Optical remote sensing (RS) data suffer from the limitation of bad weather and cloud contamination, whereas synthetic aperture radar (SAR) can work under all weather conditions and overcome this disadvantage of optical RS data. However, due to the imaging mechanism of SAR and the speckle noise, untrained people are difficult to recognize the land cover types visually from SAR images. Inspired by the excellent image-to-image translation performance of Generative Adversarial Networks (GANs), a supervised Cycle-Consistent Adversarial Network (S-CycleGAN) was proposed to generate large optical images from the SAR images. When the optical RS data are unavailable or partly unavailable, the generated optical images can be alternative data that aid in land cover visual recognition for untrained people. The main steps of SAR-to-optical image translation were as follows. First, the large SAR image was split to small patches. Then S-CycleGAN was used to translate the SAR patches to optical image patches. Finally, the optical image patches were stitched to generate the large optical image. A paired SAR-optical image dataset which covered 32 Chinese cities was published to evaluate the proposed method. The dataset was generated from Sentinel-1 (SEN-1) SAR images and Sentinel-2 (SEN-2) multi-spectral images. S-CycleGAN was applied to two experiments, which were SAR-to-optical image translation and cloud removal, and the results showed that S-CycleGAN could keep both the land cover and structure information well, and its performance was superior to some famous image-to-image translation models.

Convolutional neural networks (CNNs) have demonstrated their ability object detection of very high resolution remote sensing images. However, CNNs have obvious limitations for modeling geometric variations in remote sensing targets. In this paper, we introduced a CNN structure, namely deformable ConvNet, to address geometric modeling in object recognition. By adding offsets to the convolution layers, feature mapping of CNN can be applied to unfixed locations, enhancing CNNs’ visual appearance understanding. In our work, a deformable region-based fully convolutional networks (R-FCN) was constructed by substituting the regular convolution layer with a deformable convolution layer. To efficiently use this deformable convolutional neural network (ConvNet), a training mechanism is developed in our work. We first set the pre-trained R-FCN natural image model as the default network parameters in deformable R-FCN. Then, this deformable ConvNet was fine-tuned on very high resolution (VHR) remote sensing images. To remedy the increase in lines like false region proposals, we developed aspect ratio constrained non maximum suppression (arcNMS). The precision of deformable ConvNet for detecting objects was then improved. An end-to-end approach was then developed by combining deformable R-FCN, a smart fine-tuning strategy and aspect ratio constrained NMS. The developed method was better than a state-of-the-art benchmark in object detection without data augmentation.

Water-quality monitoring of inland lakes is essential for freshwater-resource protection. In situ water-quality measurements and ratings are accurate but high costs limit their usage. Water-quality monitoring using remote sensing has shown to be cost-effective. However, the nonoptically active parameters that mainly determine water-quality levels in China are difficult to estimate because of their weak optical characteristics and lack of explicit correlation between remote-sensing images and parameters. To address the problems, a convolutional neural network (CNN) with hierarchical structure was designed to represent the relationship between Landsat8 images and in situ water-quality levels. A transfer-learning strategy in the CNN model was introduced to deal with the lack of in situ measurement data. After the CNN model was trained by spatially and temporally matched Landsat8 images and in situ water-quality data that were collected from official websites, the surface quality of the whole water body could be classified. We tested the CNN model at the Erhai and Chaohu lakes in China, respectively. The experiment results demonstrate that the CNN model outperformed widely used machine-learning methods. The trained model at Erhai Lake can be used for the water-quality classification of Chaohu Lake. The introduced CNN model and the water-quality classification method could cover the whole lake with low costs. The proposed method has potential in inland-lake monitoring.

Unmanned aerial vehicles (UAVs) have been widely used in urban traffic supervision in recent years. However, the detection, tracking, and geolocation of moving vehicle based on the airborne platform suffer from small object sizes, complex scenes, and low-accuracy sensors. To address these problems, this paper develops a framework for moving vehicle detecting, tracking, and geolocating based on a monocular camera, a GPS receiver, and inertial measurement units (IMUs) sensors. First, the method based on YOLOv3 was employed for vehicle detection due to its effectiveness and efficiency for small object detection in complex scenes. Then, a visual tracking method based on correlation filters is introduced, and a passive geolocation method is presented to calculate the GPS coordinates of the moving vehicle. Finally, a flight control method in terms of the previous image processing results is introduced to lead the UAV that is following the interesting moving vehicle. The proposed scheme has been built on a DJI M100 platform on which a monocular camera and a microcomputer Jetson TX1 are added. The experimental results show that this scheme is capable of detecting, tracking, and geolocating the interesting moving vehicle with high precision. The framework demonstrates its capacity in automatic supervision on target vehicles in real-world experiments, which suggests its potential applications in urban traffic, logistics, and security.

A more accurate and timely rainfall prediction is needed for flood disaster reduction and prevention in Wuhan. The in situ microelectromechanical systems’ (MEMS) sensors can provide high time and spatial resolution of weather parameter measurement, but they suffer from stochastic measurement error. In order to apply MEMS sensors in real-time rainfall prediction in Wuhan, firstly, seasonal trend decomposition using Loess (STL) algorithm is utilized to decompose the observed time series into trend, seasonal, and remainder components. The trend of the observed series is compared with the corresponding trend of the data downloaded from the authoritative website with the same weather parameter in terms of Euclidean distance and cosine similarity. The similarity demonstrates that the observation of MEMS sensors is believable. Secondly, the long short-term memory (LSTM) is used to predict the real-time rainfall based on the observed data. Compared with autoregressive and moving average (ARMA), random forest (RF), support vector machine (SVM), and back propagation neural networks (BPNNs), LSTM not only performs as well as ARMA in real-time rainfall prediction but also outperforms the other four models in seasonal rainfall pattern description and seasonal real-time rainfall prediction. Our experiment results show that more detailed, timely, and accurate rainfall prediction can be achieved by using LSTM on the MEMS weather sensors.

Change detection (CD) is an essential earth observation technique. It captures the dynamic information of land objects. With the rise of deep learning, convolutional neural networks (CNN) have shown great potential in CD. However, current CNN models introduce backbone architectures that lose detailed information during learning. Moreover, current CNN models are heavy in parameters, which prevents their deployment on edge devices such as UAVs. In this work, we tackle this issue by proposing RDP-Net: a region detail preserving network for CD. We propose an efficient training strategy that constructs the training tasks during the warmup period of CNN training and lets the CNN learn from easy to hard. The training strategy enables CNN to learn more powerful features with fewer FLOPs and achieve better performance. Next, we propose an effective edge loss that increases the penalty for errors on details and improves the network’s attention to details such as boundary regions and small areas. Furthermore, we provide a CNN model with a brand new backbone that achieves the state-of-the-art empirical performance in CD with only 1.70M parameters. We hope our RDP-Net would benefit the practical CD applications on compact devices and could inspire more people to bring change detection to a new level with the efficient training strategy. The code and models are publicly available at https://github.com/Chnja/RDPNet.