With fast software and hardware developments, vision intelligence models have attracted great attention and showed unprecedented performance on large-scale datasets. In practice, studies are still needed to design innovative intelligence models for niche applications with limited data accessibilities in uncertain real-world scenarios. This research casts light on cutting edge vision intelligent applications that enhance the essential areas of people’s livelihood, including food, agriculture, and healthcare. First, a 2D/3D imaging system was developed to facilitate the autonomous processing of Chesapeake Bay blue crabs, as an efficient solution to current hand-picking protocols. The system integrates a semantic segmentation model to understand crab 2D morphology. It can detect crab back-fin knuckles with R2 larger than 0.995, which guides movements of a two degree-of-freedom gantry station in removing crab legs and extracting crab body cores with 2mm accuracy. The customized active laser line scanning 3D range imaging system shows high imaging accuracy (0.15mm) and is able to assist a linear actuator in removing crab chamber cartilages. Second, computer aided vision intelligent methods were applied to an emerging ophthalmologic imaging modality known as, erythrocyte mediated angiography. A novel regression-based segmentation model and a Monte Carlo based tracking method were proposed to monitor the erythrocytes in stasis and in movements. Both models displayed comparable performance to human experts. Preliminary clinical results also manifest the potential relationships between paused erythrocyte densities and primary open-angle glaucoma. To better understand retinal vessel and erythrocyte distributions, a novel network architecture, the Hard Attention Net was proposed. This network has achieved state-of-art retinal vessel segmentation performance across different ophthalmologic imaging modalities. Finally, deep learning based qualitative and quantitative analyses were applied to spectral signals for monitoring high-level status and low-level chemical properties of agricultural bioproducts. Experiments include early-stage tomato spotted wilt virus detection as well as nutrition content estimation of plant and corn kernels. By using adversarial training and feature weighting ideas, the two proposed networks were effectively trained with a limited dataset. The results of these studies show great potential for vision intelligence models for promoting applications of advanced imaging modalities and vision-guided automations in food, agricultural, and healthcare fields.