Lotus seedpod maturity detection and segmentation in pond environments play a significant role in yield prediction and picking pose estimation for lotus seedpods. However, it is a great challenge to accurately detect and segment lotus seedpods due to insignificant phenotypic differences between the adjacent maturity, changing illumination, overlap, and occlusion of lotus seedpods. The existing research pays attention to lotus seedpod detection while ignoring maturity detection and segmentation problems. Therefore, a semantic segmentation dataset of lotus seedpods was created, where a copy-and-paste data augmentation tool was employed to eliminate the class-imbalanced problem and improve model generalization ability. Afterwards, an improved YOLOv8-seg model was proposed to detect and segment the maturity of lotus seedpods. In the model, the convolutional block attention module (CBAM) was embedded in the neck network to extract distinguished features of different maturity stages with negligible computation cost. Wise-Intersection over Union (WIoU) regression loss function was adopted to refine the regression inference bias and improve the bounding box prediction accuracy. The experimental results showed that the proposed YOLOv8-seg model provides an effective method for “ripe” and “overripe” lotus seedpod detection and instance segmentation, where the mean average precision of segmentation mask (${mAP}_{mask}$) reaches 97.4% and 98.6%, respectively. In addition, the improved YOLOv8-seg exhibits high robustness and adaptability to complex illumination in a challenging environment. Comparative experiments were conducted using the proposed YOLOv8-seg and other state-of-the-art instance segmentation methods. The results showed that the improved model is superior to the Mask R-CNN and YOLACT models, with recall, precision, ${mAP}_{box}$ and ${mAP}_{mask}$ being 96.5%, 94.3%, 97.8%, and 98%, respectively. The average running time and weight size of the proposed model are 25.9 ms and 7.4 M, respectively. The proposed model obtained the highest mAP for lotus seedpod maturity detection and segmentation while maintaining an appropriate model size and speed. Furthermore, based on the obtained segmentation model, 3D visualization of the lotus pond scene is performed, and cloud point of lotus seedpods is generated, which provides a theoretical foundation for robot harvesting in the lotus pond.

Thermoelectric generators are high-profile energy conversion devices that can convert heat energy into electricity. In this study, a novel 1D resistance model was established to evaluate the performance of a segmented thermoelectric generator (STEG) with variable properties, and the genetic algorithm was adopted to optimize the performance. Then, influence factor analysis, multi-parameter optimization, and sensitivity analysis for an STEG couple were conducted. The results showed the great influence of geometric sizes on performance. Moreover, the optimal length ratio between the length of the high-temperature segment and the total leg length increased when the temperature difference (ΔT) was raised, but it remained unchanged as the convective heat transfer coefficient (h) changed. Furthermore, the ratio of the leg length to its cross-sectional area is affected by thermal conditions and the length ratio, while the cross-sectional area ratio between P- and N-type thermoelectric legs was not affected by the convective heat transfer coefficient. Under the conditions of ΔT = 300 K and h = 2000 W/m²K, the maximum power increased by 11.02%. Finally, the global sensitivity analysis found that material properties, especially the Seebeck coefficient, dominate the influence on optimal power. These results could contribute to the optimal design of STEGs.