Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLet There be Light: Improved Traffic Surveillance via Detail Preserving Night-to-Day Transfer
90
0
0.0
(
0
)
Added by
Lan Fu
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
In recent years, image and video surveillance have made considerable progresses to the Intelligent Transportation Systems (ITS) with the help of deep Convolutional Neural Networks (CNNs). As one of the state-of-the-art perception approaches, detecting the interested objects in each frame of video surveillance is widely desired by ITS. Currently, object detection shows remarkable efficiency and reliability in standard scenarios such as daytime scenes with favorable illumination conditions. However, in face of adverse conditions such as the nighttime, object detection loses its accuracy significantly. One of the main causes of the problem is the lack of sufficient annotated detection datasets of nighttime scenes. In this paper, we propose a framework to alleviate the accuracy decline when object detection is taken to adverse conditions by using image translation method. We propose to utilize style translation based StyleMix method to acquire pairs of day time image and nighttime image as training data for following nighttime to daytime image translation. To alleviate the detail corruptions caused by Generative Adversarial Networks (GANs), we propose to utilize Kernel Prediction Network (KPN) based method to refine the nighttime to daytime image translation. The KPN network is trained with object detection task together to adapt the trained daytime model to nighttime vehicle detection directly. Experiments on vehicle detection verified the accuracy and effectiveness of the proposed approach.
rate research
Read More
In this paper, we address the makeup transfer and removal tasks simultaneously, which aim to transfer the makeup from a reference image to a source image and remove the makeup from the with-makeup image respectively. Existing methods have achieved much advancement in constrained scenarios, but it is still very challenging for them to transfer makeup between images with large pose and expression differences, or handle makeup details like blush on cheeks or highlight on the nose. In addition, they are hardly able to control the degree of makeup during transferring or to transfer a specified part in the input face. In this work, we propose the PSGAN++, which is capable of performing both detail-preserving makeup transfer and effective makeup removal. For makeup transfer, PSGAN++ uses a Makeup Distill Network to extract makeup information, which is embedded into spatial-aware makeup matrices. We also devise an Attentive Makeup Morphing module that specifies how the makeup in the source image is morphed from the reference image, and a makeup detail loss to supervise the model within the selected makeup detail area. On the other hand, for makeup removal, PSGAN++ applies an Identity Distill Network to embed the identity information from with-makeup images into identity matrices. Finally, the obtained makeup/identity matrices are fed to a Style Transfer Network that is able to edit the feature maps to achieve makeup transfer or removal. To evaluate the effectiveness of our PSGAN++, we collect a Makeup Transfer In the Wild dataset that contains images with diverse poses and expressions and a Makeup Transfer High-Resolution dataset that contains high-resolution images. Experiments demonstrate that PSGAN++ not only achieves state-of-the-art results with fine makeup details even in cases of large pose/expression differences but also can perform partial or degree-controllable makeup transfer.
As experimental null results increase the pressure on heavy weakly interacting massive particles (WIMPs) as an explanation of thermal dark matter (DM), it seems timely to explore previously overlooked regions of the WIMP parameter space. In this work we extend the minimal gauged $U(1)_{L_mu-L_tau}$ model studied in cite{Bauer:2018onh} by a light (MeV-scale) vector-like fermion $chi$. Taking into account constraints from cosmology, direct and indirect detection we find that the standard benchmark of $M_V=3 m_chi$ for DM coupled to a vector mediator is firmly ruled out for unit DM charges. However, exploring the near-resonance region $M_Vgtrsim 2 m_chi$ we find that this model can simultaneously explain the DM relic abundance $Omega h^2 =0.12$ and the $(g-2)_mu$ anomaly. Allowing for small charge hierarchies of $lesssimmathcal{O}(10)$, we identify a second window of parameter space in the few-GeV region, where $chi$ can account for the full DM relic density.
We investigate the short-term optical variability of two gamma Cas analogs, pi Aqr and BZ Cru, thanks to intensive ground-based spectroscopic and space-borne photometric monitorings. For both stars, low-amplitude (mmag) coherent photometric variability is detected. The associated signals display long-term amplitude variations, as in other Be stars. However, these signals appear at high frequencies, especially in pi Aqr, indicating p-modes with a high degree l, a quite unusual feature amongst Be stars. While BZ Cru presents only low-level spectral variability, without clear periodicity, this is not the case of pi Aqr. In this star, the dominant photometric frequencies, near ~12/d, are confirmed spectroscopically in separate monitorings taken during very different disk activity levels ; the spectroscopic analysis suggests a probable tesseral nature for the mode.
Feature pyramids and iterative refinement have recently led to great progress in optical flow estimation. However, downsampling in feature pyramids can cause blending of foreground objects with the background, which will mislead subsequent decisions in the iterative processing. The results are missing details especially in the flow of thin and of small structures. We propose a novel Residual Feature Pyramid Module (RFPM) which retains important details in the feature map without changing the overall iterative refinement design of the optical flow estimation. RFPM incorporates a residual structure between multiple feature pyramids into a downsampling module that corrects the blending of objects across boundaries. We demonstrate how to integrate our module with two state-of-the-art iterative refinement architectures. Results show that our RFPM visibly reduces flow errors and improves state-of-art performance in the clean pass of Sintel, and is one of the top-performing methods in KITTI. According to the particular modular structure of RFPM, we introduce a special transfer learning approach that can dramatically decrease the training time compared to a typical full optical flow training schedule on multiple datasets.
The accuracy of OCR is usually affected by the quality of the input document image and different kinds of marred document images hamper the OCR results. Among these scenarios, the low-resolution image is a common and challenging case. In this paper, we propose the cascaded networks for document image super-resolution. Our model is composed by the Detail-Preserving Networks with small magnification. The loss function with perceptual terms is designed to simultaneously preserve the original patterns and enhance the edge of the characters. These networks are trained with the same architecture and different parameters and then assembled into a pipeline model with a larger magnification. The low-resolution images can upscale gradually by passing through each Detail-Preserving Network until the final high-resolution images. Through extensive experiments on two scanning document image datasets, we demonstrate that the proposed approach outperforms recent state-of-the-art image super-resolution methods, and combining it with standard OCR system lead to signification improvements on the recognition results.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
