Spike development directly affects the yield and quality of rice. We describe an algorithm for automatically identifying multiple developmental stages of rice spikes(AI-MDSRS) that transforms the automatic identificat...Spike development directly affects the yield and quality of rice. We describe an algorithm for automatically identifying multiple developmental stages of rice spikes(AI-MDSRS) that transforms the automatic identification of multiple developmental stages of rice spikes into the detection of rice spikes of diverse maturity levels. The scales vary greatly in different growth and development stages because rice spikes are dense and small, posing challenges for their effective and accurate detection. We describe a rice spike detection model based on an improved faster regions with convolutional neural network(Faster R-CNN).The model incorporates the following optimization strategies: first, Inception_Res Net-v2 replaces VGG16 as a feature extraction network;second, a feature pyramid network(FPN) replaces single-scale feature maps to fuse with region proposal network(RPN);third, region of interest(Ro I) alignment replaces Ro I pooling, and distance-intersection over union(DIo U) is used as a standard for non-maximum suppression(NMS). The performance of the proposed model was compared with that of the original Faster R-CNN and YOLOv4 models. The mean average precision(m AP) of the rice spike detection model was92.47%, a substantial improvement on the original Faster R-CNN model(with 40.96% m AP) and 3.4%higher than that of the YOLOv4 model, experimentally indicating that the model is more accurate and reliable. The identification results of the model for the heading–flowering, milky maturity, and full maturity stages were within two days of the results of manual observation, fully meeting the needs of agricultural activities.展开更多
In order to solve the problem of small objects detection in unmanned aerial vehicle(UAV)aerial images with complex background,a general detection method for multi-scale small objects based on Faster region-based convo...In order to solve the problem of small objects detection in unmanned aerial vehicle(UAV)aerial images with complex background,a general detection method for multi-scale small objects based on Faster region-based convolutional neural network(Faster R-CNN)is proposed.The bird’s nest on the high-voltage tower is taken as the research object.Firstly,we use the improved convolutional neural network ResNet101 to extract object features,and then use multi-scale sliding windows to obtain the object region proposals on the convolution feature maps with different resolutions.Finally,a deconvolution operation is added to further enhance the selected feature map with higher resolution,and then it taken as a feature mapping layer of the region proposals passing to the object detection sub-network.The detection results of the bird’s nest in UAV aerial images show that the proposed method can precisely detect small objects in aerial images.展开更多
This paper proposes a Faster R-CNN based detector for kiwi fruit detection. In order to alleviate the shortcomings of insufficient datasets and to avoid retraining a network for a long time, the idea of transfer learn...This paper proposes a Faster R-CNN based detector for kiwi fruit detection. In order to alleviate the shortcomings of insufficient datasets and to avoid retraining a network for a long time, the idea of transfer learning (Transfer learning) is used to train the kiwi dataset. Firstly, the kiwi data set in the natural environment was collected and prepared, and the different algorithms were compared with Faster R-CNN in the kiwi dataset. The experimental results also showed that Faster R-CNN is the best kiwi dataset for this paper. Different classification networks are then used as the backbone feature extraction networks for the Faster R-CNN algorithm. Finally, combined with the idea of transfer learning, the pre-trained model weights are first loaded on the COCO dataset, and then the training skills of Fine-tune are adopted to freeze the parameters of different parts of the model to train the kiwi dataset. The final experimental results show that the Faster R-CNN algorithm with backbone network VGG19 is better suitable on the kiwi dataset, and the detection accuracy is 2.69% higher than the original algorithm.展开更多
基金supported by the Key-Area Research and Development Program of Guangdong Province (2019B020214005)Agricultural Research Project and Agricultural Technology Promotion Project of Guangdong (2021KJ383)。
文摘Spike development directly affects the yield and quality of rice. We describe an algorithm for automatically identifying multiple developmental stages of rice spikes(AI-MDSRS) that transforms the automatic identification of multiple developmental stages of rice spikes into the detection of rice spikes of diverse maturity levels. The scales vary greatly in different growth and development stages because rice spikes are dense and small, posing challenges for their effective and accurate detection. We describe a rice spike detection model based on an improved faster regions with convolutional neural network(Faster R-CNN).The model incorporates the following optimization strategies: first, Inception_Res Net-v2 replaces VGG16 as a feature extraction network;second, a feature pyramid network(FPN) replaces single-scale feature maps to fuse with region proposal network(RPN);third, region of interest(Ro I) alignment replaces Ro I pooling, and distance-intersection over union(DIo U) is used as a standard for non-maximum suppression(NMS). The performance of the proposed model was compared with that of the original Faster R-CNN and YOLOv4 models. The mean average precision(m AP) of the rice spike detection model was92.47%, a substantial improvement on the original Faster R-CNN model(with 40.96% m AP) and 3.4%higher than that of the YOLOv4 model, experimentally indicating that the model is more accurate and reliable. The identification results of the model for the heading–flowering, milky maturity, and full maturity stages were within two days of the results of manual observation, fully meeting the needs of agricultural activities.
基金National Defense Pre-research Fund Project(No.KMGY318002531)。
文摘In order to solve the problem of small objects detection in unmanned aerial vehicle(UAV)aerial images with complex background,a general detection method for multi-scale small objects based on Faster region-based convolutional neural network(Faster R-CNN)is proposed.The bird’s nest on the high-voltage tower is taken as the research object.Firstly,we use the improved convolutional neural network ResNet101 to extract object features,and then use multi-scale sliding windows to obtain the object region proposals on the convolution feature maps with different resolutions.Finally,a deconvolution operation is added to further enhance the selected feature map with higher resolution,and then it taken as a feature mapping layer of the region proposals passing to the object detection sub-network.The detection results of the bird’s nest in UAV aerial images show that the proposed method can precisely detect small objects in aerial images.
文摘This paper proposes a Faster R-CNN based detector for kiwi fruit detection. In order to alleviate the shortcomings of insufficient datasets and to avoid retraining a network for a long time, the idea of transfer learning (Transfer learning) is used to train the kiwi dataset. Firstly, the kiwi data set in the natural environment was collected and prepared, and the different algorithms were compared with Faster R-CNN in the kiwi dataset. The experimental results also showed that Faster R-CNN is the best kiwi dataset for this paper. Different classification networks are then used as the backbone feature extraction networks for the Faster R-CNN algorithm. Finally, combined with the idea of transfer learning, the pre-trained model weights are first loaded on the COCO dataset, and then the training skills of Fine-tune are adopted to freeze the parameters of different parts of the model to train the kiwi dataset. The final experimental results show that the Faster R-CNN algorithm with backbone network VGG19 is better suitable on the kiwi dataset, and the detection accuracy is 2.69% higher than the original algorithm.
