23 November 2021 in IEEE Transactions on Circuits and Systems for Video Technology
As face editing scenarios have become popular, the face inpainting technique has become a hot topic. Although some existing methods can inpaint faces with preserved identity information, they fail to solve a more flexible inpainting problem that fills the “holes” with identity-specific content from other faces. In this work, we propose a disentangle and subject-agnostic framework that affects both full and partial-face inpainting with the guidance of a reference face image. The framework consists of an identity encoding module, a content inference module and a generative module. The identity encoding module extracts the identity embedding from the reference image, the content inference module learns to predict the content image, and the generative module integrates the content image and the reference identity embedding to generate the identity-specific inpainted result. To minimize the structure and style gap between the incomplete image and inpainted image, we use a double attribute loss to the generative module and a postprocess of blending operation to the swapped result. We compare our method with state-of-the-art works and demonstrate that our method achieves higher identity similarity and better structural correctness.
27 September 2023 in ACM Transactions on Multimedia Computing, Communications, and Applications
In intelligent transportation systems, various sensors, including radar and conventional frame cameras, are used to improve system robustness in various challenging scenarios. An event camera is a novel bio-inspired sensor that has attracted the interest of several researchers. It provides a form of neuromorphic vision to capture motion information asynchronously at high speeds. Thus, it possesses advantages for intelligent transportation systems that conventional frame cameras cannot match, such as high temporal resolution, high dynamic range, as well as sparse and minimal motion blur. Therefore, this study proposes an E-detector based on event cameras that asynchronously detect moving objects. The main innovation of our framework is that the spatiotemporal domain of the event camera can be adjusted according to different velocities and scenarios. It overcomes the inherent challenges that traditional cameras face when detecting moving objects in complex environments, such as high speed, complex lighting, and motion blur. Moreover, our approach adopts filter models and transfer learning to improve the performance of event-based object detection. Experiments have shown that our method can detect high-speed moving objects better than conventional cameras using state-of-the-art detection algorithms. Thus, our proposed approach is extremely competitive and extensible, as it can be extended to other scenarios concerning high-speed moving objects. The study findings are expected to unlock the potential of event cameras in intelligent transportation system applications.
1 January 2012 in AIP Conference Proceedings
Ultrasonic guided wave methods are being widely explored for inspection of large structural areas using a sparse array of surface-mounted transducers. However, structural health monitoring (SHM) with guided waves can be problematic because variable operational conditions can significantly affect the measured ultrasonic signals. Although homogeneous temperature variations have been well-researched and successful compensation algorithms developed, few studies have considered distributed surface wetting. This paper reports results from an experimental investigation of the effects of surface wetting on guided wave signals recorded from a spatially distributed array affixed to a stiffened aluminum plate. Droplets of water were applied to the plate in a random and increasing manner until almost forty percent of the plate was wet, and the percent surface area covered at each increment of wetting was independently measured via digital photographs of the plate surface. Ultrasonic guided wave signals resulting from a broadband chirp excitation were recorded from all transducer pairs in between increments of wetting. Root mean squared errors as compared to the dry plate are calculated from these signals at multiple frequencies to investigate the efficacy of quantifying the degree of surface wetting. This study is a first step in the process of assessing and addressing the effects of distributed surface wetting on the performance of a guided wave SHM system.
31 August 2024 in Pattern Recognition