— Invited Review — Computer vision in precision livestock farming: artificial intelligence-driven technologies and applications for sustainable animal production

The growing global demand for animal-derived food products is placing unprecedented pressure on livestock production systems to improve efficiency while also assuring animal welfare, environmental sustainability and economic viability. Precision livestock farming (PLF) has emerged as a transformative paradigm that integrates advanced sensing technologies, computer vision, internet of things infrastructures and artificial intelligence (AI) to enable continuous, automated and individualized animal monitoring. This paper explores the evolution of livestock management from conventional observationbased practices to sophisticated, data-driven architecture. It also synthesizes recent advancements in PLF emphasizing its system architecture, key applications in cattle production, cross-sector expansion and emerging challenges. The core architecture of PLF is structured into three functional layers: (i) data acquisition through multi-modal sensors, with a primary emphasis in this review on visual and environmental monitoring system; (ii) data analytics employing machine learning and deep learning techniques to establish behavioral and physiological baselines; and (iii) decision-support mechanisms that translate analytics into actionable farm management interventions. Major applications, including individual animal identification, body condition score estimation, lameness detection, calving time prediction and AI-powered health monitoring, are critically discussed. The extension of PLF principles to aquaculture and other livestock sectors is also discussed. By shifting from herd-level to individual-animal management, PLF provides a scalable, noninvasive approach for early disease detection, optimized resource utilization, improved welfare standards and long-term economic sustainability. The current limitations, including high capital investment, data interoperability challenges and model generalizability constraints, have been analyzed and future research directions emphasizing explainable AI and welfare-oriented system design have been proposed. Overall, PLF represents a systemic transformation of animal agriculture, allowing for data-driven, sustainable and welfarecentered production systems.