Applications of Computer Vision in Agriculture

Dear Colleagues,

Computer vision is currently becoming a cornerstone of precision agriculture, enabling scalable, non-destructive monitoring of crops, orchards, livestock, and farm environments. By converting imagery into actionable information, vision-based systems can support timely decisions across the production chain, from scouting and phenotyping to automation and postharvest quality assessment. Yet, agricultural scenes remain uniquely challenging due to changing illumination, complex backgrounds, occlusions, variable growth stages, and strong seasonal dependence. These challenges motivate continued advances in robust algorithms, sensing strategies, and deployable systems.

This Special Issue, “Applications of Computer Vision in Agriculture,” focuses on practical developments that bridge research innovation and real-world adoption. The scope covers imaging and sensing platforms (RGB, multispectral/hyperspectral, thermal, depth/LiDAR, ground, UAV, and fixed installations), core vision tasks (detection, segmentation, tracking, counting, classification, disease/pest recognition, phenotyping, and yield estimation), and integration with agricultural machinery and robotics. We welcome papers that emphasize reproducible pipelines, well-designed field experiments, and evaluation protocols that reflect operational constraints and generalization across cultivars, locations, and seasons.

This Special Issue supplements the existing literature by consolidating contributions that translate computer vision performance into precision agriculture outcomes: actionable prescriptions, decision support, and site-specific management at plant, row, and field scales. Beyond reporting accuracy, we encourage studies that demonstrate how vision outputs can be used to drive practical operations, such as variable-rate spraying, targeted thinning, selective harvesting, automated scouting, maturity and yield mapping, and early detection of disease, pests, or abiotic stress. We also welcome work that tackles the realities that determine field usability, including data efficiency and adaptability across seasons and cultivars (annotation strategy, semi-/self-supervised learning, domain adaptation), uncertainty-aware predictions that support risk-sensitive decisions, and deployment constraints such as latency, robustness, and maintainability on embedded platforms. By bringing together interdisciplinary advances from computer vision, agricultural engineering, and biological sciences, this Special Issue aims to accelerate the development of reliable, scalable vision tools that measurably improve efficiency, sustainability, and resilience in precision agriculture.

Dr. Yuzhen Lu
Dr. Xinyang Mu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. AgriEngineering is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.