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.

No abstract

Retrieval of relevant vectors produced by representation learning critically influences the efficiency in natural language processing (NLP) tasks. In this paper we demonstrate an efficient method for searching vectors via a typical nonmetric matching function: inner product. Our method, which constructs an approximate Inner Product Delaunay Graph (IPDG) for top-1 Maximum Inner Product Search (MIPS), transforms retrieving the most suitable latent vectors into a graph search problem with great benefits of efficiency. Experiments on data representations learned for different machine learning tasks verify the outperforming effectiveness and efficiency of the proposed IPDG.

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. INDEX TERMS Unmanned aerial vehicle, YOLOv3, object geolocation, moving vehicle tracking.

No abstract