With the increasing popularity of digital video communication, video data hiding has become an active research topic in covert communication and privacy protection. Traditional video data hiding methods often use quantized discrete cosine transform (QDCT) coefficients to carry a sufficient payload. However, since QDCT coefficients expose texture features and motion characteristics of the present video frame heavily, data embedding with QDCT coefficients may lead to significant intra-frame distortion and inter-frame distortion drift. To avoid obvious visual artifacts and keep bit-rate within a satisfactory level of the marked video, data embedding in QDCT coefficients should take into account both the intra-frame and inter-frame distortion impacts. It motivates the authors to propose an efficient cost assignment-based video data hiding method in this paper. The proposed cost assignment method aims to accurately evaluate the data embedding distortion. Specifically, the proposed scheme considers intra-frame changes and intra-frame distortion drift, for which the texture and motion changes of frames can be measured. The frame position is also used to reflect a cumulative distortion difference of multiple frames. For data embedding, syndrome-trellis code (STC) is adopted to minimize the overall distortion. Experimental results show that the proposed method significantly outperforms existing works in terms of payload-distortion performance.

As a secondary generation method, video recording will cause irreversible damage to the watermark within the video, which has always been challenging in video forensics. Although many video watermarking methods are reported in the literature, these methods, however, still cannot well resist camera recording. This has motivated the authors in this paper to introduce a new video watermarking method to resist camera recording. For the proposed method, two watermarks, i.e., copyright watermark and synchronization watermark, are embedded into the well-selected frequency domain coefficients. The synchronization watermark is used to ensure that the copyright watermark can be successfully extracted at the decoder side. To extract the copyright watermark without manual assistance, a neural network based segmentation model is applied to identify the watermarked video-playing region in the camera-recorded video. Meanwhile, automatic perspective correction is performed on the watermarked video-playing region so that the watermark information can be extracted accurately. The experiments show that the watermark data can be embedded into the raw video successfully and extracted from the camera-recorded video accurately by applying the proposed method. And, the proposed method significantly outperforms related works in terms of robustness in different scenarios, which has verified the superiority and applicability of the proposed method.

In recent years, reversible data hiding technology has been widely used in JPEG images for special purposes such as file management and image authentication. Histogram shifting is one of the most popular techniques for achieving reversible data hiding technology. However, invalid shifting in histogram shifting limits the performance of existing reversible data hiding schemes. Therefore, we propose a two-dimensional histogram shifting-based reversible data hiding scheme in this article to improve the performance of marked JPEG images in terms of visual quality and file size. In the proposed histogram shifting method, only the coefficient pairs containing two non-zero quantized discrete cosine transform coefficients are changed for embedding data. Specifically, the coefficient pairs with at least one quantized discrete cosine transform coefficient valued −1 or +1 are shifted and the rests leave room for embedding data. With our proposed reversible data hiding scheme, the number of invalid shifting pixels is reduced so that it improves the performance of marked JPEG images. The experimental results show that the proposed method achieves a higher peak signal-to-noise ratio and has a lower increase in file size than state-of-art methods.

Infrared and visible image fusion aims to generate synthetic images including salient targets and abundant texture details. However, traditional techniques and recent deep learning-based approaches have faced challenges in preserving prominent structures and fine-grained features. In this study, we propose a lightweight infrared and visible image fusion network utilizing multi-scale attention modules and hybrid dilated convolutional blocks to preserve significant structural features and fine-grained textural details. First, we design a hybrid dilated convolutional block with different dilation rates that enable the extraction of prominent structure features by enlarging the receptive field in the fusion network. Compared with other deep learning methods, our method can obtain more high-level semantic information without piling up a large number of convolutional blocks, effectively improving the ability of feature representation. Second, distinct attention modules are designed to integrate into different layers of the network to fully exploit contextual information of the source images, and we leverage the total loss to guide the fusion process to focus on vital regions and compensate for missing information. Extensive qualitative and quantitative experiments demonstrate the superiority of our proposed method over state-of-the-art methods in both visual effects and evaluation metrics. The experimental results on public datasets show that our method can improve the entropy (EN) by 4.80%, standard deviation (SD) by 3.97%, correlation coefficient (CC) by 1.86%, correlations of differences (SCD) by 9.98%, and multi-scale structural similarity (MS_SSIM) by 5.64%, respectively. In addition, experiments with the VIFB dataset further indicate that our approach outperforms other comparable models.

Online inspection of industrial parts becomes increasingly important for factories to improve production quality, where small sizes and high computations increase difficulties in defect detection process. In order to solve these issues, we propose a defect detection model to identify detailed defects with edge computations, named fast attention segmentation classification network (FASCNet). In the model, we design skip connection attention (SCA) with edge average attention (eAA), edge sum attention (eSA) and attention for segmentation (AS) to catch complex features of extremely tiny defects. Additionally, global mixed pooling (GMP) operation is explored to adaptively obtain severe mapping into low dimensional feature domains. Furthermore, a tensor freeze decomposition (TFD) is discovered to reduce model computation and complexity for edge devices. Finally, we achieve an AP of 97.86% and GFLOPs of 64.4495 on the real-world sprocket surface dataset, which has 16.06% of GFLOPs of the current state-of-the-art method while only lowering the AP by 0.58%. On the public dataset, we achieve an AP of 98.83% and GFLOPs of 92.0379 on the Severstal Steel dataset. The experimental results indicate that our model performs more effectively than other state-of-the-art approaches in terms of both accuracy and computational cost simultaneously.