MIMO-Uformer:用于车辆监控场景的基于变压器的图像清除网络
Jian Zhang1, Baoping Cheng1,2, Tengying Zhang1
1China Mobile (Hangzhou) Information Technology Co., Ltd., Hangzhou 311100, China.
Journal of imaging
|November 26, 2024
概括
本研究介绍了MIMO-Uformer,这是一个高效的基于变压器的网络,用于消除监控图像的模糊性. 它有效地处理车辆监控中常见的局部运动模糊,改善图像质量和信息获取.
科学领域:
- 计算机视觉 计算机视觉
- 深度学习 (Deep Learning) 是一种深度学习.
- 图像恢复 图像恢复
背景情况:
- 运动模糊显著降低了监视图像质量,阻碍了信息检索.
- 卷积神经网络 (CNN) 具有先进的图像消除模糊性,但变压器提供优越的深度表示学习.
- 标准变压器的高计算复杂性限制了它们对高分辨率图像的应用.
研究的目的:
- 提出一个高效的基于变压器的消除模糊网络,MIMO-Uformer,适用于车辆监控场景.
- 为了应对监控录像中普遍存在的局部运动模糊的挑战.
- 通过结合多尺度图像处理和专门的损失功能来提高图像消除模糊的性能.
主要方法:
- 开发了MIMO-Uformer,将Swin变压器的基于窗口的多头自我注意 (W-MSA) 集成到多输入,多输出U-Net (MIMO-UNet) 架构中.
- 在MIMO-UNet框架内使用多尺度图像处理,以利用各种图像分辨率.
- 引入了交叉点对补丁 (IoP) 因素和监督的形态损失,以特别准和减轻局部运动模糊.
主要成果:
- MIMO-Uformer在消除模糊性能方面取得了显著的改进,特别是在局部运动模糊方面.
- 在公共 (GOPRO) 和自主建立的数据集上的实验显示了峰值信号对噪声比率 (PSNR) 的显著增长.
- 与现有基准相比,在GOPRO上实现了至少0.21dB的PSNR改进,在自主建立的数据集上达到0.74dB.
结论:
- MIMO-Uformer提供了一种高效和有效的解决方案,用于消除监控图像的模糊,特别是那些受局部运动模糊影响的图像.
- 拟议的IOP因子和形态损失提高了网络处理车辆监控中常见的特定类型模糊的能力.
- 该研究通过广泛的实验验证实了拟议方法的有效性,为改进的监控系统铺平了道路.
相关概念视频
Transformers with Off-Nominal Turns Ratios
139
In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the...
139
Reconstruction of Signal using Interpolation
173
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
173
Deconvolution
132
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
132
Transformers in Distribution System
98
Transformers in distribution systems can be broadly categorized into distribution substation transformers and other distribution transformers. They are crucial for stepping down high transmission voltages to levels suitable for distribution and end-user applications.
Distribution substation transformers come in various ratings and typically use mineral oil for insulation and cooling. To prevent moisture and air from entering the oil, some transformers use an inert gas like nitrogen to fill the...
Distribution substation transformers come in various ratings and typically use mineral oil for insulation and cooling. To prevent moisture and air from entering the oil, some transformers use an inert gas like nitrogen to fill the...
98
Convolution Properties II
173
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
173


