Evaluating the Single-Shot MultiBox Detector and YOLO Deep Learning Models for the Detection of Tomatoes in a Greenhouse.
Evaluating the Single-Shot MultiBox Detector and YOLO Deep Learning Models for the Detection of Tomatoes in a Greenhouse.
复制标题
DOI：
10.3390/s21103569
复制
发表时间：
2021-05-20
期刊：
影响因子：
--
通讯作者：
Moreira AP
中科院分区：
文献类型：
--
作者：
Magalhães SA;Castro L;Moreira G;Dos Santos FN;Cunha M;Dias J;Moreira AP
农业机器人解决方案的开发需要先进的感知能力，可以在任何作物阶段可靠地工作。例如，为了使温室中的番茄收获过程自动化，视觉感知系统需要检测处于任何生命周期阶段（开花到成熟的番茄）的番茄。视觉番茄检测的最新技术主要集中在成熟的番茄上，成熟的番茄具有与背景不同的颜色。本文提供了一个带注释的绿色和红色番茄的视觉数据集。这种数据集并不常见，也不可用于研究目的。这将使边缘人工智能的进一步发展，用于开发收获机器人所需的现场和实时视觉番茄检测。考虑到这个数据集，我们选择了五个深度学习模型，进行了训练和基准测试，以检测温室中种植的绿色和红色番茄。考虑到我们的机器人平台规格，仅考虑了单次多盒检测器（SSD）和YOLO架构。实验结果表明，该系统可以检测出绿色和红色的番茄，甚至可以检测出被树叶遮挡的番茄。与SSD Inception v2、SSD ResNet 50、SSD ResNet 101和YOLOv4 Tiny相比，SSD MobileNet v2具有最佳性能，F1得分为%，mAP为%，推理时间为 搭载NVIDIA Turing Architecture平台，NVIDIA Tesla T4，12 GB。YOLOv4 Tiny也有令人印象深刻的结果，主要是关于推断时间约为5。
The development of robotic solutions for agriculture requires advanced perception capabilities that can work reliably in any crop stage. For example, to automatise the tomato harvesting process in greenhouses, the visual perception system needs to detect the tomato in any life cycle stage (flower to the ripe tomato). The state-of-the-art for visual tomato detection focuses mainly on ripe tomato, which has a distinctive colour from the background. This paper contributes with an annotated visual dataset of green and reddish tomatoes. This kind of dataset is uncommon and not available for research purposes. This will enable further developments in edge artificial intelligence for in situ and in real-time visual tomato detection required for the development of harvesting robots. Considering this dataset, five deep learning models were selected, trained and benchmarked to detect green and reddish tomatoes grown in greenhouses. Considering our robotic platform specifications, only the Single-Shot MultiBox Detector (SSD) and YOLO architectures were considered. The results proved that the system can detect green and reddish tomatoes, even those occluded by leaves. SSD MobileNet v2 had the best performance when compared against SSD Inception v2, SSD ResNet 50, SSD ResNet 101 and YOLOv4 Tiny, reaching an F1-score of %, an mAP of % and an inference time of with the NVIDIA Turing Architecture platform, an NVIDIA Tesla T4, with 12 GB. YOLOv4 Tiny also had impressive results, mainly concerning inferring times of about 5 .
登录
查看更多内容
影响因子：
19.5
作者：
Kuznetsova, Alina;Rom, Hassan;Ferrari, Vittorio
通讯作者：
Ferrari, Vittorio
影响因子：
0.8
作者：
de Luna, Robert G.;Dadios, Elmer P.;Vicerra, Ryan Rhay P.
通讯作者：
Vicerra, Ryan Rhay P.
影响因子：
2.7
作者：
Benavides, M.;Canton-Garbin, M.;Rodriguez, F.
通讯作者：
Rodriguez, F.
影响因子：
3.5
作者：
Bajesy, Ruzena;Aloimonos, Yiannis;Tsotsos, John K.
通讯作者：
Tsotsos, John K.
DOI：
10.1109/tpami.1986.4767851
发表时间：
1986-11-01
影响因子：
23.6
作者：
CANNY, J
通讯作者：
CANNY, J