Rice leaf disease (RLD) is one of the major factors that cause the decline in production, and the automatic recognition of such diseases under natural field conditions is of great significance for timely targeted rice management. Although many machine learning approaches have been proposed for RLD recognition, scale variation is still a challenging problem that affects prediction accuracy, especially in uncontrolled environments, such as natural fields. Also, the existing RLD data sets are collected in laboratory environments or with a constant scale, which cannot be used to develop the RLD classification algorithms under natural field conditions. To tackle these particular challenges, we propose a multiscale voting mechanism for RLD recognition under natural field conditions. First, data from 26 rice fields were collected to build a data set containing 6046 images of RLD. Afterwards, a feature pyramid was embedded into a mainstream classification architecture (EfficientNet) with a bottom-up and top-down pathway for feature fusion at different scales. To further reduce the inconsistency among multiscaled features, a multiscale voting strategy with regard to probability distribution was proposed to integrate the decisions from various scales. Each proposed module was carefully validated through an ablation study to demonstrate its effectiveness, and the proposed method was compared with a few state-of-the-art algorithms, including the Single Shot MultiBox Detector, Feature Pyramid Networks, Path Aggregation Network, and Bidirectional Feature Pyramid Network. Experimental results have shown that the classification accuracy of our model can reach 90.24%, which is 4.48% higher than that of the original EfficientNet-b0 model and 1.08% higher than that of existing multiscale networks. Finally, we exploit and demonstrate a visualized explanation for the boosted performance from the proposed model. As an extra outcome, our data set and codes are available at http://github.com/huanghsheng/multiscale-voting-mechanism to benefit the whole research community.

Color calibration is a critical step for Unmanned Aerial Vehicles (UAV) remote sensing, especially in precision agriculture, which relies mainly on correlating color changes to specific quality attributes, e.g., plant health, disease, and pest stresses. In UAV remote sensing, the exemplar-based color transfer is popularly used for color calibration, where the automatic search for the semantic correspondences is the key to ensuring the color transfer accuracy. However, the existing attention mechanisms encounter difficulties in building the precise semantic correspondences between the reference image and the target one, in which the normalized cross correlation is often computed for feature reassembling. As a result, the color transfer accuracy is inevitably decreased by the disturbance from the semantically unrelated pixels, leading to semantic mismatch due to the absence of semantic correspondences. In this paper, we proposed an unsupervised object-based attention mechanism (OBAM) to suppress the disturbance of the semantically unrelated pixels, along with a further introduced weight-adjusted AdaIN (WAA) method to tackle the challenges caused by the absence of semantic correspondences. By embedding the proposed modules into a photorealistic style transfer method with progressive stylization, the color transfer accuracy can be improved while better preserving the structural details. We evaluated our approach on the UAV data of different crop types including rice, beans, and cotton. Extensive experiments demonstrate that our proposed method outperforms several state-of-the-art methods. As our approach requires no annotated labels, it can be easily embedded into the off-the-shelf color transfer approaches. Relevant codes and configurations will be available at http://github.com/huanghsheng/object-based-attention-mechanism.