An improved YOLOv5s model using feature concatenation with attention mechanism for real-time fruit detection and counting.
An improved YOLOv5s model using feature concatenation with attention mechanism for real-time fruit detection and counting.
复制标题
DOI：
10.3389/fpls.2023.1153505
复制
发表时间：
2023
影响因子：
5.6
通讯作者：
中科院分区：
文献类型：
--
作者：
为了解决复杂环境下的实时检测问题，提出了一种改进的YOLOv 5s模型，并在一个新的水果数据集上进行了验证。在原有的YOLOv 5s网络中加入了特征连接和注意力机制，改进后的YOLOv 5s网络记录了122层，4.4 × 106个参数，12.8 GFLOPs和8.8 MB的权重大小，分别比原来的YOLOv 5s网络小了45.5%，30.2%，14.1%和31.3%。同时，使用改进的YOLOv 5s模型在有效集上测试的mAP为93.4%，在测试集上测试的mAP为96.0%，在视频上测试的74 fps速度分别比原始YOLOv 5s模型提高了0.6%，0.5%和10.4%。使用视频，在改进的YOLOv 5s上测试的水果跟踪和计数与原始YOLOv 5s相比，观察到更少的遗漏和错误检测。此外，改进的YOLOv 5的聚合检测性能优于GhostYOLOv 5、YOLOv 4-tiny和YOLOv 7-tiny网络，包括其他主流YOLO变体。因此，改进的YOLOv 5s是轻量级的，降低了计算成本，可以更好地概括复杂的条件，并适用于水果采摘机器人和低功耗设备的实时检测。
An improved YOLOv5s model was proposed and validated on a new fruit dataset to solve the real-time detection task in a complex environment. With the incorporation of feature concatenation and an attention mechanism into the original YOLOv5s network, the improved YOLOv5s recorded 122 layers, 4.4 × 106 params, 12.8 GFLOPs, and 8.8 MB weight size, which are 45.5%, 30.2%, 14.1%, and 31.3% smaller than the original YOLOv5s, respectively. Meanwhile, the obtained 93.4% of mAP tested on the valid set, 96.0% of mAP tested on the test set, and 74 fps of speed tested on videos using improved YOLOv5s is 0.6%, 0.5%, and 10.4% higher than the original YOLOv5s model, respectively. Using videos, the fruit tracking and counting tested on the improved YOLOv5s observed less missed and incorrect detections compared to the original YOLOv5s. Furthermore, the aggregated detection performance of improved YOLOv5s outperformed the network of GhostYOLOv5s, YOLOv4-tiny, and YOLOv7-tiny, including other mainstream YOLO variants. Therefore, the improved YOLOv5s is lightweight with reduced computation costs, can better generalize against complex conditions, and is applicable for real-time detection in fruit picking robots and low-power devices.
登录
查看更多内容
影响因子：
3.6
作者：
Qiao, Yichen;Hu, Yaohua;Guo, Jiapan
通讯作者：
Guo, Jiapan
影响因子：
3.9
作者：
Liu, Guoxu;Nouaze, Joseph Christian;Kim, Jae Ho
通讯作者：
Kim, Jae Ho
DOI：
10.3390/s16081222
发表时间：
2016-08-03
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Sa I;Ge Z;Dayoub F;Upcroft B;Perez T;McCool C
通讯作者：
McCool C
影响因子：
3.9
作者：
Lawal, Olarewaju M.
通讯作者：
Lawal, Olarewaju M.
DOI：
10.3390/s21144803
发表时间：
2021-07-14
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Parico AIB;Ahamed T
通讯作者：
Ahamed T