Maize seedling detection under different growth stages and complex field environments based on an improved Faster R–CNN

Quan, Longzhe; Feng, Huaiqu; Lv, Yingjie; Wang, Qi; Zhang, Chuanbin; Liu, Jingguo; Yuan, Zhonghua

doi:10.1016/j.biosystemseng.2019.05.002

Cited by 123 publications

(78 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the image is followed by five convolution-pooling activation layers. We adopted the default VGG19 network structure except the Max pooling layer of the fifth convolution, in order to keep more information in feature maps [16], as shown in Figure 5. In order to avoid overfitting by the network model, a regularization or dropout layer was added after each layer of the convolution-pooling layer [32].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…Recent developments in the application of the unmanned aerial vehicle (UAV) mounted with high definition cameras have increased the sample size tremendously [8][9][10]. Researchers have implemented many applications in plant height estimation [11][12][13], seedling counting [14][15][16], and crop growth estimation [17,18] using UAV images. Nevertheless, there are fewer applications of maize tassel detection using UAV images [19] which is challenging in natural environments due to light conditions, possible occlusions, and different maize genotypes.…”

Section: Introductionmentioning

confidence: 99%

“…Nevertheless, there are fewer applications of maize tassel detection using UAV images [19] which is challenging in natural environments due to light conditions, possible occlusions, and different maize genotypes. Deep learning algorithms have been widely used to count stem [20], seedling number [16], and wheat spike number [14]. Among networks in the Faster R-CNN [21] algorithm, Quan et al [16] conducted an experiment on the detection of maize seedling with different convolutional neural networks and confirmed that VGGNet [22] and ResNet [23] performed better than GoogleNet [24] and SqueezeeNet [25].…”

Section: Introductionmentioning

confidence: 99%

“…Deep learning algorithms have been widely used to count stem [20], seedling number [16], and wheat spike number [14]. Among networks in the Faster R-CNN [21] algorithm, Quan et al [16] conducted an experiment on the detection of maize seedling with different convolutional neural networks and confirmed that VGGNet [22] and ResNet [23] performed better than GoogleNet [24] and SqueezeeNet [25]. Kumar et al [19] confirmed that the Faster R-CNN algorithm performed better than You Only Look Once (YOLO) [26] for the detection of maize tassel with UAVs.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Detection of Maize Tassels from UAV RGB Imagery with Faster R-CNN

et al. 2020

View full text Add to dashboard Cite

Maize tassels play a critical role in plant growth and yield. Extensive RGB images obtained using unmanned aerial vehicle (UAV) and the prevalence of deep learning provide a chance to improve the accuracy of detecting maize tassels. We used images from UAV, a mobile phone, and the Maize Tassel Counting dataset (MTC) to test the performance of faster region-based convolutional neural network (Faster R-CNN) with residual neural network (ResNet) and a visual geometry group neural network (VGGNet). The results showed that the ResNet, as the feature extraction network, was better than the VGGNet for detecting maize tassels from UAV images with 600 × 600 resolution. The prediction accuracy ranged from 87.94% to 94.99%. However, the prediction accuracy was less than 87.27% from the UAV images with 5280 × 2970 resolution. We modified the anchor size to [852, 1282, 2562] in the region proposal network according to the width and height of pixel distribution to improve detection accuracy up to 89.96%. The accuracy reached up to 95.95% for mobile phone images. Then, we compared our trained model with TasselNet without training their datasets. The average difference of tassel number was 1.4 between the calculations with 40 images for the two methods. In the future, we could further improve the performance of the models by enlarging datasets and calculating other tassel traits such as the length, width, diameter, perimeter, and the branch number of the maize tassels.

show abstract

Section: Convolutional Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detection of Maize Tassels from UAV RGB Imagery with Faster R-CNN

et al. 2020

View full text Add to dashboard Cite

show abstract

“…A potential solution for this is the real-time object detection technique using the deep-learning methods such as RCNN, YOLO or SSD. [44][45][46] This can be integrated into the LATW system. The realtime object detection can also be used for realizing gap and overlap where the emission coefficient is changing.…”

Section: Process Improvementmentioning

confidence: 99%

Temperature variation during continuous laser-assisted adjacent hoop winding of type-IV pressure vessels: An experimental analysis

Zaami

Schäkel

Baran

et al. 2019

Journal of Composite Materials

View full text Add to dashboard Cite

Laser-assisted tape winding is an automated process to produce tubular or tube-like continuous fiber-reinforced polymer composites by winding a tape around a mandrel or liner. Placing additional layers on a previously heated substrate and variation in material and process parameters causes a variation in the bonding temperature of fiber-reinforced thermoplastic tapes which need to be understood and described well in order to have a reliable manufacturing process. In order to quantify the variation in this critical bonding temperature, a comprehensive temperature analysis of an adjacent hoop winding process of type-IV pressure vessels is performed. A total of five tanks are manufactured in which three glass/HDPE tapes are placed on an HDPE liner. The tape and substrate temperatures, roller force and tape feeding velocity are measured. The coefficient of variation for each round is characterized for the first time. According to the statistical analysis, the coefficient of variation in substrate temperature is found to be approximately 4.8–8.8% which is larger than the coefficient of variation of the tape temperature which is 2.1–7.8%. The coefficient of variations of the substrate temperatures in the third round decrease as compared with the coefficient of variations in the second round mainly due to the change in gap/overlap behavior of the deposited tapes. Fourier and thermographic analysis evince that the geometrical disturbances such as unroundness and eccentricity have a direct effect on the temperature variation. In addition to the temperature feedback control, a real-time object detection technique with deep learning algorithms can be used to mitigate the unwanted temperature variation and to have a more reliable thermal history.

show abstract

A novel deep learning‐based method for detection of weeds in vegetables

Xiao

Sun

Che

et al. 2022

Pest Management Science

View full text Add to dashboard Cite

BACKGROUND Precision weed control in vegetable fields can substantially reduce the required weed control inputs. Rapid and accurate weed detection in vegetable fields is a challenging task due to the presence of a wide variety of weed species at various growth stages and densities. This paper presents a novel deep‐learning‐based method for weed detection that recognizes vegetable crops and classifies all other green objects as weeds. RESULTS The optimal confidence threshold values for YOLO‐v3, CenterNet, and Faster R‐CNN were 0.4, 0.6, and 0.4/0.5, respectively. These deep‐learning models had average precision (AP) above 97% in the testing dataset. YOLO‐v3 was the most accurate model for detection of vegetables and yielded the highest F1 score of 0.971, along with high precision and recall values of 0.971 and 0.970, respectively. The inference time of YOLO‐v3 was similar to CenterNet, but significantly shorter than that of Faster R‐CNN. Overall, YOLO‐v3 showed the highest accuracy and computational efficiency among the deep‐learning architectures evaluated in this study. CONCLUSION These results demonstrate that deep‐learning‐based methods can reliably detect weeds in vegetable crops. The proposed method avoids dealing with various weed species, and thus greatly reduces the overall complexity of weed detection in vegetable fields. Findings have implications for advancing site‐specific robotic weed control in vegetable crops.

show abstract

Maize seedling detection under different growth stages and complex field environments based on an improved Faster R–CNN

Cited by 123 publications

References 21 publications

Detection of Maize Tassels from UAV RGB Imagery with Faster R-CNN

Detection of Maize Tassels from UAV RGB Imagery with Faster R-CNN

Temperature variation during continuous laser-assisted adjacent hoop winding of type-IV pressure vessels: An experimental analysis

A novel deep learning‐based method for detection of weeds in vegetables

Contact Info

Product

Resources

About