Search

We propose a pipeline for combined multi-class object geolocation and height estimation from street level RGB imagery, which is considered as a single available input data modality. Our solution is formulated via Markov Random Field optimization with deterministic output. The proposed technique uses image metadata along with coordinates of objects detected in the image plane as found by a custom-trained Convolutional Neural Network. Computing the object height using our methodology, in addition to object geolocation, has negligible effect on the overall computational cost. Accuracy is demonstrated experimentally for water drains and road signs on which we achieve average elevation estimation error lower than 20cm.

Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. We propose to learn these filters as combinations of preset spectral filters defined by the Discrete Cosine Transform (DCT). Our proposed DCT-based harmonic blocks replace conventional convolutional layers to produce partially or fully harmonic versions of new or existing CNN architectures. Using DCT energy compaction properties, we demonstrate how the harmonic networks can be efficiently compressed by truncating high-frequency information in harmonic blocks thanks to the redundancies in the spectral domain. We report extensive experimental validation demonstrating benefits of the introduction of harmonic blocks into state-of-the-art CNN models in image classification, object detection and semantic segmentation applications.

Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. We propose to learn these filters as combinations of preset spectral filters defined by the Discrete Cosine Transform (DCT). Our proposed DCT-based harmonic blocks replace conventional convolutional layers to produce partially or fully harmonic versions of new or existing CNN architectures. Using DCT energy compaction properties, we demonstrate how the harmonic networks can be efficiently compressed by truncating high-frequency information in harmonic blocks thanks to the redundancies in the spectral domain. We report extensive experimental validation demonstrating benefits of the introduction of harmonic blocks into state-of-the-art CNN models in image classification, object detection and semantic segmentation applications.

In this paper we propose an approach to perform semantic segmentation of 3D point cloud data by importing the geographic information from a 2D GIS layer (OpenStreetMap). The proposed automatic procedure identifies meaningful units such as buildings and adjusts their locations to achieve best fit between the GIS polygonal perimeters and the point cloud. Our processing pipeline is presented and illustrated by segmenting point cloud data of Trinity College Dublin (Ireland) campus constructed from optical imagery collected by a drone., Comment: 8 pages

Estimation of the Digital Surface Model (DSM) and building heights from single-view aerial imagery is a challenging inherently ill-posed problem that we address in this paper by resorting to machine learning. We propose an end-to-end trainable convolutional-deconvolutional deep neural network architecture that enables learning mapping from a single aerial imagery to a DSM for analysis of urban scenes. We perform multisensor fusion of aerial optical and aerial light detection and ranging (Lidar) data to prepare the training data for our pipeline. The dataset quality is key to successful estimation performance. Typically, a substantial amount of misregistration artifacts are present due to georeferencing/projection errors, sensor calibration inaccuracies, and scene changes between acquisitions. To overcome these issues, we propose a registration procedure to improve Lidar and optical data alignment that relies on Mutual Information, followed by Hough transform-based validation step to adjust misregistered image patches. We validate our building height estimation model on a high-resolution dataset captured over central Dublin, Ireland: Lidar point cloud of 2015 and optical aerial images from 2017. These data allow us to validate the proposed registration procedure and perform 3D model reconstruction from single-view aerial imagery. We also report state-of-the-art performance of our proposed architecture on several popular DSM estimation datasets.

Estimation of the Digital Surface Model (DSM) and building heights from single-view aerial imagery is a challenging inherently ill-posed problem that we address in this paper by resorting to machine learning. We propose an end-to-end trainable convolutional-deconvolutional deep neural network architecture that enables learning mapping from a single aerial imagery to a DSM for analysis of urban scenes. We perform multisensor fusion of aerial optical and aerial light detection and ranging (Lidar) data to prepare the training data for our pipeline. The dataset quality is key to successful estimation performance. Typically, a substantial amount of misregistration artifacts are present due to georeferencing/projection errors, sensor calibration inaccuracies, and scene changes between acquisitions. To overcome these issues, we propose a registration procedure to improve Lidar and optical data alignment that relies on Mutual Information, followed by Hough transform-based validation step to adjust misregistered image patches. We validate our building height estimation model on a high-resolution dataset captured over central Dublin, Ireland: Lidar point cloud of 2015 and optical aerial images from 2017. These data allow us to validate the proposed registration procedure and perform 3D model reconstruction from single-view aerial imagery. We also report state-of-the-art performance of our proposed architecture on several popular DSM estimation datasets.

Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. We propose to learn these filters as combinations of preset spectral filters defined by the Discrete Cosine Transform (DCT). Our proposed DCT-based harmonic blocks replace conventional convolutional layers to produce partially or fully harmonic versions of new or existing CNN architectures. Using DCT energy compaction properties, we demonstrate how the harmonic networks can be efficiently compressed by truncating high-frequency information in harmonic blocks thanks to the redundancies in the spectral domain. We report extensive experimental validation demonstrating benefits of the introduction of harmonic blocks into state-of-the-art CNN models in image classification, object detection and semantic segmentation applications., Comment: arXiv admin note: substantial text overlap with arXiv:1812.03205

We show how parameter redundancy in Convolutional Neural Network (CNN) filters can be effectively reduced by pruning in spectral domain. Specifically, the representation extracted via Discrete Cosine Transform (DCT) is more conducive for pruning than the original space. By relying on a combination of weight tensor reshaping and reordering we achieve high levels of layer compression with just minor accuracy loss. Our approach is applied to compress pretrained CNNs and we show that minor additional fine-tuning allows our method to recover the original model performance after a significant parameter reduction. We validate our approach on ResNet-50 and MobileNet-V2 architectures for ImageNet classification task.

In mammals, leptin and tumor-necrosis factor (TNF) are prominent interacting adipokines mediating appetite control and insulin sensitivity. While TNF pleiotropically functions in immune defense and cell survival, leptin is largely confined to signaling energy stores in adipocytes. Knowledge about the function of avian leptin and TNF is limited and they are absent or lowly expressed in adipose, respectively. Employing radiation-hybrid mapping and FISH-TSA, we mapped TNF and its syntenic genes to chicken chromosome 16 within the major histocompatibility complex (MHC) region. This mapping position suggests that avian TNF has a role in regulating immune response. To test its possible interaction with leptin within the immune system and beyond, we compared the transcription patterns of TNF, leptin and their cognate receptors obtained by meta-analysis of GenBank RNA-seq data. While expression of leptin and its receptor (LEPR) were detected in the brain and digestive tract, TNF and its receptor mRNAs were primarily found in viral-infected and LPS-treated leukocytes. We confirmed leptin expression in the duodenum by immunohistochemistry staining. Altogether, we suggest that whereas leptin and TNF interact as adipokines in mammals, in birds, they have distinct roles. Thus, the interaction between leptin and TNF may be unique to mammals.

In mammals, leptin and tumor-necrosis factor (TNF) are prominent interacting adipokines mediating appetite control and insulin sensitivity. While TNF pleiotropically functions in immune defense and cell survival, leptin is largely confined to signaling energy stores in adipocytes. Knowledge about the function of avian leptin and TNF is limited and they are absent or lowly expressed in adipose, respectively. Employing radiation-hybrid mapping and FISH-TSA, we mapped TNF and its syntenic genes to chicken chromosome 16 within the major histocompatibility complex (MHC) region. This mapping position suggests that avian TNF has a role in regulating immune response. To test its possible interaction with leptin within the immune system and beyond, we compared the transcription patterns of TNF, leptin and their cognate receptors obtained by meta-analysis of GenBank RNA-seq data. While expression of leptin and its receptor (LEPR) were detected in the brain and digestive tract, TNF and its receptor mRNAs were primarily found in viral-infected and LPS-treated leukocytes. We confirmed leptin expression in the duodenum by immunohistochemistry staining. Altogether, we suggest that whereas leptin and TNF interact as adipokines in mammals, in birds, they have distinct roles. Thus, the interaction between leptin and TNF may be unique to mammals.

In mammals, leptin and tumor-necrosis factor (TNF) are prominent interacting adipokines mediating appetite control and insulin sensitivity. While TNF pleiotropically functions in immune defense and cell survival, leptin is largely confined to signaling energy stores in adipocytes. Knowledge about the function of avian leptin and TNF is limited and they are absent or lowly expressed in adipose, respectively. Employing radiation-hybrid mapping and FISH-TSA, we mapped TNF and its syntenic genes to chicken chromosome 16 within the major histocompatibility complex (MHC) region. This mapping position suggests that avian TNF has a role in regulating immune response. To test its possible interaction with leptin within the immune system and beyond, we compared the transcription patterns of TNF, leptin and their cognate receptors obtained by meta-analysis of GenBank RNA-seq data. While expression of leptin and its receptor (LEPR) were detected in the brain and digestive tract, TNF and its receptor mRNAs were primarily found in viral-infected and LPS-treated leukocytes. We confirmed leptin expression in the duodenum by immunohistochemistry staining. Altogether, we suggest that whereas leptin and TNF interact as adipokines in mammals, in birds, they have distinct roles. Thus, the interaction between leptin and TNF may be unique to mammals.

Single Image Super-Resolution (SISR) has witnessed a dramatic improvement in recent years through the use of deep learning and, in particular, convolutional neural networks (CNN). In this work we address reconstruction from low-resolution images and consider as well degrading factors in images such as blurring. To address this challenging problem, we propose a new architecture to tackle blur with the down-sampling of images by extending the DBSRCNN architecture [1]. We validate our new architecture (DBSR) experimentally against several state of the art super-resolution techniques.

Single Image Super-Resolution (SISR) has witnessed a dramatic improvement in recent years through the use of deep learning and, in particular, convolutional neural networks (CNN). In this work we address reconstruction from low-resolution images and consider as well degrading factors in images such as blurring. To address this challenging problem, we propose a new architecture to tackle blur with the down-sampling of images by extending the DBSRCNN architecture [1]. We validate our new architecture (DBSR) experimentally against several state of the art super-resolution techniques.

Convolutional neural networks (CNNs) are very popular nowadays for image processing. CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context. However this typically requires abundant labelled training data to estimate the filter parameters. Alternative strategies have been deployed for reducing the number of parameters and / or filters to be learned and thus decrease overfitting. In the context of reverting to preset filters, we propose here a computationally efficient harmonic block that uses Discrete Cosine Transform (DCT) filters in CNNs. In this work we examine the performance of harmonic networks in limited training data scenario. We validate experimentally that its performance compares well against scattering networks that use wavelets as preset filters.

Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. In contrast, in this paper we propose harmonic blocks that produce features by learning optimal combinations of responses to preset spectral filters. We rely on the use of the Discrete Cosine Transform filters which have excellent energy compaction properties and are widely used for image compression. The proposed harmonic blocks are intended to replace conventional convolutional layers to produce partially or fully harmonic versions of new or existing CNN architectures. We demonstrate how the harmonic networks can be efficiently compressed by exploiting redundancy in spectral domain and truncating high-frequency information. We extensively validate our approach and show that the introduction of harmonic blocks into state-of-the-art CNN models results in improved classification performance on CIFAR and ImageNet datasets.

Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. In contrast, in this paper we propose harmonic blocks that produce features by learning optimal combinations of responses to preset spectral filters. We rely on the use of the Discrete Cosine Transform filters which have excellent energy compaction properties and are widely used for image compression. The proposed harmonic blocks are intended to replace conventional convolutional layers to produce partially or fully harmonic versions of new or existing CNN architectures. We demonstrate how the harmonic networks can be efficiently compressed by exploiting redundancy in spectral domain and truncating high-frequency information. We extensively validate our approach and show that the introduction of harmonic blocks into state-of-the-art CNN models results in improved classification performance on CIFAR and ImageNet datasets.

Convolutional neural networks (CNNs) are very popular nowadays for image processing. CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context. However this typically requires abundant labelled training data to estimate the filter parameters. Alternative strategies have been deployed for reducing the number of parameters and / or filters to be learned and thus decrease overfitting. In the context of reverting to preset filters, we propose here a computationally efficient harmonic block that uses Discrete Cosine Transform (DCT) filters in CNNs. In this work we examine the performance of harmonic networks in limited training data scenario. We validate experimentally that its performance compares well against scattering networks that use wavelets as preset filters.

In mammals, leptin and tumor-necrosis factor (TNF) are prominent interacting adipokines mediating appetite control and insulin sensitivity. While TNF pleiotropically functions in immune defense and cell survival, leptin is largely confined to signaling energy stores in adipocytes. Knowledge about the function of avian leptin and TNF is limited and they are absent or lowly expressed in adipose, respectively. Employing radiation-hybrid mapping and FISH-TSA, we mapped TNF and its syntenic genes to chicken chromosome 16 within the major histocompatibility complex (MHC) region. This mapping position suggests that avian TNF has a role in regulating immune response. To test its possible interaction with leptin within the immune system and beyond, we compared the transcription patterns of TNF, leptin and their cognate receptors obtained by meta-analysis of GenBank RNA-seq data. While expression of leptin and its receptor (LEPR) were detected in the brain and digestive tract, TNF and its receptor mRNAs were primarily found in viral-infected and LPS-treated leukocytes. We confirmed leptin expression in the duodenum by immunohistochemistry staining. Altogether, we suggest that whereas leptin and TNF interact as adipokines in mammals, in birds, they have distinct roles. Thus, the interaction between leptin and TNF may be unique to mammals.

In mammals, leptin and tumor-necrosis factor (TNF) are prominent interacting adipokines mediating appetite control and insulin sensitivity. While TNF pleiotropically functions in immune defense and cell survival, leptin is largely confined to signaling energy stores in adipocytes. Knowledge about the function of avian leptin and TNF is limited and they are absent or lowly expressed in adipose, respectively. Employing radiation-hybrid mapping and FISH-TSA, we mapped TNF and its syntenic genes to chicken chromosome 16 within the major histocompatibility complex (MHC) region. This mapping position suggests that avian TNF has a role in regulating immune response. To test its possible interaction with leptin within the immune system and beyond, we compared the transcription patterns of TNF, leptin and their cognate receptors obtained by meta-analysis of GenBank RNA-seq data. While expression of leptin and its receptor (LEPR) were detected in the brain and digestive tract, TNF and its receptor mRNAs were primarily found in viral-infected and LPS-treated leukocytes. We confirmed leptin expression in the duodenum by immunohistochemistry staining. Altogether, we suggest that whereas leptin and TNF interact as adipokines in mammals, in birds, they have distinct roles. Thus, the interaction between leptin and TNF may be unique to mammals.

Convolutional neural networks (CNNs) are very popular nowadays for image processing. CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context. However this typically requires abundant labelled training data to estimate the filter parameters. Alternative strategies have been deployed for reducing the number of parameters and / or filters to be learned and thus decrease overfitting. In the context of reverting to preset filters, we propose here a computationally efficient harmonic block that uses Discrete Cosine Transform (DCT) filters in CNNs. In this work we examine the performance of harmonic networks in limited training data scenario. We validate experimentally that its performance compares well against scattering networks that use wavelets as preset filters.

We explore the applicability and limitations of a state-of-the-art object detection and geotagging system [4] applied to crowdsourced image data. Our experiments with imagery from Mapillary crowdsourcing platform demonstrate that with increasing amount of images, the detection accuracy is getting close to that obtained with high-end street level data. Nevertheless, due to excessive camera position noise, the estimated geolocation (position) of the detected object is less accurate on crowdsourced Mapillary imagery than with high-end street level imagery obtained by Google Street View.

Recently multiple high performance algorithms have been developed to infer high-resolution images from low-resolution image input using deep learning algorithms. The related problem of super-resolution from blurred or corrupted low-resolution images has however received much less attention. In this work, we propose a new deep learning approach that simultaneously addresses deblurring and super-resolution from blurred low resolution images. We evaluate the state-of-the-art super-resolution convolutional neural network (SR-CNN) architecture proposed in [1] for the blurred reconstruction scenario and propose a revised deeper architecture that proves its superiority experimentally both when the levels of blur are known and unknown a priori.

Abundant image and sensory data collected over the last decades represents an invaluable source of information for cataloging and monitoring of the environment. Fusion of heterogeneous data sources is a challenging but promising tool to efficiently leverage such information. In this work we propose a pipeline for automatic detection and geolocation of recurring stationary objects deployed on fusion scenario of street level imagery and LiDAR point cloud data. The objects are geolocated coherently using a fusion procedure formalized as a Markov random field problem. This allows us to efficiently combine information from object segmentation, triangulation, monocular depth estimation and position matching with LiDAR data. The proposed fusion approach produces object mappings robust to scenes reporting multiple object instances. We introduce a new challenging dataset of over 200 traffic lights in Dublin city centre and demonstrate high performance of the proposed methodology and its capacity to perform multi -sensor data fusion.

We explore the applicability and limitations of a state-of-the-art object detection and geotagging system [4] applied to crowdsourced image data. Our experiments with imagery from Mapillary crowdsourcing platform demonstrate that with increasing amount of images, the detection accuracy is getting close to that obtained with high-end street level data. Nevertheless, due to excessive camera position noise, the estimated geolocation (position) of the detected object is less accurate on crowdsourced Mapillary imagery than with high-end street level imagery obtained by Google Street View.

Abundant image and sensory data collected over the last decades represents an invaluable source of information for cataloging and monitoring of the environment. Fusion of heterogeneous data sources is a challenging but promising tool to efficiently leverage such information. In this work we propose a pipeline for automatic detection and geolocation of recurring stationary objects deployed on fusion scenario of street level imagery and LiDAR point cloud data. The objects are geolocated coherently using a fusion procedure formalized as a Markov random field problem. This allows us to efficiently combine information from object segmentation, triangulation, monocular depth estimation and position matching with LiDAR data. The proposed fusion approach produces object mappings robust to scenes reporting multiple object instances. We introduce a new challenging dataset of over 200 traffic lights in Dublin city centre and demonstrate high performance of the proposed methodology and its capacity to perform multi -sensor data fusion.

Many applications, such as autonomous navigation, urban planning, and asset monitoring, rely on the availability of accurate information about objects and their geolocations. In this paper, we propose the automatic detection and computation of the coordinates of recurring stationary objects of interest using street view imagery. Our processing pipeline relies on two fully convolutional neural networks: the first segments objects in the images, while the second estimates their distance from the camera. To geolocate all the detected objects coherently we propose a novel custom Markov random field model to estimate the objects’ geolocation. The novelty of the resulting pipeline is the combined use of monocular depth estimation and triangulation to enable automatic mapping of complex scenes with the simultaneous presence of multiple, visually similar objects of interest. We validate experimentally the effectiveness of our approach on two object classes: traffic lights and telegraph poles. The experiments report high object recall rates and position precision of approximately 2 m, which is approaching the precision of single-frequency GPS receivers.

Recently multiple high performance algorithms have been developed to infer high-resolution images from low-resolution image input using deep learning algorithms. The related problem of super-resolution from blurred or corrupted low-resolution images has however received much less attention. In this work, we propose a new deep learning approach that simultaneously addresses deblurring and super-resolution from blurred low resolution images. We evaluate the state-of-the-art super-resolution convolutional neural network (SR-CNN) architecture proposed in [1] for the blurred reconstruction scenario and propose a revised deeper architecture that proves its superiority experimentally both when the levels of blur are known and unknown a priori.

Many applications, such as autonomous navigation, urban planning, and asset monitoring, rely on the availability of accurate information about objects and their geolocations. In this paper, we propose the automatic detection and computation of the coordinates of recurring stationary objects of interest using street view imagery. Our processing pipeline relies on two fully convolutional neural networks: the first segments objects in the images, while the second estimates their distance from the camera. To geolocate all the detected objects coherently we propose a novel custom Markov random field model to estimate the objects’ geolocation. The novelty of the resulting pipeline is the combined use of monocular depth estimation and triangulation to enable automatic mapping of complex scenes with the simultaneous presence of multiple, visually similar objects of interest. We validate experimentally the effectiveness of our approach on two object classes: traffic lights and telegraph poles. The experiments report high object recall rates and position precision of approximately 2 m, which is approaching the precision of single-frequency GPS receivers.

Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. In contrast, in this paper we propose harmonic blocks that produce features by learning optimal combinations of spectral filters defined by the Discrete Cosine Transform. The harmonic blocks are used to replace conventional convolutional layers to construct partial or fully harmonic CNNs. We extensively validate our approach and show that the introduction of harmonic blocks into state-of-the-art CNN baseline architectures results in comparable or better performance in classification tasks on small NORB, CIFAR10 and CIFAR100 datasets.

Many applications such as autonomous navigation, urban planning and asset monitoring, rely on the availability of accurate information about objects and their geolocations. In this paper we propose to automatically detect and compute the GPS coordinates of recurring stationary objects of interest using street view imagery. Our processing pipeline relies on two fully convolutional neural networks: the first segments objects in the images while the second estimates their distance from the camera. To geolocate all the detected objects coherently we propose a novel custom Markov Random Field model to perform objects triangulation. The novelty of the resulting pipeline is the combined use of monocular depth estimation and triangulation to enable automatic mapping of complex scenes with multiple visually similar objects of interest. We validate experimentally the effectiveness of our approach on two object classes: traffic lights and telegraph poles. The experiments report high object recall rates and GPS accuracy within 2 meters, which is comparable with the precision of single-frequency GPS receivers., Comment: Video demo at https://youtu.be/X0tM_iSRJMw

Denial-of-Service attacks continue to be a serious problem for the Internet community despite the fact that a large number of defense approaches has been proposed by the research community. In this paper we introduce IP Fast Hopping, easily deployable and effective network-layer architecture against DDoS attacks. Our approach also provides an easy way for clients to hide content and destination server of theirs communication sessions. We describe a method of dynamic server IP address change and all modules necessary to implement the approach., Comment: 6 pages, 3 figures

Growth is a priority trait from the point of view of genetic improvement. Molecular markers linked to quantitative trait loci (QTL) have been regarded as useful for marker-assisted selection in complex traits as growth. Polymorphisms have been studied in five candidate genes influencing growth in gilthead seabream (Sparus aurata): the growth hormone (GH), insulin-like growth factor-1 (IGF-1), myostatin (MSTN-1), prolactin (PRL), and somatolactin (SL) genes. Specimens evaluated were from a commercial broodstock comprising 131 breeders (from which 36 males and 44 females contributed to the progeny). In all samples eleven gene fragments, covering more than 13,000 bp, generated by PCR-RFLP, were analyzed; tests were made for significant associations between these markers and growth traits. ANOVA results showed a significant association between MSTN-1 gene polymorphism and growth traits. Pairwise tests revealed several RFLPs in the MSTN-1 gene with significant heterogeneity of genotypes among size groups. PRL and MSTN-1 genes presented linkage disequilibrium. The MSTN-1 gene was mapped in the centromeric region of a medium-size acrocentric chromosome pair.