SCSheng Chen

Sheng Chen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Sheng Chen has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Multi-Scenario Recognition and Detection Model in National Parks Based on Improved YOLOv8

    by Xiongwei Lou, Zixuan Qin, Hanbao Lou, Xinyu Zheng, Linhao Sun, Faneng Wang, Dasheng Wu, Sheng Chen, Guangyu Jiang

    With the advancement of unmanned aerial vehicle (UAV) technology, its use in ecological monitoring and safety management of national parks has expanded significantly. However, object detection in complex scenes remains challenging due to environmental complexity, background interference, and occlusion. To address these issues, this paper proposes two improved YOLOv8-based models, YOLOv8-StarNet-CGA and SCS-YOLOv8, for detecting pine wilt disease-infected trees, under-construction farmhouses, and forest fires. In YOLOv8-StarNet-CGA, the StarNet module and Content-Guided Attention (CGA) are integrated into the backbone to enhance global feature extraction and focus on critical regions through dynamic weight adjustment. In SCS-YOLOv8, the original CIoU loss is also replaced with SIoU loss to optimize shape and orientation consistency, improving robustness. Experiments on UAV datasets covering diverse national park scenes demonstrate the effectiveness of the models. Results show that the improved models substantially outperform the original YOLOv8 in Precision, Recall, and mAP50. For pine wilt disease caused by the pine wood nematode Bursaphelenchus xylophilus, YOLOv8-StarNet-CGA achieves 8.6% higher Precision and 11.7% higher mAP50, facilitating early diagnosis and intervention of the disease. In under-construction farmhouse scenarios, Precision rises by 11% and mAP50 by 10.1%, lowering annual inspection labor by nearly 30% and improving oversight. For forest fires, SCS-YOLOv8 is more effective, with Precision improved by 7.2% and mAP50 by 6.3%. The improved detection model enables earlier identification of fire spots, thereby providing additional response time for emergency intervention, helping to mitigate fire spread and reduce the loss of forest resources. Both models also reduce GFLOPs and computational complexity, striking a balance between efficiency and accuracy, and showing strong potential for UAV deployment.

  • Open Access

    Assessing Forest Quality through Forest Growth Potential, an Index Based on Improved CatBoost Machine Learning

    by Lianjun Cao, Xiaobing He, Sheng Chen, Luming Fang

    Human activities have always depended on nature, and forests are an important part of this; the determination and improvement of forest quality is therefore highly significant. Currently, domestic and foreign research on forest quality focuses on the current states of forests. We propose a new research direction based on the future states. By referencing and analyzing the forest quality standards of domestic and foreign experts and institutions, the concept and model for calculating forest growth potential were constructed. Forest growth potential is a new forest quality indicator. Based on the data of 110,000 subcompartments of forest resources from the Lin’an and Landsat8 satellites’ remote sensing data, the unit volume was predicted using three machine-learning algorithms: random gradient descent SGD, the integrated machine learning algorithm CatBoost, and deep learning CNN. The CatBoost algorithm model was improved based on Optuna; then the improved CatBoost algorithm was selected through evaluation indicators for the prediction of forest volume and finally incorporated into the calculation model for forest growth-potential value. The forest growth-potential value was calculated, and an accurate forest quality improvement scheme based on the subcompartments is preliminarily discussed. The successful calculation of forest growth potential values has a certain reference significance, providing guidance for accurately improving forest quality and forest management. The improved CatBoost calculation model is effective in the prediction of forest growth potential, and the determination coefficient R2 reaches 0.89, a value that compares favorably with those in other studies.


  • Open Access

    Tree Recognition and Crown Width Extraction Based on Novel Faster-RCNN in a Dense Loblolly Pine Environment

    by Chongyuan Cai, Hao Xu, Sheng Chen, Laibang Yang, Yuhui Weng, Siqi Huang, Chen Dong, Xiongwei Lou

    Tree crown width relates directly to wood quality and tree growth. The traditional method used to measure crown width is labor-intensive and time-consuming. Pairing imagery taken by an unmanned aerial vehicle (UAV) with a deep learning algorithm such as a faster region-based convolutional neural network (Faster-RCNN) has the potential to be an alternative to the traditional method. In this study, Faster-RCNN outperformed single-shot multibox detector (SSD) for crown detection in a young loblolly pine stand but performed poorly in a dense, mature loblolly pine stand. This paper proposes a novel Faster-RCNN algorithm for tree crown identification and crown width extraction in a forest stand environment with high-density loblolly pine forests. The new algorithm uses Residual Network 101 (ResNet101) and a feature pyramid network (FPN) to build an FPN_ResNet101 structure, improving the capability to model shallow location feature extraction. The algorithm was applied to images from a mature loblolly pine plot in eastern Texas, USA. The results show that the accuracy of crown recognition and crown width measurement using the FPN_ResNet101 structure as the backbone network in Faster-RCNN (FPN_Faster-RCNN_ResNet101) was high, being 95.26% and 0.95, respectively, which was 4.90% and 0.27 higher than when using Faster-RCNN with ResNet101 as the backbone network (Faster-RCNN_ResNet101). The results fully confirm the effectiveness of the proposed algorithm.