Topic
Upsampling
About: Upsampling is a research topic. Over the lifetime, 2426 publications have been published within this topic receiving 57613 citations.
Papers published on a yearly basis
Papers
More filters
TL;DR: A novel upsampling theory which is based on almost-causal finite impulse response (FIR) filters is developed, which can be implemented on lower-cost hardware and perform quite well compared to more expensive systems.
Abstract: Frequency-modulated continuous wave (FMCW) radars are an important class of radar systems, and they are quite popular because of their simpler architecture and lower cost. A fundamental problem in FMCW radars is the nonlinearity of the voltage-controlled oscillator (VCO), which results in a range of measurement errors, problems in multitarget detection, and degradation in synthetic aperture radar (SAR) images. In this paper, we first introduce a novel upsampling theory, then propose new algorithms to improve range accuracy and multitarget detection capability. These improvements are demonstrated both by simulations and actual lab experiments on a 2.4 GHz radar system. There are several techniques reported in the literature for VCO nonlinearity correction, but what makes the proposed approach different is that we focus on real-time processing on low-cost hardware and optimize the design subject to this constraint. We first developed an optimal upsampling theory which is based on almost-causal finite impulse response (FIR) filters. Compared to the sinc-based noncausal interpolation-based upsamplers, the proposed approach is based on using interpolation filters with few number of coefficients. Furthermore, interpolators are trained for a specific class of signals rather than a highly general signal set. Therefore, the proposed approach can be implemented on lower-cost hardware and perform quite well compared to more expensive systems.
16 citations
TL;DR: An upscaling method taking advantage of convolutional neural networks (CNNs) and downsampling techniques showed a satisfying match between the dynamic behaviour of the upscaled model through CNNs and high-resolution properties with a significant reduction of computational cost and time.
16 citations
01 Jan 2015
TL;DR: A new sensor fusion approach called Combined Bilateral Filter (CBF) together with the new Depth Discontinuity Preservation (DDP) post processing, which combine the information of a depth and a color sensor is proposed.
Abstract: Highly accurate depth images at video frame rate are required in many areas of computer vision, such as 3D reconstruction, 3D video capturing or manufacturing. Nowadays low cost depth cameras, which deliver a high frame rate, are widely spread but suffer from a high level of noise and a low resolution. Thus, a sophisticated real time upsampling algorithm is strongly required. In this paper we propose a new sensor fusion approach called Combined Bilateral Filter (CBF) together with the new Depth Discontinuity Preservation (DDP) post processing, which combine the information of a depth and a color sensor. Thereby we especially focus on two drawbacks that are common in related algorithms namely texture copying and upsampling without depth discontinuity preservation. The output of our algorithm is a higher resolution depth image with essentially reduced noise, no aliasing effects, no texture copying and very sharply preserved edges. In a ground truth comparison our algorithm was able to reduce the mean error up to 73% within around 30ms. Furthermore, we compare our method against other state of the art algorithms and obtain superior results.
16 citations
04 May 2020
TL;DR: In this paper, a fixed convolutional layer with an order of smoothness was proposed to avoid checkboard artifacts in CNNs, where the smoothness of its filter kernel can be controlled by a parameter.
Abstract: In this paper, we propose a fixed convolutional layer with an order of smoothness not only for avoiding checkerboard artifacts in convolutional neural networks (CNNs) but also for enhancing the performance of CNNs, where the smoothness of its filter kernel can be controlled by a parameter. It is well-known that a number of CNNs generate checkerboard artifacts in both of two process: forward-propagation of upsampling layers and backward-propagation of strided convolutional layers. The proposed layer can perfectly prevent checkerboard artifacts caused by strided convolutional layers or upsampling layers including transposed convolutional layers. In an image-classification experiment with four CNNs: a simple CNN, VGG8, ResNet-18, and ResNet-101, applying the fixed layers to these CNNs is shown to improve the classification performance of all CNNs. In addition, the fixed layer are applied to generative adversarial networks (GANs), for the first time. From image-generation results, a smoother fixed convolutional layer is demonstrated to enable us to improve the quality of images generated with GANs.
16 citations
TL;DR: Li et al. as mentioned in this paper proposed an improved 3D object detection method based on a two-stage detector called the Improved Point-Voxel Region Convolutional Neural Network (IPV-RCNN), which contains online training for data augmentation, upsampling convolution and k-means clustering for the bounding box to achieve 3D detection tasks from raw point clouds.
Abstract: Recently, 3D object detection based on deep learning has achieved impressive performance in complex indoor and outdoor scenes. Among the methods, the two-stage detection method performs the best; however, this method still needs improved accuracy and efficiency, especially for small size objects or autonomous driving scenes. In this paper, we propose an improved 3D object detection method based on a two-stage detector called the Improved Point-Voxel Region Convolutional Neural Network (IPV-RCNN). Our proposed method contains online training for data augmentation, upsampling convolution and k-means clustering for the bounding box to achieve 3D detection tasks from raw point clouds. The evaluation results on the KITTI 3D dataset show that the IPV-RCNN achieved a 96% mAP, which is 3% more accurate than the state-of-the-art detectors.
16 citations