Search

Logs require multiple verifications to ensure accurate volume and quantity measurements. Log end detection is a crucial step in measuring log volume and counting logs. Currently, this task primarily relies on the Mask R-CNN instance segmentation model. However, the Feature Pyramid Network (FPN) in Mask R-CNN may compromise accuracy due to feature redundancy during multi-scale fusion, particularly with small objects. Moreover, counting logs in a single image is challenging due to their large size and stacking. To address the above issues, we propose an improved log segmentation model based on Cascade Mask R-CNN. This method uses ResNet for multi-scale feature extraction and integrates a hierarchical Convolutional Block Attention Module (CBAM) to refine feature weights and enhance object emphasis. Then, a Region Proposal Network (RPN) is employed to generate log segmentation proposals. Finally, combined with Deep SORT, the model tracks log ends in video streams and counts the number of logs in the stack. Experiments demonstrate the effectiveness of our method, achieving an average precision ( A P ) of 82.3, A P s of 75.3 for small, A P m of 70.9 for medium, and A P l of 86.2 for large objects. These results represent improvements of 1.8%, 3.7%, 2.6%, and 1.4% over Mask R-CNN, respectively. The detection rate reached 98.6%, with a counting accuracy of 95%. Compared to manually measured volumes, our method shows a low error rate of 4.07%. [ABSTRACT FROM AUTHOR]

Atypical porcine pestivirus (APPV) can cause congenital tremor type A-II in neonatal piglets, posing a significant threat to swine herd health globally. Our previous study demonstrated that the Mut domains, comprising 112 amino acids at the N-terminus, are the primary functional regions of the E2 protein of APPV. This study identified 14 host cellular proteins that exhibit potential interactions with the Mut domains of the E2 protein using yeast two-hybrid screening. Using bioinformatics analysis, we discovered that the Mut domains of the E2 protein might exert regulatory effects on apoptosis by modulating energy metabolism within the mitochondria. We also conducted co-immunoprecipitation, glutathione S-transferase pull-down, and immunofluorescence assays to confirm the interaction between the Mut domains of the E2 protein and cathepsin H and signal sequence receptor subunit 4 (SSR4). Ultimately, SSR4 enhanced APPV replication in vitro. In summary, our study successfully elucidated the interactions between the Mut domains of the E2 protein and host cell protein, predicted the potential pathways implicated in these interactions, and demonstrated SSR4 involvement in APPV infection. These significant findings contribute valuable knowledge toward a deeper understanding of APPV pathogenesis and the role of the Mut domains of the E2 protein in this intricate process. [ABSTRACT FROM AUTHOR]

Forest aboveground biomass (AGB) is an important research topic in the field of forestry, with implications for carbon cycles and carbon sinks. Malania oleifera Chun et S. K. Lee (M. oleifera) is a valuable plant species that is listed on the National Second-Class Protected Plant checklist and has received global attention for its conservation and resource utilization. To obtain accurate AGB of individual M. oleifera trees in a fast, low-finance-cost and low-labor-cost way, this study first attempted to estimate individual M. oleifera tree AGB by combining the centimeter-level resolution RGB imagery derived from unmanned aerial vehicles (UAVs) and the deep learning model of Mask R-CNN. Firstly, canopy area (CA) was obtained from the 3.5 cm high-resolution UAV-RGB imagery using the Mask R-CNN; secondly, to establish an allometric growth model between the diameter at breast height (DBH) and CA, the correlation analysis of both was conducted; thirdly, the AGB estimation method of individual M. oleifera trees was presented based on an empirical equation. The study showed that: (1) The deep learning model of Mask R-CNN achieved an average segmentation accuracy of 90% in the mixed forests to the extraction of the canopy of M. oleifera trees from UAV-RGB imagery. (2) The correlation between the extracted CA and field-measured DBH reached an R2 of 0.755 (n = 96). (3) The t-test method was used to verify the predicted and observed values of the CA-DBH model presented in this study, and the difference in deviation was not significant (p > 0.05). (4) AGB of individual M. oleifera was estimated for the first time. This study provides a reference method for the estimation of individual tree AGB of M. oleifera based on centimeter-level resolution UAV-RGB images and the Mask R-CNN deep learning. [ABSTRACT FROM AUTHOR]

Tomicus yunnanensis Kirkendall (Coleoptera: Scolytinae) is a stem-boring pest that endangers Pinus yunnanensis Franch (Pinales:Pinoideae), which seriously affects the ecological environment safety in southwest China. In order to understand the potential distribution pattern and change in the potential distribution of P. yunnanensis and T. yunnanensis, this study used the maximum entropy model to predict the distribution of potentially suitable areas for P. yunnanensis and T. yunnanensis and explored the relationships between their different spatiotemporal distributions based on change analysis. The experimental results show that altitude is the main factor restricting the current distribution of P. yunnanensis. The current suitable areas of P. yunnanensis are mainly distributed in Yunnan, Sichuan and Guizhou. The minimum temperature of the coldest month is the main factor affecting the current distribution of T. yunnanensis. The current suitable areas of T. yunnanensis are mainly distributed in Yunnan, Sichuan and Tibet. Under future climate scenarios, the total suitable areas of P. yunnanensis and T. yunnanensis are expected to increase. The suitable areas tend to move to higher altitudes in the west and higher latitudes in the north. At the same time, this study finds that there is an obvious bottleneck of expansion to northeastern Sichuan near the Daba Mountains. The results of intersection analysis showed that, with future climate change, P. yunnanensis and T. yunnanensis mainly showed lowly suitable (or unsuitable)—lowly suitable (or unsuitable) to moderately (or highly) suitable—and moderate (or high) variation patterns of suitable areas under the SSP1-2.6 climate scenario. These results will provide an important basis for the breeding of P. yunnanensis and controlling T. yunnanensis. [ABSTRACT FROM AUTHOR]

In order to solve the problem of wheel boundary fracture in Canny edge detection of wood end face scanning image, this paper proposes a growth ring image boundary repair algorithm. The algorithm is realized by connecting and repairing two adjacent broken wheel boundary regions whose longitudinal axis distance is less than threshold t1, and the extension repair is carried out for other fracture wheel boundary areas. In order to verify the effectiveness of the algorithm, this paper uses C# programming language to implement the algorithm. In the experiment, the edge detection results of the end face all have fracture growth ring boundaries, and the growth rings of Cunninghamia lanceolata, Calocedrus formosana, Sequoia sempervirens and Ilex chinensis with growth rings of 21, 104, 235 and 14 are selected. The experimental results show that the algorithm can accurately repair the growth ring boundary of the fracture and prepare for the accurate growth ring number in the later stage. [ABSTRACT FROM AUTHOR]

Hole transport in the p-type metal-oxide-semiconductor field-effect-transistor (p-MOSFET) inversion layer under arbitrary stress, surface, and channel orientation is investigated by employing a six-band k·p model and finite difference formalism. The piezoresistance coefficients are calculated and measured at stresses up to 300 MPa via wafer-bending experiments for stresses of technological importance: uniaxial and biaxial stresses on (001) and (110) surface oriented p-MOSFETs with <110> and <111> channels. With good agreement in the measured and calculated small stress piezoresistance coefficients, k·p calculations are used to give physical insights into hole mobility enhancement at large stress (∼3 GPa). The results show that the maximum hole mobility is similar for (001)/<110>, (110)/<110>, and (110)/<111> p-MOSFETs under uniaxial stress, although the enhancement factor is different. Strong quantum confinement and a low density of states cause less stress-induced mobility enhancement for (110) p-MOSFETs. For (001) p-MOSFETs, the dominant factor for the improved hole mobility is reduced conductivity effective mass at small stress and lower phonon scattering rate at large stress. [ABSTRACT FROM AUTHOR]