Motion Blurred Images Research Articles

Shuttlecock Detection Using Residual Learning in U-Net Architecture

This paper introduces an enhanced approach for detecting shuttlecock. Detecting fast-moving objects, such as a shuttlecock, is crucial in various applications, including badminton video analysis and object tracking. Many deep-learning techniques have been proposed in literature to address this challenge. However, low image quality, motion blur, afterimage, and short-term occlusion can hinder accurate detection. To overcome these limitations, this research focuses on improving the existing method called TrackNetV2, which utilizes the U-Net architecture. The primary enhancement proposed in this study is incorporating residual learning within the U-Net architecture, emphasizing processing speed, prediction accuracy, and precision. Specifically, each U-Net layer is augmented with a residual layer, enhancing the network's overall performance. The results demonstrate that our proposed method outperforms the existing detection accuracy and reliability technique.

Image Motion Blur Removal Algorithm Based on Generative Adversarial Network

Image Motion Blur Removal Algorithm Based on Generative Adversarial Network

Optimizing Real-Time Advanced Ultrasound Supervision in a University Setting

Introduction: Ultrasound-based diagnosis requires great expertise for reliability and accuracy, thus practical training is vital. Digital training can offer students the possibility of practical training in their local setups. However, there are critical issues that remote educators must address, particularly in advanced ultrasound training. The present study was therefore aiming at developing a suitable technical setup for supervision and education in tele-ultrasound that can be applied to a variety of advanced diagnostic and therapeutic areas. Methods: Using an action research approach including four cycles of action, we tested four technical setups with different software and hardware components across four ultrasound courses. Based on evaluation forms, written reflections, and two focus group interviews from the four cycles of action, respectively, we modified the setups to improve the technical solution for the next cycle. Results: The initial set-up was using commercial video call apps via mobile phones. Although no additional equipment or expertise was required, it was precluded by the poor image quality and motion blur resulting from capturing the ultrasound image on the smartphone. Nevertheless, this solution is viable when quick clarifications are needed. Additional stabilization support in the second set-up did not provide satisfactory image quality. The best technical solution was found in the third set-up, using a frame grabber and Reacts, which allows simultaneous live streaming of the ultrasound screen image and two web cameras. However, the cumbersome software interface, the need for an expensive user license, and problems with the internet connection reduced the acceptability of this setup. The optimal setup in cycle four, was a reasonable frame grabber, and Zoom, which is free, has a simple user interface and can stream live audio-visual ultrasound data from the probe and user simultaneously. Its annotation function is also beneficial in supervision. Conclusion: Through an action research approach including four cycles of action and thorough, subsequent evaluations, we found that a videoconferencing platform, such as Zoom, a computer, and a frame grabber connected to the ultrasound scanner was the optimal solution as this set-up is simple and affordable and is facilitating a good video-transmitted learning situation for students and supervisors. This technical set-up could therefore be suitable for a wide range of remote ultrasound courses.

Restoration of motion-blurred numeral image using a complex-amplitude diffractive processor.

We propose a complex-amplitude diffractive processor based on diffractive deep neural networks (D2NNs). By precisely controlling the propagation of an optical field, it can effectively remove the motion blur in numeral images and realize the restoration. Comparative analysis of phase-only, amplitude-only, and complex-amplitude diffractive processor reveals that the complex-amplitude network significantly enhances the performance of the processor and improves the peak signal-to-noise ratio (PSNR) of the images. Appropriate use of complex-amplitude networks contributes to reduce the number of network layers and alleviates alignment difficulties. Due to its fast processing speed and low power consumption, complex-amplitude diffractive processors hold potential applications in various fields including road monitoring, sports photography, satellite imaging, and medical diagnostics.

A novel method for measuring center-axis velocity of unmanned aerial vehicles through synthetic motion blur images

Accurate velocity measurement of unmanned aerial vehicles (UAVs) is essential in various applications. Traditional vision-based methods rely heavily on visual features, which are often inadequate in low-light or feature-sparse environments. This study presents a novel approach to measure the axial velocity of UAVs using motion blur images captured by a UAV-mounted monocular camera. We introduce a motion blur model that synthesizes imaging from neighboring frames to enhance motion blur visibility. The synthesized blur frames are transformed into spectrograms using the Fast Fourier Transform (FFT) technique. We then apply a binarization process and the Radon transform to extract light-dark stripe spacing, which represents the motion blur length. This length is used to establish a model correlating motion blur with axial velocity, allowing precise velocity calculation. Field tests in a hydropower station penstock demonstrated an average velocity error of 0.048 m/s compared to ultra-wideband (UWB) measurements. The root-mean-square error was 0.025, with an average computational time of 42.3 ms and CPU load of 17%. These results confirm the stability and accuracy of our velocity estimation algorithm in challenging environments.

The Motion Estimation of Unmanned Aerial Vehicle Axial Velocity Using Blurred Images

This study proposes a novel method for estimating the axial velocity of unmanned aerial vehicles (UAVs) using motion blur images captured in environments where GPS signals are unavailable and lighting conditions are poor, such as underground tunnels and corridors. By correlating the length of motion blur observed in images with the UAV’s axial speed, the method addresses the limitations of traditional techniques in these challenging scenarios. We enhanced the accuracy by synthesizing motion blur images from neighboring frames, which is particularly effective at low speeds where single-frame blur is minimal. Six flight experiments conducted in the corridor of a hydropower station demonstrated the effectiveness of our approach, achieving a mean velocity error of 0.065 m/s compared to ultra-wideband (UWB) measurements and a root-mean-squared error within 0.3 m/s. The results highlight the stability and precision of the proposed velocity estimation algorithm in confined and low-light environments.

Deep learning-based restoration of nonlinear motion blurred images for plant classification using multi-spectral images

There have been various plant image-based studies for segmentation, deblurring, super-resolution reconstruction, and classification. However, nonlinear motion blur in thermal images was not considered in the existing studies on plant classification. Nonlinear motion blur occurs in images due to camera or plant movements, and it causes the degradation of plant classification accuracy. Moreover, nonlinear motion blur in images gets worse when both camera and plant movements occur simultaneously. In this case, it becomes difficult to recognize plants, and the performance of plant image classification becomes very low. Therefore, to reduce the nonlinear motion blur, a thermal and visible light plant images-based deblurring network (TVPD-Net) is proposed in this study. In addition, a thermal and visible light plant images-based classification network (TVPC-Net) is also proposed to improve the plant classification performance on deblurred images. Experimental results revealed that the proposed TVPD-Net achieved 21.21 and 22.53 of the peak signal-to-noise ratio (PSNR), and 0.726 and 0.737 of the structural similarity index measure (SSIM) on both visible light and thermal plant image datasets which were self-collected, respectively. Moreover, the proposed TVPC-Net with deblurred images by TVPD-Net achieved 92.52 % (top-1 accuracy) and 87.73 % (harmonic mean of precision and recall (F1-score)). In addition, the experimental results on an open dataset named Hyperspectral Flower Dataset (HFD100) revealed that the proposed plant classification method achieved 90.94 % of top-1 accuracy and 86.21 % of F1-score. The accuracies of the proposed methods are greater than those of the state-of-the-art methods.

Research on the influence of image motion blur on the effectiveness of machine vision-based metal scraps separation system

Research on the influence of image motion blur on the effectiveness of machine vision-based metal scraps separation system

Detecting Line Segments in Motion-Blurred Images With Events.

Making line segment detectors more reliable under motion blurs is one of the most important challenges for practical applications, such as visual SLAM and 3D line mapping. Existing line segment detection methods face severe performance degradation for accurately detecting and locating line segments when motion blur occurs. While event data shows strong complementary characteristics to images for minimal blur and edge awareness at high-temporal resolution, potentially beneficial for reliable line segment recognition. To robustly detect line segments over motion blurs, we propose to leverage the complementary information of images and events. Specifically, we first design a general frame-event feature fusion network to extract and fuse the detailed image textures and low-latency event edges, which consists of a channel-attention-based shallow fusion module and a self-attention-based dual hourglass module. We then utilize the state-of-the-art wireframe parsing networks to detect line segments on the fused feature map. Moreover, due to the lack of line segment detection datasets with pairwise motion-blurred images and events, we contribute two datasets, i.e., synthetic FE-Wireframe and realistic FE-Blurframe, for network training and evaluation. Extensive analyses on the component configurations demonstrate the design effectiveness of our fusion network. When compared to the state-of-the-arts, the proposed approach achieves the highest detection accuracy while maintaining comparable real-time performance. In addition to being robust to motion blur, our method also exhibits superior performance for line detection under high dynamic range scenes.

Interpretable deep learning analysis on correction of motion blur X-ray images to ensure the efficiency and reliability of clinical decisions

Motion blur X-rays often lead to repeated imaging and extra radiation exposure. This study introduces an interpretable deep learning method to ensure AI prediction efficiency and reliability and uses the correction of motion blur X-ray images as a case study. A deep learning model that integrates Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) and EfficientNet-B3 is trained to correct motion-blurred images with interpretable analysis. ESRGAN corrects motion-blurred images and EfficientNet-B3 tackles the disease recognition. The accuracy on public datasets reaches 0.97 and clinical motion blur X-rays improves from 0.4 to 0.74 with an 85% increase. The results are analyzed using image quality metrics and interpretative methods to confirm the effectiveness and reliability of the proposed method. The proposed method ensures accuracy and reliability in disease recognition and improves the quality of X-ray images, which are verified with actual clinical data. This approach alleviates the workload of radiologists, reduces radiation exposure risks for patients, and holds promise for wider applications in medical imaging. To the best of our knowledge, this is the first study combining deep learning with interpretability to ensure the deblurring task of medical images with potential applications in CT and MRI.

Estimating Acceleration from a Single Uniform Linear Motion-Blurred Image using Homomorphic Mapping and Machine Learning

Context: Vision-based measurement (VBM) systems are becoming popular as an affordable and suitable alternative for scientific and engineering applications. When cameras are used as instruments, motion blur usually emerges as a recurrent and undesirable image degradation, which in fact contains kinematic information that is usually dismissed. Method: This paper introduces an alternative approach to measure relative acceleration from a real invariant uniformly accelerated linear motion-blurred image. This is done by using homomorphic mapping to extract the characteristic Point Spread Function (PSF) of the blurred image, as well as machine learning regression. A total of 125 uniformly accelerated motion-blurred pictures were taken in a light- and distance-controlled environment, at five different accelerations ranging between 0,64 and 2,4 m/s2. This study evaluated 19 variants such as tree ensembles, Gaussian processes (GPR), and linear, support vector machine (SVM), and tree regression. Results: The best RMSE result corresponds to GPR (Matern 5/2), with 0,2547 m/s2 and a prediction speed of 530 observations per second (obs/s). Additionally, some novel deep learning methods were used to obtain the best RMSE value (0,4639 m/s2 for Inception ResNet v2, with a prediction speed of 11 obs/s. Conclusions: The proposed method (homomorphic mapping and machine learning) is a valid alternative for calculating acceleration from invariant motion blur in real-time applications when additive noise is not dominant, even surpassing the deep learning techniques evaluated.

Image deblurring by multi-scale modified U-Net using dilated convolution.

In modern urban traffic systems, intersection monitoring systems are used to monitor traffic flows and track vehicles by recognizing license plates. However, intersection monitors often produce motion-blurred images because of the rapid movement of cars. If a deep learning network is used for image deblurring, the blurring of the image can be eliminated first, and then the complete vehicle information can be obtained to improve the recognition rate. To restore a dynamic blurred image to a sharp image, this paper proposes a multi-scale modified U-Net image deblurring network using dilated convolution and employs a variable scaling iterative strategy to make the scheme more adaptable to actual blurred images. Multi-scale architecture uses scale changes to learn the characteristics of different scales of images, and the use of dilated convolution can improve the advantages of the receptive field and obtain more information from features without increasing the computational cost. Experimental results are obtained using a synthetic motion-blurred image dataset and a real blurred image dataset for comparison with existing deblurring methods. The experimental results demonstrate that the image deblurring method proposed in this paper has a favorable effect on actual motion-blurred images.

Event-Assisted Recurrent Network for Arbitrary-Temporal-Scale Blurry Image Unfolding.

Recovering a sequence of latent sharp frames from a motion-blurred image is a challenging task. The bio-inspired event camera, which produces an event stream with high temporal resolution, has been exploited to promote the recovery performance. However, recovering sharp sequences with arbitrary temporal scales has been ignored for a long time. Existing works can only recover a fixed number of latent frames from a blurry image once they are trained. In this work, we propose an event-assisted blurry image unfolding framework that can work across arbitrary temporal scales. A bi-directional recurrent network is employed to encode events corresponding to each latent frame, which gathers information over all events in the exposure time. Features of both the blurry image and events are fused together and fed to a bi-directional latent sequence decoder (BiLSD) to produce a sequence of latent sharp frames. Extensive experiments show that the proposed method not only performs favorably against state-of-the-art methods in recovering a fixed number of frames from a blurry image but can be well generalized to arbitrary-temporal-scale blurry image unfolding.

Image Motion Blur Mechanism-based Measurement Method for Low-Frequency Vibration Amplitude and Directi on

Image Motion Blur Mechanism-based Measurement Method for Low-Frequency Vibration Amplitude and Directi on

Dynamic and Real-Time Object Detection Based on Deep Learning for Home Service Robots

Home service robots operating indoors, such as inside houses and offices, require the real-time and accurate identification and location of target objects to perform service tasks efficiently. However, images captured by visual sensors while in motion states usually contain varying degrees of blurriness, presenting a significant challenge for object detection. In particular, daily life scenes contain small objects like fruits and tableware, which are often occluded, further complicating object recognition and positioning. A dynamic and real-time object detection algorithm is proposed for home service robots. This is composed of an image deblurring algorithm and an object detection algorithm. To improve the clarity of motion-blurred images, the DA-Multi-DCGAN algorithm is proposed. It comprises an embedded dynamic adjustment mechanism and a multimodal multiscale fusion structure based on robot motion and surrounding environmental information, enabling the deblurring processing of images that are captured under different motion states. Compared with DeblurGAN, DA-Multi-DCGAN had a 5.07 improvement in Peak Signal-to-Noise Ratio (PSNR) and a 0.022 improvement in Structural Similarity (SSIM). An AT-LI-YOLO method is proposed for small and occluded object detection. Based on depthwise separable convolution, this method highlights key areas and integrates salient features by embedding the attention module in the AT-Resblock to improve the sensitivity and detection precision of small objects and partially occluded objects. It also employs a lightweight network unit Lightblock to reduce the network’s parameters and computational complexity, which improves its computational efficiency. Compared with YOLOv3, the mean average precision (mAP) of AT-LI-YOLO increased by 3.19%, and the detection precision of small objects, such as apples and oranges and partially occluded objects, increased by 19.12% and 29.52%, respectively. Moreover, the model inference efficiency had a 7 ms reduction in processing time. Based on the typical home activities of older people and children, the dataset Grasp-17 was established for the training and testing of the proposed method. Using the TensorRT neural network inference engine of the developed service robot prototype, the proposed dynamic and real-time object detection algorithm required 29 ms, which meets the real-time requirement of smooth vision.

AFA-Net: Adaptive Feature Attention Network in image deblurring and super-resolution for improving license plate recognition

Although a number of license plate recognition (LPR) systems have become significantly advanced, they are still far from producing ideal images. They are still fiddled with low-resolution (LR) and motion blur, which are two of the most common problems in images extracted from automobile driving environment. In order to address this issue, we present a novel LPR method that processes LR and motion blurred images from dash cams. We propose a unique framework, AFA-Net (Adaptive Feature Attention Network) organized by image pre-restoration, feature composition and image reconstruction modules. The proposed AFA-Net can generate a clear restoration image for robust LPR performance with the images obtained from dash cams in an unconstrained environment. Furthermore, we explore the novel problem, Joint-IRLPRNet (Joint-Image Restoration and License Plate Recognition Network), that simultaneously address image restoration (i.e. SR and deblurring) and LPR in an end-to end trainable manner. Moreover, we introduce a dataset called LBLP (LR and blurred license plate (LP)). The dataset is composed of 2,779 LR and motion blurred cropped LP images, extracted from unconstrained dash cams. The experimental results on LBLP dataset indicate that AFA-Net achieves 15.28% improvement in recognition accuracy, 6.47% in sequence similarity, and 3.89% in character similarity, compared to the traditional LPR model with image restoration model. Moreover, Joint-IRLPRNet can be more effective results than AFA-Net.

Capsule Endoscopy Image Deblurring Method Based on Multi-scale Recurrent Network

During the process of acquiring capsule endoscope images, image motion blur may result from errors made by the operating physician. A multi-scale recurrent attention network is proposed to address the issue of motion blur in collected images. Considering the issue of over-exposure during image acquisition in capsule endoscopy, which can adversely affect network generation results, an image preprocessing module has been incorporated into the network to eliminate highlights caused by over-exposure in input images. To enhance network sampling efficiency, the encoder is equipped with a Convolutional Block Attention Module (CBAM) to extract fuzzy features more effectively. Additionally, depthwise separable convolution is employed to reduce parameter count. Since the structure of images obtained through capsule endoscopy is relatively simple and stable, we have opted for the mean square error as our loss function due to its heightened sensitivity to data errors. The experimental results demonstrate that the proposed network achieves a Peak Signal-to-Noise Ratio (PSNR) of 31.096 and a Structural Similarity Index Measure (SSIM) of 0.925, indicating a significant improvement over DeblurGAN-v2 and Pix2pix.

Improved weed segmentation in UAV imagery of sorghum fields with a combined deblurring segmentation model

BackgroundEfficient and site-specific weed management is a critical step in many agricultural tasks. Image captures from drones and modern machine learning based computer vision methods can be used to assess weed infestation in agricultural fields more efficiently. However, the image quality of the captures can be affected by several factors, including motion blur. Image captures can be blurred because the drone moves during the image capturing process, e.g. due to wind pressure or camera settings. These influences complicate the annotation of training and test samples and can also lead to reduced predictive power in segmentation and classification tasks.ResultsIn this study, we propose DeBlurWeedSeg, a combined deblurring and segmentation model for weed and crop segmentation in motion blurred images. For this purpose, we first collected a new dataset of matching sharp and naturally blurred image pairs of real sorghum and weed plants from drone images of the same agricultural field. The data was used to train and evaluate the performance of DeBlurWeedSeg on both sharp and blurred images of a hold-out test-set. We show that DeBlurWeedSeg outperforms a standard segmentation model that does not include an integrated deblurring step, with a relative improvement of 13.4 % in terms of the Sørensen-Dice coefficient.ConclusionOur combined deblurring and segmentation model DeBlurWeedSeg is able to accurately segment weeds from sorghum and background, in both sharp as well as motion blurred drone captures. This has high practical implications, as lower error rates in weed and crop segmentation could lead to better weed control, e.g. when using robots for mechanical weed removal.

Video reconstruction from a single motion blurred image using learned dynamic phase coding

Video reconstruction from a single motion-blurred image is a challenging problem, which can enhance the capabilities of existing cameras. Recently, several works addressed this task using conventional imaging and deep learning. Yet, such purely digital methods are inherently limited, due to direction ambiguity and noise sensitivity. Some works attempt to address these limitations with non-conventional image sensors, however, such sensors are extremely rare and expensive. To circumvent these limitations by simpler means, we propose a hybrid optical-digital method for video reconstruction that requires only simple modifications to existing optical systems. We use learned dynamic phase-coding in the lens aperture during image acquisition to encode motion trajectories, which serve as prior information for the video reconstruction process. The proposed computational camera generates a sharp frame burst of the scene at various frame rates from a single coded motion-blurred image, using an image-to-video convolutional neural network. We present advantages and improved performance compared to existing methods, with both simulations and a real-world camera prototype. We extend our optical coding to video frame interpolation and present robust and improved results for noisy videos.

Blind Restoration of a Single Real Turbulence-Degraded Image Based on Self-Supervised Learning

Turbulence-degraded image frames are distorted by both turbulent deformations and space–time varying blurs. Restoration of the atmospheric turbulence-degraded image is of great importance in the state of affairs, such as remoting sensing, surveillance, traffic control, and astronomy. While traditional supervised learning uses lots of simulated distorted images for training, it has poor generalization ability for real degraded images. To address this problem, a novel blind restoration network that only inputs a single turbulence-degraded image is presented, which is mainly used to reconstruct the real atmospheric turbulence distorted images. In addition, the proposed method does not require pre-training, and only needs to input a single real turbulent degradation image to output a high-quality result. Meanwhile, to improve the self-supervised restoration effect, Regularization by Denoising (RED) is introduced to the network, and the final output is obtained by averaging the prediction of multiple iterations in the trained model. Experiments are carried out with real-world turbulence-degraded data by implementing the proposed method and four reported methods, and we use four non-reference indicators for evaluation, among which Average Gradient, NIQE, and BRISQUE have achieved state-of-the-art effects compared with other methods. As a result, our method is effective in alleviating distortions and blur, restoring image details, and enhancing visual quality. Furthermore, the proposed approach has a certain degree of generalization, and has an excellent restoration effect for motion-blurred images.