Due to the limited improvement of single-image based super-resolution (SR) methods in recent years, the reference based image SR (RefSR) methods, which super-resolve the low-resolution (LR) input with the guidance of similar high-resolution (HR) reference images are emerging. There are two main challenges in RefSR, i.e. reference image warping and exploring the guidance information from the warped references. For reference warping, we propose an efficient dense warping method to deal with large displacements, which is much faster than traditional patch (or texture) matching strategy. For the SR process, since different reference images complement each other, and have different similarities with the LR image, we further propose a similarity based feature fusion strategy to take advantage of the most similar reference regions. The SR process is realized by an encoder–decoder network and trained with pixel-level reconstruction loss, degradation loss and feature-level perceptual loss. Extensive experiments on three benchmark datasets demonstrate that the proposed method outperforms state-of-the-art SR methods in both subjective and objective measurements. 相似文献
Electrothermal materials can easily and controllably convert electric energy into heat energy, and are widely used in many electrothermal fields. In this paper, a series of conductive pastes were simply prepared by ball milling, and their rheological and electrothermal properties were studied. Phenolic resin was used as curing agent of epoxy resin and rheological modifier, which could make the paste have very good printing applicability. Ultrafine carbon(UC) powder has excellent dispersion effect. Sheet carbon materials such as graphite powder(GP), graphite nanosheet(GS) and graphene(GE) would improve the performance of paste using only UC as conductive filler. It was proved that GE with the smallest thickness has the most obvious lifting effect. UC was gathered around the graphene sheet, as a bridge between graphene sheets. GE could also be connected with each other to build a more effective and denser conductive path. The electrothermal film could reach 199°C under 30 V voltage, increasing by 254.7% compared with the electrothermal film with only UC as conductive filler. The electrothermal film had a short response time, good recyclability and excellent flexibility. The electrothermal film also had certain electromagnetic shielding efficiency. The electromagnetic shielding efficiency SE could reach about 20 dB at 30–1500 MHz, and the ratio of field strength before and after attenuation SE% could reach 97%?+?. This electrothermal film has simple preparation process, good printing applicability, controllable film resistance, excellent flexibility, fast response speed and good recyclability. It is suitable for large-scale preparation and has broad application prospects in many scenarios.
International Journal of Control, Automation and Systems - The vibration control problem of offshore jacket platforms is studied. The model of offshore platforms with nonlinear interactions of the... 相似文献
Small group detection and tracking in crowd scenes are basis for high level crowd analysis tasks. However, it suffers from the ambiguities in generating proper groups and in handling dynamic changes of group configurations. In this paper, we propose a novel delay decision-making based method for addressing the above problems, motivated by the idea that these ambiguities can be solved using rich temporal context. Specifically, given individual detections, small group hypotheses are generated. Then candidate group hypotheses across consecutive frames and their potential associations are built in a tree. By seeking for the best non-conflicting subset from the hypothesis tree, small groups are determined and simultaneously their trajectories are got. So this framework is called joint detection and tracking. This joint framework reduces the ambiguities in small group decision and tracking by looking ahead for several frames. However, it results in the unmanageable solution space because the number of track hypotheses grows exponentially over time. To solve this problem, effective pruning strategies are developed, which can keep the solution space manageable and also improve the credibility of small groups. Experiments on public datasets demonstrate the effectiveness of our method. The method achieves the state-of-the-art performance even in noisy crowd scenes. 相似文献