Individual Tree Detection in Coal Mine Afforestation Area Based on Improved Faster RCNN in UAV RGB Images

Abstract

Forests are the most important part of terrestrial ecosystems. In the context of China’s industrialization and urbanization, mining activities have caused huge damage to the forest ecology. In the Ulan Mulun River Basin (Ordos, China), afforestation is standard method for reclamation of coal mine degraded land. In order to understand, manage and utilize forests, it is necessary to collect local mining area’s tree information. This paper proposed an improved Faster R-CNN model to identify individual trees. There were three major improved parts in this model. First, the model applied supervised multi-policy data augmentation (DA) to address the unmanned aerial vehicle (UAV) sample label size imbalance phenomenon. Second, we proposed Dense Enhance Feature Pyramid Network (DE-FPN) to improve the detection accuracy of small sample. Third, we modified the state-of-the-art Alpha Intersection over Union (Alpha-IoU) loss function. In the regression stage, this part effectively improved the bounding box accuracy. Compared with the original model, the improved model had the faster effect and higher accuracy. The result shows that the data augmentation strategy increased AP by 1.26%, DE-FPN increased AP by 2.82%, and the improved Alpha-IoU increased AP by 2.60%. Compared with popular target detection algorithms, our improved Faster R-CNN algorithm had the highest accuracy for tree detection in mining areas. AP was 89.89%. It also had a good generalization, and it can accurately identify trees in a complex background. Our algorithm detected correct trees accounted for 91.61%. In the surrounding area of coal mines, the higher the stand density is, the smaller the remote sensing index value is. Remote sensing indices included Green Leaf Index (GLI), Red Green Blue Vegetation Index (RGBVI), Visible Atmospheric Resistance Index (VARI), and Normalized Green Red Difference Index (NGRDI). In the drone zone, the western area of Bulianta Coal Mine (Area A) had the highest stand density, which was 203.95 trees ha−1. GLI mean value was 0.09, RGBVI mean value was 0.17, VARI mean value was 0.04, and NGRDI mean value was 0.04. The southern area of Bulianta Coal Mine (Area D) was 105.09 trees ha−1 of stand density. Four remote sensing indices were all the highest. GLI mean value was 0.15, RGBVI mean value was 0.43, VARI mean value was 0.12, and NGRDI mean value was 0.09. This study provided a sustainable development theoretical guidance for the Ulan Mulun River Basin. It is crucial information for local ecological environment and economic development.

Mangrove Tree Density Detector using YOLO Based on Darknet Framework using RGB Drone Imagery

“…Luo et al [22] proposed using Faster R-CNN, a modified version of Convolutional Neural Network (CNN), to detect individual tree. The imagery data is gathered by the use of drone to capture images of the afforestation of the coal mine.…”

“…Environment monitoring also needs to be done frequently, which will increase the cost and time needed even more [8] [9]. [21] Yes No Ground 360°Cam No YOLOv2 Luo et al [22] Yes Yes RGB Drone No Faster R-CNN Donmez et al [23] Yes No RGB Drone No CCL Algorithm Mubin et al [24] Yes No RGB Sattelite No CNN LeNet Beloiu et al [25] Yes Yes Aerial Imagery No Faster R-CNN Pu et al [26] Yes Yes LiDAR Drone No LiDAR Analysis Jemaa et al [27] Yes No RGB Drone No YOLO Buonocore et al [29] No Based on the mentioned problems, in this research, we propose a system for mangrove density health system. In the era of emerging technology, there are more and more systems that can aid or replace human tasks for gathering data.…”

A Novel Wood Log Measurement Combined Mask R-CNN and Stereo Vision Camera

“…Wang transformed the point cloud map of rubber trees obtained from mobile LiDAR scanning into a depth map, used Faster R-CNN to segment them and detect the rubber trees, and obtained a segmentation accuracy of 98% [27]. Luo proposed an improved Faster R-CNN algorithm for tree detection in mining areas and obtained 89.89% AP and 91.61% accuracy in tree detection [28]. Lin proposed an improved YOLOv4-Tiny network and K-median clustering algorithm to detect bundled log ends, and precision, recall, and the F1-score reached 93.97%, 95.34%, and 0.95 respectively on the test set [29].…”

An InSAR Deformation Phase Retrieval Method Combined with Reference Phase in Mining Areas

“…The advent of Ddfferential InSAR (DInSAR) technology, introduced by Gabriel et al in 1989, marked the inception of InSAR-based surface deformation monitoring [4]. Furthermore, the utilization of unmanned aerial vehicles (UAV) in photogrammetry has given rise to a progressive surge in the monitoring of surface deformations within mining areas, affording a more realistic representation of surface deformation within regions characterized by pronounced deformation gradients [5,6]. In the context of mining subsidence prediction, the probability integration method (PIM) presently stands as one of China's most established and widely applied techniques [7].…”