Real-world face recognition using a single sample per person (SSPP) is a challenging task. The problem is exacerbated if the conditions under which the gallery image and the probe set are captured are completely different. To address these issues from the perspective of domain adaptation, we introduce an SSPP domain adaptation network (SSPP-DAN). In the proposed approach, domain adaptation, feature extraction, and classification are performed jointly using a deep architecture with domain-adversarial training. However, the SSPP characteristic of one training sample per class is insufficient to train the deep architecture. To overcome this shortage, we generate synthetic images with varying poses using a 3D face model. Experimental evaluations using a realistic SSPP dataset show that deep domain adaptation and image synthesis complement each other and dramatically improve accuracy. Experiments on a benchmark dataset using the proposed approach show state-of-the-art performance. All the dataset and the source code can be found in our online repository (https://github.com/csehong/SSPP-DAN).
Omnidirectional depth sensing has its advantage over the conventional stereo systems since it enables us to recognize the objects of interest in all directions without any blind regions. In this paper, we propose a novel widebaseline omnidirectional stereo algorithm which computes the dense depth estimate from the fisheye images using a deep convolutional neural network. The capture system consists of multiple cameras mounted on a wide-baseline rig with ultrawide field of view (FOV) lenses, and we present the calibration algorithm for the extrinsic parameters based on the bundle adjustment. Instead of estimating depth maps from multiple sets of rectified images and stitching them, our approach directly generates one dense omnidirectional depth map with full 360°coverage at the rig global coordinate system. To this end, the proposed neural network is designed to output the cost volume from the warped images in the sphere sweeping method, and the final depth map is estimated by taking the minimum cost indices of the aggregated cost volume by SGM. For training the deep neural network and testing the entire system, realistic synthetic urban datasets are rendered using Blender. The experiments using the synthetic and real-world datasets show that our algorithm outperforms the conventional depth estimation methods and generate highly accurate depth maps.
In this paper, we propose a novel end-to-end deep neural network model for omnidirectional depth estimation from a wide-baseline multi-view stereo setup. The images captured with ultra wide field-of-view (FOV) cameras on an omnidirectional rig are processed by the feature extraction module, and then the deep feature maps are warped onto the concentric spheres swept through all candidate depths using the calibrated camera parameters. The 3D encoderdecoder block takes the aligned feature volume to produce the omnidirectional depth estimate with regularization on uncertain regions utilizing the global context information. In addition, we present large-scale synthetic datasets for training and testing omnidirectional multi-view stereo algorithms. Our datasets consist of 11K ground-truth depth maps and 45K fisheye images in four orthogonal directions with various objects and environments. Experimental results show that the proposed method generates excellent results in both synthetic and real-world environments, and it outperforms the prior art and the omnidirectional versions of the state-of-the-art conventional stereo algorithms.
The purpose of this study was to evaluate the typical ultrasonographic findings of transient small bowel intussusception (SBI) and to differentiate it from ileocolic intussusception (ICI) in paediatrics. 22 transient SBI (male:female = 13:9, age: 7-132 months (mean 38 months)) and 27 ICI (male:female = 19:8, age: 1-60 months (mean 13 months)) patients diagnosed on ultrasonography were retrospectively evaluated. The findings of location, diameter, thickness of outer rim, and inclusion of mesenteric lymph nodes within intussuscipiens were compared. In the transient SBI, the head of intussusception was located in the right lower quadrant (RLQ) in 11 (50%), the right upper quadrant (RUQ) in 2 (9.1%) and the periumbilical area in 9 (40.9%) cases. The anteroposterior (AP) diameter ranged from 0.84-2.4 cm (mean 1.38 cm), and thickness of outer rim ranged from 0.10-0.34 cm (mean 0.26 cm). No mesenteric lymph nodes were contained within the intussuscipiens. In the ICI, the head was located in the RUQ in 17 (63%), the epigastrium in 7 (25.9%) and the left upper quadrant in 3 (11.1%) cases. The AP diameter ranged from 1.89-3.32 cm (mean 2.53 cm), and the thickness of the outer rim ranged from 0.30-0.86 cm (mean 0.53 cm). Mesenteric lymph nodes were contained within the intussuscipiens in 26 (96.3%) cases. In conclusion, when compared with ICI, the transient SBI occurs predominantly in the RLQ or periumbilical region, has a smaller AP diameter, a thinner outer rim, and dose not contain mesenteric lymph nodes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.