FSA-GhostNet: A Frequency–Spatial Adaptive Lightweight Network for Deployment-Oriented Crop Growth Monitoring

Timely assessment of crop growth is essential for greenhouse management because irrigation,nutrient supply, pruning, and harvest scheduling all depend on reliable informationon plant development. In practice, greenhouse imagery is affected by illumination variation,occlusion, and cluttered backgrounds, whereas deployment-oriented vision models mustremain compact enough for resource-constrained computing environments. To address thischallenge, FSA-GhostNet was developed as a lightweight visual backbone for greenhousecrop growth monitoring, and a Cucumber Growth Dataset (CGD) was constructed for densetemporal observation of cucumber development. The model was evaluated on ImageNet-100 and CGD under a unified protocol, and a joint learning setting was further used forsimultaneous growth-stage classification and continuous Days After Planting (DAP) regression.FSA-GhostNet achieved accuracies of 78.98% on ImageNet-100 and 98.22% onCGD with 2.07 million trainable parameters. Under a unified RTX 3060 runtime setting, themodel required 8.08 MB of storage, 0.868 G FLOPs, 13.96 ms/image latency, and 161.58 MBof peak GPU memory. In the joint prediction setting, it achieved 96.03% classificationaccuracy, a mean absolute error of 0.93 days, a root mean square error of 1.36 days, andan R2 score of 0.9962. These results show that FSA-GhostNet maintains a strong balancebetween predictive performance and compactness for greenhouse crop monitoring, whileCGD provides a useful temporal resource for fine-grained agricultural growth analysis.More broadly, the findings suggest that lightweight agricultural vision models can extendbeyond coarse stage recognition toward more continuous and agronomically meaningfulmonitoring of crop development.