Toward Robotic Weed Control: Detection of Nutsedge Weed in Bermudagrass Turf Using Inaccurate and Insufficient Training Data
Toward Robotic Weed Control: Detection of Nutsedge Weed in Bermudagrass Turf Using Inaccurate and Insufficient Training Data
复制标题
DOI：
10.1109/lra.2021.3098012
复制
发表时间：
2021-06
影响因子：
5.2
通讯作者：
Shuangyun Xie;Chengsong Hu;M. Bagavathiannan;Dezhen Song
中科院分区：
文献类型：
--
作者：
Shuangyun Xie;Chengsong Hu;M. Bagavathiannan;Dezhen Song
为了使机器人杂草控制，我们开发的算法来检测莎草杂草从狗牙根草坪。由于杂草和背景草皮之间的相似性，手动数据标记是昂贵的并且容易出错。因此，直接将深度学习方法应用于对象检测无法产生令人满意的结果。基于实例检测方法（即Mask R-CNN），我们将联合收割机合成数据与原始数据相结合来训练网络。我们提出了一种算法来生成高保真度的合成数据，采用不同层次的注释，以减少标记成本。此外，我们构建了一个基于莎草纸的概率图（NSPM）作为神经网络输入，以减少对逐像素精确标记的依赖。我们还修改了损失函数从交叉熵Kullback-Leibler分歧，以适应在标记过程中的不确定性。我们实现了所提出的算法，并将其与Faster R-CNN和Mask R-CNN进行了比较。结果表明，我们的设计可以有效地克服不精确和训练样本不足问题的影响，并显著优于Faster R-CNN，假阴性率仅为0.4%。特别是，与原始的Mask R-CNN方法相比，我们的方法还将标记时间减少了95%，同时实现了更好的性能。
To enable robotic weed control, we develop algorithms to detect nutsedge weed from bermudagrass turf. Due to the similarity between the weed and the background turf, manual data labeling is expensive and error-prone. Consequently, directly applying deep learning methods for object detection cannot generate satisfactory results. Building on an instance detection approach (i.e. Mask R-CNN), we combine synthetic data with raw data to train the network. We propose an algorithm to generate high fidelity synthetic data, adopting different levels of annotations to reduce labeling cost. Moreover, we construct a nutsedge skeleton-based probabilistic map (NSPM) as the neural network input to reduce the reliance on pixel-wise precise labeling. We also modify loss function from cross entropy to Kullback-Leibler divergence which accommodates uncertainty in the labeling process. We implement the proposed algorithm and compare it with both Faster R-CNN and Mask R-CNN. The results show that our design can effectively overcome the impact of imprecise and insufficient training sample issues and significantly outperform the Faster R-CNN counterpart with a false negative rate of only 0.4%. In particular, our approach also reduces labeling time by 95% while achieving better performance if comparing with the original Mask R-CNN approach.