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.

With the progress of computer vision and the development of unmanned aerial vehicles (UAVs), UAVs have been widely used in forest resource investigation and tree feature extraction. In the field of crown width measurement, the use of traditional manual measurement methods is time-consuming and costly and affects factors such as terrain and weather. Although the crown width extraction method based on the segmentation of UAV images that have recently risen in popularity extracts a large amount of information, it consumes long amounts of time for dataset establishment and segmentation. This paper proposes an improved YOLOv7 model designed to precisely extract the crown width of Metasequoia glyptostroboides. This species is distinguished by its well-developed terminal buds and distinct central trunk morphology. Taking the M. glyptostroboides forest in the Qingshan Lake National Forest Park in Lin’an District, Hangzhou City, Zhejiang Province, China, as the target sample plot, YOLOv7 was improved using the simple, parameter-free attention model (SimAM) attention and SIoU modules. The SimAM attention module was experimentally proved capable of reducing the attention to other irrelevant information in the training process and improving the model’s accuracy. The SIoU module can improve the tightness between the detection frame and the edge of the target crown during the detection process and effectively enhance the accuracy of crown width measurement. The experimental results reveal that the improved model achieves 94.34% mAP@0.5 in the task of crown detection, which is 5% higher than that achieved by the original model. In crown width measurement, the R² of the improved model reaches 0.837, which is 0.151 higher than that of the original model, thus verifying the effectiveness of the improved algorithm.