Real-Time Detection and Instance Segmentation of Strawberry in Unstructured Environment

The real-time detection and instance segmentation of strawberries constitute fundamental components in the development of strawberry harvesting robots.Real-time identification of strawberries in an unstructured envi-ronment is a challenging task.Current instance segmentation algorithms for strawberries suffer from issues such as poor real-time performance and low accuracy.To this end,the present study proposes an Efficient YOLACT(E-YOLACT)algorithm for strawberry detection and segmentation based on the YOLACT framework.The key enhancements of the E-YOLACT encompass the development of a lightweight attention mechanism,pyramid squeeze shuffle attention(PSSA),for efficient feature extraction.Additionally,an attention-guided context-feature pyramid network(AC-FPN)is employed instead of FPN to optimize the architecture’s performance.Furthermore,a feature-enhanced model(FEM)is introduced to enhance the prediction head’s capabilities,while efficient fast non-maximum suppression(EF-NMS)is devised to improve non-maximum suppression.The experimental results demonstrate that the E-YOLACT achieves a Box-mAP and Mask-mAP of 77.9 and 76.6,respectively,on the custom dataset.Moreover,it exhibits an impressive category accuracy of 93.5%.Notably,the E-YOLACT also demonstrates a remarkable real-time detection capability with a speed of 34.8 FPS.The method proposed in this article presents an efficient approach for the vision system of a strawberry-picking robot.

Semi-liquid metal-based highly permeable and adhesive electronic skin inspired by spider web

Soft and stretchable electronics have garnered significant attention in various fields, such as wearable electronics, electronic skins, and soft robotics. However, current wearable electronics made from materials like conductive elastomers, hydrogels, and liquid metals face limitations, including low permeability, poor adhesion, inadequate conductivity, and limited stretchability. These issues hinder their effectiveness in long-term healthcare monitoring and exercise monitoring. To address these challenges,we introduce a novel design of web-droplet-like electronics featuring a semi-liquid metal coating for wearable applications. This innovative design offers high permeability, excellent stretchability, strong adhesion, and good conductivity for the electronic skin. The unique structure, inspired by the architecture of a spider web, significantly enhances air permeability compared to commercial breathable patches.Furthermore, the distribution of polyborosiloxane mimics the adhesive properties of spider web mucus,while the use of semi-liquid metals in this design results in remarkable conductivity(9 × 10^(6)S/m) and tensile performance(up to 850% strain). This advanced electronic skin technology enables long-term monitoring of various physiological parameters and supports machine learning recognition functions with unparalleled advantages. This web-droplet structure design strategy holds great promise for commercial applications in medical health monitoring and disease diagnosis.