Search

Aircraft type recognition has been researched deeply for plenty years on remote sensing and radar signal processing fields because of military needs. However, with the rapid development of UAV visualization technology in recent years, the advanced optical sensors on high-altitude drones are able to capture high-definition aircraft images of various aircraft flight postures, which brings aircraft type recognition into a brand-new research field. Different from remote sensing images, images with aircrafts in flight have larger intra-class difference caused by flight posture variation, which is 3D-view and more challenging for aircraft type recognition. Facing the new challenges, we propose a aircraft type recognition framework in 3D-view optical images. The framework consists of two stages: a coarse stage for aircraft contour segmentation and a fine stage for aircraft contour template matching. At the coarse stage, we propose a instance segmentation network CP-Deepsnake with a novel loss function CP loss which improves the accuracy of extracted aircraft contours by supervising the global distribution of contour points during contour deformation. At the fine stage, we utilize contour template matching to realize aircraft type recognition in 3D-view images. Based on IDSC contour feature descriptor, we propose a fast contour template matching approach with a new matching evaluation criterion and establish an aircraft contour template database for aircraft contour template matching. To train and test our aircraft type recognition framework, we build two datasets with 3D-view aircraft images of 10 aircraft types. Experiments show that our method achieves considerable recognition accuracy on the aircraft type testing dataset. Besides, we evaluate the proposed CP-Deepsnake network on two challenging instance segmentation public datasets SBD and KINS, where it compares favorably against state-of-the-art methods, which means our CP-Deepsnake network can be extended to more instance segmentation sences like road pedestrian detection and vehicle detection. [ABSTRACT FROM AUTHOR]

Despite significant progress has been made in image and video deblurring, much less attention has been paid to process ultra high-definition (UHD) videos (e.g., 4K resolution). In this work, we propose a novel deep model for fast and accurate UHD video deblurring (UHDVD). The proposed UHDVD is achieved by a depth-wise separable-patch architecture, which operates with a multi-scale integration scheme to achieve a large receptive field without adding the number of generic convolutional layers and kernels. Additionally, we adopt the temporal feature attention module to effectively exploit the temporal correlation between video frames to obtain clearer recovered images. We design an asymmetrical encoder–decoder architecture with residual channel-spatial attention blocks to improve accuracy and reduce the depth of the network appropriately. Consequently, the proposed UHDVD achieves real-time performance on 4K videos at 30 fps. To train the proposed model, we build a new dataset comprised of 4K blurry videos and corresponding sharp frames using three different smartphones. Extensive experimental results show that our network performs favorably against the state-of-the-art methods on the proposed 4K dataset and existing 720p and 2K benchmarks in terms of accuracy, speed, and model size. [ABSTRACT FROM AUTHOR]

Conductive patterned metal films bonded to compliant elastomeric substrates form meshes which enable flexible electronic interconnects for various applications. However, while bottom-up deposition of thin films by sputtering or growth is well-developed for rigid electronics, maintaining good electrical conductivity in sub-micron thin metal films upon large deformations or cyclic loading remains a significant challenge. Here, we propose a strategy to improve the electromechanical performance of nanometer-thin palladium films by in-situ synthesis of a conformal graphene coating using chemical vapor deposition (CVD). The uniform graphene coverage improves the thin film's damage tolerance, electro-mechanical fatigue, and fracture toughness owing to the high stiffness of graphene and the conformal CVD-grown graphene-metal interface. Graphene-coated Pd thin film interconnects exhibit stable increase in electrical resistance even when strained beyond 60% and longer fatigue life up to a strain range of 20%. The effect of graphene is more significant for thinner films of < 300 nm, particularly at high strains. The experimental observations are well described by the thin film electro-fragmentation model and the Coffin-Manson relationship. These findings demonstrate the potential of CVD-grown graphene nanocomposite materials in improving the damage tolerance and electromechanical robustness of flexible electronics. The proposed approach offers opportunities for the development of reliable and high-performance ultra-conformable flexible electronic devices. [ABSTRACT FROM AUTHOR]

After Chemical Vapor Deposition (CVD), faceted structures are routinely observed on a variety of metal catalyst surfaces in the graphene-covered regions. In spite of having its bare surface flattened through high diffusivity and surface pre-melting at high temperatures, the graphene-covered copper surface still presents faceted structures. Using atomistic simulations, we show the role of graphene in the preservation of the faceted surface morphology at the graphene–copper interface, manifesting as a suppressant against surface melting and surface-specific diffusion. The results of our molecular dynamics simulations are consistent with our experimental observations and demonstrate the thermo-mechanical interfacial surface stabilization role of graphene. Our study provides an understanding applicable to most metal–graphene interfaces and is especially relevant to most metallic catalysts for graphene growth by CVD. Understanding the interaction between graphene and the catalyst surface structure is critical for producing ultra-flat and defect-free graphene. [ABSTRACT FROM AUTHOR]

Image deblurring is a classic problem in low-level computer vision with the aim to recover a sharp image from a blurred input image. Advances in deep learning have led to significant progress in solving this problem, and a large number of deblurring networks have been proposed. This paper presents a comprehensive and timely survey of recently published deep-learning based image deblurring approaches, aiming to serve the community as a useful literature review. We start by discussing common causes of image blur, introduce benchmark datasets and performance metrics, and summarize different problem formulations. Next, we present a taxonomy of methods using convolutional neural networks (CNN) based on architecture, loss function, and application, offering a detailed review and comparison. In addition, we discuss some domain-specific deblurring applications including face images, text, and stereo image pairs. We conclude by discussing key challenges and future research directions. [ABSTRACT FROM AUTHOR]

Rain is a common natural phenomenon. Taking images in the rain however often results in degraded quality of images, thus compromises the performance of many computer vision systems. Most existing de-rain algorithms use only one single input image and aim to recover a clean image. Few work has exploited stereo images. Moreover, even for single image based monocular deraining, many current methods fail to complete the task satisfactorily because they mostly rely on per pixel loss functions and ignore semantic information. In this paper, we present a Paired Rain Removal Network (PRRNet), which exploits both stereo images and semantic information. Specifically, we develop a Semantic-Aware Deraining Module (SADM) which solves both tasks of semantic segmentation and deraining of scenes, and a Semantic-Fusion Network (SFNet) and a View-Fusion Network (VFNet) which fuse semantic information and multi-view information respectively. In addition, we also introduce an Enhanced Paired Rain Removal Network (EPRRNet) which exploits semantic prior to remove rain streaks from stereo images. We first use a coarse deraining network to reduce the rain streaks on the input images, and then adopt a pre-trained semantic segmentation network to extract semantic features from the coarse derained image. Finally, a parallel stereo deraining network fuses semantic and multi-view information to restore finer results. We also propose new stereo based rainy datasets for benchmarking. Experiments on both monocular and the newly proposed stereo rainy datasets demonstrate that the proposed method achieves the state-of-the-art performance. https://github.com/HDCVLab/Stereo-Image-Deraining. [ABSTRACT FROM AUTHOR]

Although deep learning-based methods have dominated stereo matching leaderboards by yielding unprecedented disparity accuracy, their inference time is typically slow, i.e., less than 4 FPS for a pair of 540p images. The main reason is that the leading methods employ time-consuming 3D convolutions applied to a 4D feature volume. A common way to speed up the computation is to downsample the feature volume, but this loses high-frequency details. To overcome these challenges, we propose a displacement-invariant cost computation module to compute the matching costs without needing a 4D feature volume. Rather, costs are computed by applying the same 2D convolution network on each disparity-shifted feature map pair independently. Unlike previous 2D convolution-based methods that simply perform context mapping between inputs and disparity maps, our proposed approach learns to match features between the two images. We also propose an entropy-based refinement strategy to refine the computed disparity map, which further improves the speed by avoiding the need to compute a second disparity map on the right image. Extensive experiments on standard datasets (SceneFlow, KITTI, ETH3D, and Middlebury) demonstrate that our method achieves competitive accuracy with much less inference time. On typical image sizes (e.g., 540 × 960 ), our method processes over 100 FPS on a desktop GPU, making our method suitable for time-critical applications such as autonomous driving. We also show that our approach generalizes well to unseen datasets, outperforming 4D-volumetric methods. We will release the source code to ensure the reproducibility. [ABSTRACT FROM AUTHOR]

Images captured in snowy days suffer from noticeable degradation of scene visibility, which degenerates the performance of current vision-based intelligent systems. Removing snow from images thus is an important topic in computer vision. In this paper, we propose a Deep Dense Multi-Scale Network (DDMSNet) for snow removal by exploiting semantic and depth priors. As images captured in outdoor often share similar scenes and their visibility varies with depth from camera, such semantic and depth information provides a strong prior for snowy image restoration. We incorporate the semantic and depth maps as input and learn the semantic-aware and geometry-aware representation to remove snow. In particular, we first create a coarse network to remove snow from the input images. Then, the coarsely desnowed images are fed into another network to obtain the semantic and depth labels. Finally, we design a DDMSNet to learn semantic-aware and geometry-aware representation via a self-attention mechanism to produce the final clean images. Experiments evaluated on public synthetic and real-world snowy images verify the superiority of the proposed method, offering better results both quantitatively and qualitatively. https://github.com/HDCVLab/Deep-Dense-Multi-scale-Network https://github.com/HDCVLab/Deep-Dense-Multi-scale-Network. [ABSTRACT FROM AUTHOR]

Automatic hand-drawn sketch recognition is an important task in computer vision. However, the vast majority of prior works focus on exploring the power of deep learning to achieve better accuracy on complete and clean sketch images, and thus fail to achieve satisfactory performance when applied to incomplete or destroyed sketch images. To address this problem, we first develop two datasets that contain different levels of scrawl and incomplete sketches. Then, we propose an angular-driven feedback restoration network (ADFRNet), which first detects the imperfect parts of a sketch and then refines them into high quality images, to boost the performance of sketch recognition. By introducing a novel “feedback restoration loop” to deliver information between the middle stages, the proposed model can improve the quality of generated sketch images while avoiding the extra memory cost associated with popular cascading generation schemes. In addition, we also employ a novel angular-based loss function to guide the refinement of sketch images and learn a powerful discriminator in the angular space. Extensive experiments conducted on the proposed imperfect sketch datasets demonstrate that the proposed model is able to efficiently improve the quality of sketch images and achieve superior performance over the current state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Camera shake or target movement often leads to undesired blur effects in videos captured by a hand-held camera. Despite significant efforts having been devoted to video-deblur research, two major challenges remain: 1) how to model the spatio-temporal characteristics across both the spatial domain (i.e., image plane) and the temporal domain (i.e., neighboring frames) and 2) how to restore sharp image details with respect to the conventionally adopted metric of pixel-wise errors. In this paper, to address the first challenge, we propose a deblurring network (DBLRNet) for spatial-temporal learning by applying a 3D convolution to both the spatial and temporal domains. Our DBLRNet is able to capture jointly spatial and temporal information encoded in neighboring frames, which directly contributes to the improved video deblur performance. To tackle the second challenge, we leverage the developed DBLRNet as a generator in the generative adversarial network (GAN) architecture and employ a content loss in addition to an adversarial loss for efficient adversarial training. The developed network, which we name as deblurring GAN, is tested on two standard benchmarks and achieves the state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Owing to the superior strength and atomic thickness of graphene, it can in theory reinforce metals beyond the usual rule of mixtures bounds by constraining dislocations motion and strain localization at the grain boundaries. This unusual enhancement relies on the graphene's ability to conform to and wrap metal grains. This study experimentally probes the limits of this behavior and investigates the role of interface in designing superior graphene composites. Free-standing nickel-multilayer graphene (Ni-MLG) nanomembranes are fabricated by in situ chemical vapor deposition. Using nanoindentation, elastic modulus (285.16 GPa), maximum stress (2.35 GPa), and toughness (1407.26 Jm−2) are measured, and these values exceed the rule of mixtures bounds. The multi-frequency atomic force microscopy (AFM) is used to spatially map the elastic properties and topography of the MLG on Ni grain boundaries. This emerging characterization reveals that effective reinforcement is achieved when graphene conforms and bridges the grain texture. Nanoindentation and AFM confirm that these mechanisms are ineffective in non-conformally attached Ni-MLG composites, which exhibit significantly weaker mechanical behavior. These results guide the design of effective graphene composites by highlighting the importance of nanoscale roughness and interfaces, and clearly demonstrate the superiority of composite processing routes based on in situ graphene synthesis. [ABSTRACT FROM AUTHOR]

One key challenging issue of facial expression recognition is to capture the dynamic variation of facial physical structure from videos. In this paper, we propose a part-based hierarchical bidirectional recurrent neural network (PHRNN) to analyze the facial expression information of temporal sequences. Our PHRNN models facial morphological variations and dynamical evolution of expressions, which is effective to extract “temporal features” based on facial landmarks (geometry information) from consecutive frames. Meanwhile, in order to complement the still appearance information, a multi-signal convolutional neural network (MSCNN) is proposed to extract “spatial features” from still frames. We use both recognition and verification signals as supervision to calculate different loss functions, which are helpful to increase the variations of different expressions and reduce the differences among identical expressions. This deep evolutional spatial-temporal network (composed of PHRNN and MSCNN) extracts the partial-whole, geometry-appearance, and dynamic-still information, effectively boosting the performance of facial expression recognition. Experimental results show that this method largely outperforms the state-of-the-art ones. On three widely used facial expression databases (CK+, Oulu-CASIA, and MMI), our method reduces the error rates of the previous best ones by 45.5%, 25.8%, and 24.4%, respectively. [ABSTRACT FROM AUTHOR]

The skin of the cephalopod is a 3D display, where the papillae muscles control the protrusion of each voxel by several millimeters out of the skin plane, create hierarchical textures, and collectively change the overall skin pattern in a fraction of a second. A material system capable of mimicking this response using electromechanical actuation of twisted spiral artificial muscles (TSAMs) is presented in this study. TSAMs leverage the mechanics of their twisted geometry to extend out of plane by 8 mm, corresponding to 2000% strain using a voltage of only 0.02 V mm−1. They are made of polymer fibers wrapped with a helical metal wire. These actuators are assembled on a stretchable skin with the required flexible electrical connections to form an array of digital texture voxels (DTVs). The DTV array produces arbitrary 3D surface patterns on‐demand, and provides opportunities to control hydrodynamic drag, camouflage, and haptic displays. [ABSTRACT FROM AUTHOR]

Gilding is the ancient process of coating intricate artifacts with precious metals. Fascinating Egyptian and Chinese sculptures, coated with <200 nm thin metal films by this process, have resisted corrosion, wear, and other environmental degradations for thousands of years. Here, 150 nm thin palladium leaves are enriched by doped with a single layer of graphene. Commercially available Pd leaves are uniquely suited for graphene synthesis by a highly dynamic chemical vapor deposition process. The Pd leaves made by high strain rate beating are stable at high synthesis temperature, resisting solid‐state dewetting owing to their extremely low grain triple junctions density (0.017 µm−1). Mathematical models of growth kinetics guide the development of extremely rapid synthesis conditions, resulting in the formation of high‐quality graphene on Pd in less than a minute, owing to the graphene grains growing twice as fast as copper‐catalyzed growth. The graphene monolayer on the leaf increases the effective surface modulus by 59% to 236 GPa. Uniaxial strain testing with Raman spectroscopy reveals the excellent crystallinity of graphene by probing the stress‐induced phonon shifts. This new material could open exciting opportunities in utilizing high‐quality 2D materials to coat large structures. Gilding is the ancient process of coating sculptures with ultrathin metal films to enrich them and protect them against corrosion and wear. In this study, commercial palladium leaves with 150 nm thickness are used as ultrathin catalyst for high‐quality monolayer graphene growth. The graphene‐Pd leaves show advantageous mechanical behaviors, which make them suitable for advanced gilding. [ABSTRACT FROM AUTHOR]