Fast and accurate vehicle detection in unmanned aerial vehicle (UAV) imagery is a meaningful but challenging task, playing an important role in a wide range of applications. Due to its tiny size, few features, variable scales and imbalance vehicle sample problems in UAV imagery, current deep learning methods used in this task cannot achieve a satisfactory performance both in accuracy and speed, which is obvious a classical trade-off problem. In this paper, we propose a single-shot vehicle detector, which focuses on accurate and real-time vehicle detection in UAV imagery. We make contributions in the following two aspects: 1) presenting a multi-scale feature fusion module to combine the high resolution but semantically weak features with the low resolution but semantically strong features, aiming to introduce context information to enhance the feature representation of the small vehicles; 2) proposing a dynamic training strategy (DTS) which constructs the network to learn more discriminative features of hard examples, via using cross entropy and focal loss function alternately. Experimental results show that our method can achieve 90.8% accuracy in UAV images and can run at 59 FPS on a single NVIDIA 1080Ti GPU for the small vehicle detection in UAV images.

Dynamic Vision Sensor (DVS) is an event-based camera, which captures the changing pixel of vision. It captures the scene in the form of events. In this paper, we use a unique approach to visualize the events DVS captures with "DVS images". DVS is sensitive enough to capture objects moving in high speed, but noise is also captured. In order to improve the quality, we remove the noise of those images. Different from traditional images, the noise and objects in "DVS images" are both composed of distributed points. It is hard to use traditional methods to remove the noise. This paper proposes an efficient approach for "DVS image" noise removal. It is based on K-SVD algorithm and we improve the algorithm according to certain applications. The proposed framework can deal with "DVS images" containing different amount of noise. Experiments show that the proposed method can work well both on a fixed DVS and a moving DVS.

Vehicle detection based on unmanned aerial vehicle (UAV) images is a challenging task. One reason is that the objects are small size, low-resolution, and large scale variations, resulting in weak feature representation. Another reason is the imbalance between positive and negative examples. In this paper, we propose a novel architecture for UAV vehicle detection to solve above problems. In detail, we use anchor-free mechanism to eliminate predefined anchors, which can reduce complicated computation and relieve the imbalance between positive and negative samples. Meanwhile, to enhance the features for vehicles, we design a multi-scale semantic enhancement block (MSEB) and an effective 49-layer backbone which is based on the DetNet59. The proposed network offers appropriate receptive fields that match the small-sized vehicles, and involves precise localization information provided by the contexts with high resolution. The MSEB strengthens discriminative feature representation at various scales, without reducing the spatial resolution of prediction layers. Experiments show that the proposed method achieves the state-of-the-art performance. Particularly, the main part of vehicles, much smaller ones, the accuracy is about 2% higher than other existing methods.

UAV vehicle detection based on convolutional neural network exits a key problem of information imbalance of different feature layers. Shallow features have spatial information that is beneficial to localization, but lack semantic information. On the contrary, deep features have semantic information that is beneficial to classification, but lack spatial information. However, accurate classification and localization for UAV vehicle detection require both shallow spatial information and high semantic information. In our work, a bi-directional information guidance network (BDIG-Net) for UAV vehicle detection is proposed, which can ensure that each feature prediction layer has abundant mid-/low-level spatial information and high-level semantic information. There are two main parts in the BDIG-Net: shallow-level spatial information guidance part and deep-level semantic information guidance part. In the shallow-level guidance part, we design a feature transform module (FTM) to supply the mid-/low-level feature information, which can guide the BDIG-Net to enhance detailed and spatial features for deep features. Furthermore, we adopt a light-weight attention module (LAM) to reduce unnecessary shallow background information, making the network more focused on small-sized vehicles. In the deep-level guidance part, we use classical feature pyramid network to supply high-level semantic information, which can guide the BDIG-Net to enhance contextual information for shallow features. Meanwhile, we design a feature enhancement module (FEM) to suppress redundant features and improve the discriminability of vehicles. The proposed BDIG-Net can reduce the information imbalance. The experimental results show that the BDIG-Net can achieve accurate classification and localization for UAV vehicles and realize the real-time application requirements.