Comprehending the intricacies of image structure and noise distribution is pivotal in employing paired training methods. Nevertheless, these approaches encounter difficulties when attempting to generalize to images characterized by unknown noise distributions. In response to this challenge, we propose a two-stage image denoising method designed to enhance generalization performance. In the initial stage, we introduce a preliminary denoiser based on a Multilayer Perceptron (MLP). This denoiser utilizes an implicit structural prior to forecast preliminary denoising results, ensuring alignment with the clean image structure. This stage necessitates training with a limited set of paired low-noise images. In the subsequent stage, we incorporate initial denoising results as guiding conditions for denoising diffusion null-space model (DDNM), we proficiently harness the generated diffusion prior, markedly amplifying the denoising model's generalization capability. We utilize a pretrained unconditional diffusion model, obviating the need for supplementary training or network optimization, thereby resulting in an economical overall training cost for the entire method. Through extensive experimental validation encompassing diverse datasets, noise types, and intensity levels, our method consistently outperforms alternative image denoising techniques in both denoising performance and generalization ability.
Aimed at the characteristics of the diversity of traffic road targets and the complexity and variability of detection scenarios, it is difficult for general target detection algorithms to find an ideal balance between accuracy and speed, resulting in slower detection speed and higher false detection rate. An improved YOLOv4 traffic road target detection algorithm has been proposed to solve these problems. Firstly, a Context Exploitation method is introduced to reduce information loss at the highest level feature map in FPN. Secondly, the residual feature augmentation method is adopted to enhance the feature extraction of the convolutional layer of the YOLOv4 neck, which greatly improves the detection speed and also obtains an increase in accuracy. Finally, the augmented PANet is used to improve the feature fusion method and enhance the representation ability of the feature map. Compared with other classic methods on the VOC and TT100K datasets for road target detection, it is found that the improved YOLOv4 algorithm can effectively reduce the false detection rate of small targets and significantly improve the accuracy and speed of detection. Experimental results show that the improved YOLOv4 algorithm has an average accuracy of 2.42% higher than original YOLOv4 algorithm on detection, and the detection speed reaches 61.5 frames/s.
With the development of solar radio spectrometer, it is difficult to process a large number of observed data quickly by manual detection method. An automatic detection method of solar radio burst based on Otsu binarization is proposed in this paper. In this method, channel normalization is used to denoise the original solar radio image. Through experimental comparison, Otsu method is selected as a binary method of solar radio spectrum, and Open and Close operations are used to smooth the binary image. Experiments show that the proposed method for automatic detection of solar radio bursts is effective
With the development of solar radio spectrometer, a large number of observational data has been obtained and the manual detection is difficult to reach the research needs. An automatic detection method of solar radio burst using kmeans clustering was presented in this paper. K-means clustering is introduced to classify the burst points in solar radio spectrum, and it can do better in high spectral and time resolution spectrometer. The experimental results show that the proposed method is effective.
Face detection is one of the important topics in computer vision research and is the basis of many applications. A face detection algorithm based on improved Multi-Task Convolution Neural Network (MTCNN) is proposed in this paper. To increase the accuracy of eye location in complex situations, this method improves the network structure of MTCNN, builds a neural network model based on MTCNN using TensorFlow, and cascades an eye regression network. The Face-Net neural network model was used for training, and the obtained training model was used for detection. Experiments have shown that the accuracy on the LFW dataset is 0.9963 and the accuracy on the YouTube Faces DB dataset is 0.9512.
The performance of vector graphics render has always been one of the key elements in mobile devices and the most important step to improve the performance is to enhance the efficiency of polygon fill algorithms. In this paper, we proposed a new and more efficient polygon fill algorithm based on the scan line algorithm and Grid Fill Algorithm (GFA). First, we elaborated the GFA through solid fill. Second, we described the techniques for implementing antialiasing and self-intersection polygon fill with GFA. Then, we discussed the implementation of GFA based on the gradient fill. Generally, compared to other fill algorithms, GFA has better performance and achieves faster fill speed, which is specifically consistent with the inherent characteristics of mobile devices. Experimental results show that better fill effects can be achieved by using GFA.
Moving object detection is the fundamental task in machine vision applications. However, moving cast shadows detection is one of the major concerns for accurate video segmentation. Since detected moving object areas are often contain shadow points, errors in measurements, localization, segmentation, classification and tracking may arise from this. A novel shadow elimination algorithm is proposed in this paper. A set of suspected moving object area are detected by the adaptive Gaussian approach. A model is established based on shadow optical properties analysis. And shadow regions are discriminated from the set of moving pixels by using the properties of brightness, chromaticity and texture in sequence.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.