Yong Cao’s research while affiliated with Southwest Forestry University and other places

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 (AP) of 82.3, APs of 75.3 for small, APm of 70.9 for medium, and APl 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%.

With the in-depth reform of education, deep learning is gradually being applied to education, which can stimulate students’ initiative in learning and improve their learning efficiency. This article explores some specific applications of deep learning in education, uses the deep learning model LSTM to predict students’ learning abilities and outcomes, and obtains high accuracy. Through deep learning models, we have abstracted the characteristics of students’ learning states and made relatively accurate predictions on their learning outcomes. This paper provides some useful explorations on the application of artificial intelligence and deep learning in education, which can provide valuable references for better research in the future.

Introduction Dendrolimus punctatus, a major pest endemic to the native Pinus massoniana forests in China, displays major outbreak characteristics and causes severe destructiveness. In the context of global climate change, this study aims to investigate the effects of climatic variations on the distribution of D. punctatus and its host, P. massoniana. Methods We predict their potential suitable distribution areas in the future, thereby offering a theoretical basis for monitoring and controlling D. punctatus, as well as conserving P. massoniana forest resources. By utilizing existing distribution data on D. punctatus and P. massoniana, coupled with relevant climatic variables, this study employs an optimized maximum entropy (MaxEnt) model for predictions. With feature combinations set as linear and product (LP) and the regularization multiplier at 0.1, the model strikes an optimal balance between complexity and accuracy. Results The results indicate that the primary climatic factors influencing the distribution of D. punctatus and P. massoniana include the minimum temperature of the coldest month, annual temperature range, and annual precipitation. Under the influence of climate change, the distribution areas of P. massoniana and its pests exhibit a high degree of similarity, primarily concentrated in the region south of the Qinling−Huaihe line in China. In various climate scenarios, the suitable habitat areas for these two species may expand to varying degrees, exhibiting a tendency to shift toward higher latitude regions. Particularly under the high emission scenario (SSP5-8.5), D. punctatus is projected to expand northwards at the fastest rate. Discussion By 2050, its migration direction is expected to closely align with that of P. massoniana, indicating that the pine forests will continue to be affected by the pest. These findings provide crucial empirical references for region-specific prevention of D. punctatus infestations and for the rational utilization and management of P. massoniana resources.

The Dendrolimus houi, a phytophagous pest, displays a broad range of adaptations and often inflicts localized damage to its hosts. Cupressus funebris, an indigenous timber species in China, is significantly impacted by D. houi. Investigating the suitable habitat distribution and changes in D. houi and its host plant, C. funebris, within the context of climate warming, is essential for understanding D. houi’s development and providing novel insights for managing D. houi and conserving C. funebris resources. In this study, MaxEnt was employed to simulate the distribution of D. houi and its host plant, C. funebris, in their suitable habitats, evaluating the influence of environmental factors on their distribution and determining changes under a warming scenario. MaxEnt model parameters were adjusted using the Kuenm data package based on available distribution and climatic data. The minimum temperature of the coldest month emerged as the primary environmental factor influencing the distribution of a suitable habitat for D. houi and C. funebris, with a percentage contribution of environmental factors over 60%. There was a substantial similarity in the suitable habitat distributions of D. houi and C. funebris, with varying degrees of expansion in the total habitat area under different temporal and climatic scenarios. Intersection analysis results indicated that the 2041–2060 period, especially under low (SSP1-2.6) and high (SSP5-8.5) emission scenarios, is a critical phase for D. houi control. The habitat expansion of D. houi and C. funebris due to climate change was observed, with the distribution center of D. houi shifting northeast and that of C. funebris shifting northwest.

Wood logs need to be measured for size when passing through customs to verify their quantity and volume. Due to the large number of wood logs needs through customs, a fast and accurate measurement method is required. The traditional log measurement methods are inefficient, have significant errors in determining the long and short diameters of the wood, and are difficult to achieve fast measurements in complex wood stacking environments. We use a Mask R-CNN instance segmentation model to detect the contour of the wood log and employ a binocular stereo camera to measure the log diameter. A rotation search algorithm centered on the wood contour is proposed to find long and short diameters and to optimal log size according to the Chinese standard. The experiments show that the Mask R-CNN we trained obtains 0.796 average precision and 0.943 IOUmask, and the recognition rate of wood log ends reaches 98.2%. The average error of the short diameter of the measurement results is 5.7 mm, the average error of the long diameter is 7.19 mm, and the average error of the diameter of the wood is 5.3 mm.

Wood recognition is necessary for work in the wood trade activities. The advantage of the one-class wood classification method is more generalization, and it only needs positive samples and does not need negative samples in the training phase, so it is suitable for rare wood species inspection. This paper proposed an improved method based on the one-class support vector machine (OCSVM) for wood species recognition. It uses cross-section images acquired with a magnifying glass, which uses a pre-trained VGG16 model for feature extraction, a normal distribution test for key features filtering, and OCSVM to determine the wood species. The results showed that the approach achieved a mean recall of 0.842 for both positive and negative samples, which indicates this method has good performance for wood recognition. In a negative public dataset, the negative recall reached as high as 0.989, which showed that this method has good generalization.