accuracy on new produce or production throughput; those require a project-specific study.
Project discovery
What to prepare
Useful starting material includes sample images or scenes, sensor details and wavelengths, lighting conditions, labels or reference measurements, and the decision the system must make. These determine whether RGB, spectral imaging, or both are appropriate.
Bring your vision problem to us
Tell us about the images, sensor, operating environment, and decision you want the system to support. We can identify a practical first evaluation.