基于改进YOLO v3网络的夜间环境柑橘识别方法

Citrus Detection Method in Night Environment Based on Improved YOLO v3 Network

为研究夜间环境下采摘机器人的视觉检测技术,实现采摘机器人的夜间作业,提出了一种多尺度卷积神经网络Des-YOLO v3算法,可实现夜间复杂环境下成熟柑橘的识别与检测。借鉴残差网络和密集连接网络,设计了Des-YOLO v3网络结构,实现了网络多层特征的复用和融合,加强了小目标和重叠遮挡果实识别的鲁棒性,显著提高了果实检测精度。柑橘识别试验结果表明,Des-YOLO v3网络的精确率达97.67%、召回率为97.46%、F1值为0.976,分别比YOLO v3网络高6.26个百分点、6.36个百分点和0.063。同时,经过训练的模型在测试集下的平均精度(m AP)为90.75%、检测速度达53 f/s,高于YOLO v3_DarkNet53网络的平均精度88.48%,m AP比YOLO v3_Dark Net53网络提高了2.27个百分点,检测速度比YOLO v3_DarkNet53网络提高了11 f/s。研究结果表明,本文提出的Des-YOLO v3网络对野外夜间复杂环境下成熟柑橘的识别具有更强的鲁棒性和更高的检测精度,为柑橘采摘机器人的视觉识别提供了技术支持。

In China,citrus production occupies an important position in agriculture and has great economic benefit. For a long time,most of citrus harvesting relies on manual work,which has low efficiency and high labor cost. The labor cost accounts for almost one-half of total labor cost in citrus production process. In addition,citrus picking is usually carried out during the day,while makes less use of night time. Therefore,it is of great significance to develop a fruit picking robot working at nighttime. Focusing on citrus picking process,a multi-scale convolution neural network named DesYOLO v3 was proposed and used to detect citrus at nighttime under natural environment. By using ResNet and DenseNet for reference,the Des-YOLO v3 network was designed to realize the reuse and fusion of multi-layer features of the network,which strengthened the robustness of small target and overlapping occlusion fruit recognition,and significantly improved the precision of fruit detection. The experimental results showed that the precision,recall rate and F1 value of the Des-YOLO v3 network were 97. 67%,97. 46% and 0. 976,respectively,while those of YOLO v3 network were 91. 41%,91. 10% and 0. 913,respectively. At the same time,the mean average precision of the trained model under the test set was 90. 75%,and the detection speed was 53 f/s,which was 2. 27 percentage points and 11 f/s higher than those of YOLO v3_DarkNet53,respectively. The final results showed that the DesYOLO v3 recognition network had stronger robustness and higher detection precision for the recognition of mature citrus in the complex field environment at night,which provided technical support for the visual recognition of citrus picking robot.