Search

Mid-to-high altitude Unmanned Aerial Vehicle (UAV) imagery can provide important remote sensing information between satellite and low altitude platforms, and vehicle detection in mid-to-high altitude UAV images plays a crucial role in land monitoring and disaster relief. However, the high background complexity of images and limited pixels of objects challenge the performance of tiny vehicle detection. Traditional methods suffer from poor adaptation ability to complex backgrounds, while deep neural networks (DNNs) have inherent defects in feature extraction of tiny objects with finite pixels. To address the issue above, this paper puts forward a vehicle detection method combining the DNNs-based and traditional methods for mid-to-high altitude UAV images. We first employ the deep segmentation network to exploit the co-occurrence of the road and vehicles, then detect tiny vehicles based on visual attention mechanism with spatial-temporal constraint information. Experimental results show that the proposed method achieves effective detection of tiny vehicles in complex backgrounds. In addition, ablation experiments are performed to inspect the effectiveness of each component, and comparative experiments on tinier objects are carried out to prove the superior generalization performance of our method in detecting vehicles with a limited size of 5 × 5 pixels or less. [ABSTRACT FROM AUTHOR]

Deep learning has recently attracted much attention due to its excellent performance in processing audio, image, and video data. However, few studies are devoted to the field of automatic modulation classification (AMC). It is one of the most well-known research topics in communication signal recognition and remains challenging for traditional methods due to complex disturbance from other sources. This paper proposes a heterogeneous deep model fusion (HDMF) method to solve the problem in a unified framework. The contributions include the following: (1) a convolutional neural network (CNN) and long short-term memory (LSTM) are combined by two different ways without prior knowledge involved; (2) a large database, including eleven types of single-carrier modulation signals with various noises as well as a fading channel, is collected with various signal-to-noise ratios (SNRs) based on a real geographical environment; and (3) experimental results demonstrate that HDMF is very capable of coping with the AMC problem, and achieves much better performance when compared with the independent network. [ABSTRACT FROM AUTHOR]

aerial scene recognition. A novel superpixel-based feature is proposed in this study to characterize aerial image scenes. Then, based on the proposed feature, a scene recognition method of the Bag-of-Words model for aerial imaging is designed. The proposed superpixel-based feature that utilizes landform information establishes top-task superpixel extraction of landforms to bottom-task expression of feature vectors. This characterization technique comprises the following steps: simple linear iterative clustering based superpixel segmentation, adaptive filter bank construction, Lie group-based feature quantification, and visual saliency model-based feature weighting. Experiments of image scene recognition are carried out using real image data captured by an unmanned aerial vehicle (UAV). The recognition accuracy of the proposed superpixel-based feature is 95.1%, which is higher than those of scene recognition algorithms based on other local features. [ABSTRACT FROM AUTHOR]

Professional cleaning and safe social distance monitoring are often considered as demanding, time-consuming, repetitive, and labor-intensive tasks with the risk of getting exposed to the virus. Safe social distance monitoring and cleaning are emerging problems solved through robotics solutions. This research aims to develop a safe social distance surveillance system on an intra-reconfigurable robot with a multi-robot cleaning system for large population environments, like office buildings, hospitals, or shopping malls. We propose an adaptive multi-robot cleaning strategy based on zig-zag-based coverage path planning that works in synergy with the human interaction heat map generated by safe social distance monitoring systems. We further validate the proposed adaptive velocity model's efficiency for the multi-robot cleaning systems regarding time consumption and energy saved. The proposed method using sigmoid-based non-linear function has shown superior performance with 14.1 percent faster and energy consumption of 11.8 percent less than conventional cleaning methods. [ABSTRACT FROM AUTHOR]

Facial recognition has attracted more and more attention since the rapid growth of artificial intelligence (AI) techniques in recent years. However, most of the related works about facial reconstruction and recognition are mainly based on big data collection and image deep learning related algorithms. The data driven based AI approaches inevitably increase the computational complexity of CPU and usually highly count on GPU capacity. One of the typical issues of RGB-based facial recognition is its applicability in low light or dark environments. To solve this problem, this paper presents an effective procedure for facial reconstruction as well as facial recognition via using a depth sensor. For each testing candidate, the depth camera acquires a multi-view of its 3D point clouds. The point cloud sets are stitched for 3D model reconstruction by using the iterative closest point (ICP). Then, a segmentation procedure is designed to separate the model set into a body part and head part. Based on the segmented 3D face point clouds, certain facial features are then extracted for recognition scoring. Taking a single shot from the depth sensor, the point cloud data is going to register with other 3D face models to determine which is the best candidate the data belongs to. By using the proposed feature-based 3D facial similarity score algorithm, which composes of normal, curvature, and registration similarities between different point clouds, the person can be labeled correctly even in a dark environment. The proposed method is suitable for smart devices such as smart phones and smart pads with tiny depth camera equipped. Experiments with real-world data show that the proposed method is able to reconstruct denser models and achieve point cloud-based 3D face recognition. [ABSTRACT FROM AUTHOR]

Recently, drone shows have impressed many people through a convergence of technology and art. However, these demonstrations have limited operating hours based on the battery life. Thus, it is important to minimize the unnecessary transition time between scenes without collision to increase operating time. This paper proposes a fast and energy-efficient scene transition algorithm that minimizes the transition times between scenes. This algorithm reduces the maximum drone movement distance to increase the operating time and exploits a multilayer method to avoid collisions between drones. In addition, a swarming flight system including robust communication and position estimation is presented as a concrete experimental system. The proposed algorithm was verified using the swarming flight system at a drone show performed with 100 drones. [ABSTRACT FROM AUTHOR]