Hough Transform has been widely used for straight line detection in low-definition and still images, but it suffers from execution time and resource requirements. Field Programmable Gate Arrays (FPGA) provide a competitive alternative for hardware acceleration to reap tremendous computing performance. In this paper, we propose a novel parallel Hough Transform (PHT) and FPGA architecture-associated framework for real-time straight line detection in high-definition videos. A resource-optimized Canny edge detection method with enhanced non-maximum suppression conditions is presented to suppress most possible false edges and obtain more accurate candidate edge pixels for subsequent accelerated computation. Then, a novel PHT algorithm exploiting spatial angle-level parallelism is proposed to upgrade computational accuracy by improving the minimum computational step. Moreover, the FPGA based multi-level pipelined PHT architecture optimized by spatial parallelism ensures real-time computation for 1,024 × 768 resolution videos without any off-chip memory consumption. This framework is evaluated on ALTERA DE2-115 FPGA evaluation platform at a maximum frequency of 200 MHz, and it can calculate straight line parameters in 15.59 ms on the average for one frame. Qualitative and quantitative evaluation results have validated the system performance regarding data throughput, memory bandwidth, resource, speed and robustness.

Early rehabilitation with the right intensity contributes to the physical recovery of stroke survivors. In clinical practice, physicians determine whether the training intensity is suitable for rehabilitation based on patients’ narratives, training scores, and evaluation scales, which puts tremendous pressure on medical resources. In this study, a lightweight facial expression recognition algorithm is proposed to diagnose stroke patients’ training motivations automatically. First, the properties of convolution are introduced into the Vision Transformer’s structure, allowing the model to extract both local and global features of facial expressions. Second, the pyramid-shaped feature output mode in Convolutional Neural Networks is also introduced to reduce the model’s parameters and calculation costs significantly. Moreover, a classifier that can better classify facial expressions of stroke patients is designed to improve performance further. We verified the proposed algorithm on the Real-world Affective Faces Database (RAF-DB), the Face Expression Recognition Plus Dataset (FER+), and a private dataset for stroke patients. Experiments show that the backbone network of the proposed algorithm achieves better performance than Pyramid Vision Transformer (PvT) and Convolutional Vision Transformer (CvT) with fewer parameters and Floating-point Operations Per Second (FLOPs). In addition, the algorithm reaches an 89.44% accuracy on the RAF-DB dataset, which is higher than other recent studies. In particular, it obtains an accuracy of 99.81% on the private dataset, with only 4.10M parameters.

This paper proposes an embedded vision system for real-time moving object tracking using modified mean-shift algorithm for mobile robot application. This design of modified mean-shift algorithm fully utilizing the advanced parallelism of Field Programmable Gate Arrays (FPGA) is capable of processing real-time PAL video of 720*576 at 25 fps. This hardware implementation realizes time-consumed color space transformation using pipeline operations, which completely removes the dependence of off-chip RAM memory. In addition, this system incorporates adaptive kernel based mass center calculation method to balance the tracking complication and precision. Finally, the time division multiplex (TDM) technology obviously saves the FPGA hardware resources. As a result, the feasibility and tracking robustness of this implementation have been demonstrated through realtime tracking videos.

As a self-supervised learning paradigm, contrastive learning has been widely used to pre-train a powerful encoder as an effective feature extractor for various downstream tasks. This process requires numerous unlabeled training data and computational resources, which makes the pre-trained encoder become the valuable intellectual property of the owner. However, the lack of a priori knowledge of downstream tasks makes it non-trivial to protect the intellectual property of the pre-trained encoder by applying conventional watermarking methods. To deal with this problem, in this paper, we introduce AWEncoder, an adversarial method for watermarking the pre-trained encoder in contrastive learning. First, as an adversarial perturbation, the watermark is generated by enforcing the training samples to be marked to deviate respective location and surround a randomly selected key image in the embedding space. Then, the watermark is embedded into the pre-trained encoder by further optimizing a joint loss function. As a result, the watermarked encoder not only performs very well for downstream tasks, but also enables us to verify its ownership by analyzing the discrepancy of output provided using the encoder as the backbone under both white-box and black-box conditions. Extensive experiments demonstrate that the proposed work enjoys quite good effectiveness and robustness on different contrastive learning algorithms and downstream tasks, which has verified the superiority and applicability of the proposed work.

Background: Hand dysfunction is one of the main symptoms of stroke patients, but there is still a lack of accurate hand function assessment systems. This study focused on the application of the multi-dimensional intelligent visual quantitative assessment system (MDIVQAS) in the rehabilitation assessment of hand function in stroke patients and evaluate hand function rehabilitation in stroke patients. Methods: Eighty-two patients with stroke and unilateral hand dysfunction were evaluated by MDIVQAS. Cronbach’s Alpha coefficient was used to assess the internal consistency of MDIVQAS; the F-test is used to assess the differences in MDIVQAS for multiple repeated measures. Spearman’s analysis was used to identify correlations of MDIVQAS with other assessment systems. t-tests were used to identify differences in outcomes assessed with MDIVQAS in patients before and after treatment. p < 0.05 were considered significant. Results: (1) Cronbach’s Alpha coefficient of MDIVQAS in evaluating hand’s function > 0.9. (2) There was no significant difference between the other repeated measurements, except for thumb rotation in MDIVQAS. (3) MDIVQAS had a significant correlation with other assessment systems (r > 0.5, p < 0.01). (4) There were significant differences in the evaluation of hand function in patients before and after treatment using MDIVQAS. Conclusion: The MDIVQAS system has good reliability and validity in the evaluation of stroke hand function, and it can also better evaluate the treatment effect.

Although Deep Neural Networks (DNNs) have achieved great success on various applications, investigations have increasingly shown DNNs to be highly vulnerable when adversarial examples are used as input. Here, we present a comprehensive defense framework to protect DNNs against adversarial examples. First, we present statistical and minor alteration detectors to filter out adversarial examples contaminated by noticeable and unnoticeable perturbations, respectively. Then, we ensemble the detectors, a deep Residual Generative Network (ResGN), and an adversarially trained targeted network, to construct a complete defense framework. In this framework, the ResGN is our previously proposed network which is used to remove adversarial perturbations, and the adversarially trained targeted network is a network that is learned through adversarial training. Specifically, once the detectors determine an input example to be adversarial, it is cleaned by ResGN and then classified by the adversarially trained targeted network; otherwise, it is directly classified by this network. We empirically evaluate the proposed complete defense on ImageNet dataset. The results confirm the robustness against current representative attacking methods including fast gradient sign method, randomized fast gradient sign method, basic iterative method, universal adversarial perturbations, DeepFool method, and Carlini & Wagner method.