School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China.
Sensors (Basel). 2022 Jun 22;22(13):4704. doi: 10.3390/s22134704.
Pine wilt nematode disease is a devastating forest disease that spreads rapidly. Using drone remote sensing to monitor pine wilt nematode trees promptly is an effective way to control the spread of pine wilt nematode disease. In this study, the YOLOv4 algorithm was used to automatically identify abnormally discolored wilt from pine wilt nematode disease on UAV remote sensing images. Because the network structure of YOLOv4 is too complex, although the detection accuracy is high, the detection speed is relatively low. To solve this problem, the lightweight deep learning network MobileNetv2 is used to optimize the backbone feature extraction network. Furthermore, the YOLOv4 algorithm was improved by improving the backbone network part, adding CBAM attention, and adding the Inceptionv2 structure to reduce the number of model parameters and improve the accuracy and efficiency of identification. The speed and accuracy of the Faster R-CNN, YOLOv4, SSD, YOLOv5, and the improved MobileNetv2-YOLOv4 algorithm were compared, and the detection effects of the Faster R-CNN, YOLOv4, SSD, YOLOv5 and the improved MobileNetv2-YOLOv4 algorithm on trees with pine wilt nematode were analyzed. The experimental results show that the average precision of the improved MobileNetv2-YOLOv4 algorithm is 86.85%, the training time of each iteration cycle is 156 s, the parameter size is 39.23 MB, and the test time of a single image is 15 ms, which is better than Faster R-CNN, YOLOv4, and SSD, but comparable to YOLOv5. Compared with the advantages and disadvantages, comprehensively comparing these four indicators, the improved algorithm has a more balanced performance in the detection speed, the parameter size, and the average precision. The F1 score of the improved algorithm (95.60%) was higher than that of Faster R-CNN (90.80%), YOLOv4 (94.56%), and SSD (92.14%), which met the monitoring requirements of pine wilt nematode trees. Faster R-CNN and SSD pine-wilt-nematode tree detection models are not ideal in practical applications. Compared with the YOLOv4 pine-wilt-nematode tree detection model, the improved MobileNetv2-YOLOv4 algorithm satisfies the condition of maintaining a lower model parameter quantity to obtain higher detection accuracy; therefore, it is more suitable for practical application scenarios of embedded devices. It can be used for the rapid detection of pine wilt nematode diseased trees.
松材线虫病是一种破坏性很强的森林病害，传播速度快。利用无人机遥感及时监测松材线虫病松树是控制松材线虫病传播的有效方法。本研究采用 YOLOv4 算法自动识别无人机遥感图像上由松材线虫病引起的异常变色萎蔫。由于 YOLOv4 网络结构过于复杂，虽然检测精度高，但检测速度相对较低。为解决这一问题，采用轻量化深度学习网络 MobileNetv2 对骨干特征提取网络进行优化。此外，通过改进骨干网络部分、添加 CBAM 注意力机制和添加 Inceptionv2 结构来减少模型参数数量，提高识别的准确性和效率，对 YOLOv4 算法进行了改进。比较了 Faster R-CNN、YOLOv4、SSD、YOLOv5 和改进的 MobileNetv2-YOLOv4 算法的速度和精度，并分析了 Faster R-CNN、YOLOv4、SSD、YOLOv5 和改进的 MobileNetv2-YOLOv4 算法对感染松材线虫的树木的检测效果。实验结果表明，改进的 MobileNetv2-YOLOv4 算法的平均精度为 86.85%，每个迭代周期的训练时间为 156s，参数大小为 39.23MB，单张图像的测试时间为 15ms，优于 Faster R-CNN、YOLOv4 和 SSD，但与 YOLOv5 相当。综合比较这四个指标的优缺点，改进算法在检测速度、参数大小和平均精度方面具有更均衡的性能。改进算法的 F1 得分（95.60%）高于 Faster R-CNN（90.80%）、YOLOv4（94.56%）和 SSD（92.14%），满足了松材线虫病监测的要求。Faster R-CNN 和 SSD 松材线虫树检测模型在实际应用中并不理想。与 YOLOv4 松材线虫树检测模型相比，改进的 MobileNetv2-YOLOv4 算法在保持较低模型参数数量的条件下，能够获得更高的检测精度，因此更适用于嵌入式设备的实际应用场景。可用于快速检测松材线虫病病树。
