watersk

While picking robots aim to address this, the complex growth environment poses challenges in identifying and locating fruits due to factors like light and leaf occlusion. This study focuses on designing a recognition and localization method tailored to the natural growth conditions of melons and fruits, aiming to provide precise positional information for effective harvesting. Leveraging GTR-Net and binocular stereo vision, the proposed technology integrates a lightweight backbone network with Ghost bottleneck and TCSPG modules. The inclusion of TCSPRep and RepBlock modules enhances feature fusion, adapting to varying lighting conditions. To tackle occlusion challenges, the study introduces the RIoU loss function. Experimental validation using watermelons demonstrates GTR-Net's adaptability, achieving a remarkable mean Average Precision (mAP) of 91.7%. The model, with a compact 10.3MB size, attains a high detection speed of 106 frames per second (FPS), meeting real-time detection requirements. Our research enhances robot adaptability in complex environments, offering valuable insights for watermelon identification by mobile harvesting robots in challenging conditions.

在挑选机器人领域，旨在应对此问题，然而复杂的生长环境由于光线和叶片遮挡等因素，给水果的识别和定位带来了挑战。本研究聚焦于针对西瓜及水果的自然生长条件，设计了一种定制化的识别与定位方法，旨在提供精确的定位信息以实现高效的采摘。借助GTR-Net和双目立体视觉技术，所提出的技术集成了轻量级骨干网络，包括Ghost瓶颈和TCSPG模块。引入TCSPRep和RepBlock模块，进一步增强了特征融合，以适应多变的光照条件。为应对遮挡问题，本研究提出了RIoU损失函数。使用西瓜进行的实验验证了GTR-Net的适应性，实现了令人瞩目的平均精度均值（mAP）达到91.7%。该模型体积紧凑，仅为10.3MB，检测速度高达每秒106帧（FPS），满足了实时检测的需求。本研究提升了机器人在复杂环境中的适应性，为移动采摘机器人在恶劣条件下识别西瓜提供了宝贵的见解。