Real Time Pear Fruit Detection and Counting Using YOLOv4 Models and Deep SORT.
Real Time Pear Fruit Detection and Counting Using YOLOv4 Models and Deep SORT.
复制标题
DOI：
10.3390/s21144803
复制
发表时间：
2021-07-14
期刊：
影响因子：
--
通讯作者：
Ahamed T
中科院分区：
文献类型：
--
作者：
Parico AIB;Ahamed T
本研究旨在仅使用RGB数据、最先进的对象检测模型YOLOv 4的变体和多对象跟踪算法Deep SORT为移动的应用程序生成一个强大的实时梨果实计数器。本研究也提供了一个系统和实用的方法，选择最合适的模型，在农业科学中的应用。在准确性方面，YOLOv 4-CSP被视为最佳模型，AP@0.50为98%。在速度和计算成本方面，YOLOv 4-tiny被认为是理想的模型，速度超过50 FPS，FLOPS为6.8-14.5。如果考虑准确性、速度和计算成本方面的平衡，YOLOv 4被发现是最合适的，并且具有最高的准确性度量，同时满足大于或等于24 FPS的真实的时间速度。在使用Deep SORT的两种计数方法中，发现唯一ID方法更可靠，F1计数为87.85%。这是因为YOLOv 4在检测梨果实时具有非常低的假阴性。ROI线更可靠，因为它的限制性更强，但由于检测中的闪烁，尽管检测到了一些梨，但它无法计数。
This study aimed to produce a robust real-time pear fruit counter for mobile applications using only RGB data, the variants of the state-of-the-art object detection model YOLOv4, and the multiple object-tracking algorithm Deep SORT. This study also provided a systematic and pragmatic methodology for choosing the most suitable model for a desired application in agricultural sciences. In terms of accuracy, YOLOv4-CSP was observed as the optimal model, with an AP@0.50 of 98%. In terms of speed and computational cost, YOLOv4-tiny was found to be the ideal model, with a speed of more than 50 FPS and FLOPS of 6.8–14.5. If considering the balance in terms of accuracy, speed and computational cost, YOLOv4 was found to be most suitable and had the highest accuracy metrics while satisfying a real time speed of greater than or equal to 24 FPS. Between the two methods of counting with Deep SORT, the unique ID method was found to be more reliable, with an F1count of 87.85%. This was because YOLOv4 had a very low false negative in detecting pear fruits. The ROI line is more reliable because of its more restrictive nature, but due to flickering in detection it was not able to count some pears despite their being detected.
登录
查看更多内容
影响因子：
3.9
作者：
Liu, Guoxu;Nouaze, Joseph Christian;Kim, Jae Ho
通讯作者：
Kim, Jae Ho
影响因子：
6
作者：
Gai, Rongli;Chen, Na;Yuan, Hai
通讯作者：
Yuan, Hai
影响因子：
8.1
作者：
Huang, Zhanchao;Wang, Jianlin;Wang, Rutong
通讯作者：
Wang, Rutong
影响因子：
4.2
作者：
Lee, YongJoo;Lee, Keon Myung;Lee, Sang Ho
通讯作者：
Lee, Sang Ho
影响因子：
4.6
作者：
Lawal MO
通讯作者：
Lawal MO