YOLOMuskmelon: Quest for Fruit Detection Speed and Accuracy Using Deep Learning
YOLOMuskmelon: Quest for Fruit Detection Speed and Accuracy Using Deep Learning
复制标题
DOI：
10.1109/access.2021.3053167
复制
发表时间：
2021-01-01
期刊：
影响因子：
3.9
通讯作者：
Lawal, Olarewaju M.
中科院分区：
文献类型：
--
作者：
Lawal, Olarewaju M.
水果检测在收获机器人平台中起着至关重要的作用。然而，复杂的环境属性，如光照变化，遮挡，使水果检测是一个具有挑战性的任务。针对检测困难的问题，提出了一种准确、快速的鲁棒YOLOMuskmelon模型. YOLOMuskmelon模型将ReLU激活的ResNet 43骨干与新的2，3，4，3，2残差块排列、空间金字塔池化（SPP）、完全交集（CIoU）损失、特征金字塔网络（FPN）和距离交集非最大值抑制（DIoU-NMS）结合起来，以提高检测性能。获得的YOLOMuskmelon平均精确度（AP）结果为89.6%，高于YOLOv 3的82.3%、YOLOResNet 50的85.5%，但低于YOLOv 4的91.6%。然而，YOLOMuskmelon在96.3帧每秒（fps）的检测速度优于YOLOv 3的56.6fps，YOLOv 4的54.1fps和YOLOResNet 50的71.2fps。同时，与YOLOv 4模型相比，YOLOv 4模型的速度提高了56.1%，显示出更好的泛化性和实时性，为水果采摘机器人的开发提供了前景。
Fruit detection plays a vital role in harvesting robot platforms. However, complicated environment attributes such as illumination variation, occlusion, have made fruit detection a challenging task. A robust YOLOMuskmelon model that is accurate and fast was proposed to solve detection difficulties. The YOLOMuskmelon model incorporated ReLU activated ResNet43 backbone with new 2,3,4,3,2 residual block arrangement, spatial pyramid pooling(SPP), complete Intersection over Union (CIoU) loss, feature pyramid network(FPN), and distance Intersection over Union-Non Maximum Suppression(DIoU-NMS) to improve detection performance. The obtained average precision (AP) results of YOLOMuskmelon at 89.6% is greater than YOLOv3 at 82.3%, YOLOResNet50 at 85.5%, but less than YOLOv4 at 91.6%. However, the detection speed of YOLOMuskmelon at 96.3 frame per second(fps) outperformed YOLOv3 at 56.6fps, YOLOv4 at 54.1fps and YOLOResNet50 at 71.2fps. Meanwhile, the YOLOMuskmelon which is 56.1% faster than YOLOv4 model showed a better generalization and real-time fruit harvesting robots prospect.