Design of smart citrus picking model based on Mask RCNN and adaptive threshold segmentation

作者：Ziwei Guo, Yuanwu Shi, Ibrar Ahmad · 发表于：PeerJ Computer Science · 年份：2024 · DOI：10.7717/peerj-cs.1865 · 被引用次数：12 · 研究领域：Smart Agriculture and AI、Date Palm Research Studies、Spectroscopy and Chemometric Analyses

Smart agriculture is steadily progressing towards automation and heightened efficacy. The rapid ascent of deep learning technology provides a robust foundation for this trajectory. Leveraging computer vision and the depths of deep learning techniques enables real-time monitoring and management within agriculture, facilitating swift detection of plant growth and autonomous assessment of ripeness. In response to the demands of smart agriculture, this exposition delves into automated citrus harvesting, presenting an ATT-MRCNN target detection model that seamlessly integrates channel attention and spatial attention mechanisms for discerning and identifying citrus images. This framework commences by subjecting diverse citrus image classifications to Mask Region-based CNN's (Mask RCNN's) discerning scrutiny, enhancing the model's efficacy through the incorporation of attention mechanisms. During the model's training phase, transfer learning is utilized to expand data performance and optimize training efficiency, culminating in parameter initialization. Empirical results notably demonstrate that this method achieves a recognition rate surpassing the 95% threshold across the three sensory recognition tasks. This provides invaluable algorithmic support and essential guidance for the imminent era of intelligent harvesting.