Object Texture Research Articles

The Method for Determining Informative Zones on Images from On-Board Surveillance Systems

The article focuses on the stage of determining information zones on images from on-board surveillance systems in order to provide information for their classification, necessary for further semantic segmentation and recognition. Information zones in the study are understood as zones where objects of interest are most likely to be found. Objects of interest can be elements of urban infrastructure (roads, streets, buildings, etc.), railway stations and tracks, dividing lines between different texture objects, objects (cars, equipment, military facilities, etc.). The main motivation for the study is the allocation of such information zones in order to reduce the time for image processing (improving the efficiency of image processing). The method for determining information zones on images of on-board surveillance systems has been improved. It consists of the following steps: processing the original image with Canny edge detector and using the Hough transform on the segmented image. The results of the work of this method are presented on the color image of the space-based surveillance systems and on the color image from an unmanned aerial vehicle. Visual assessment of the quality of the proposed method is satisfactory. A quantitative indicator of the quality of the method for determining information zones on images of on-board surveillance systems was calculated. Analysis of the quantitative indicator showed that this method for determining information zones on images of on-board surveillance systems makes it possible to increase the efficiency of further image processing by the operator interpreter for further semantic segmentation and recognition images.

Single-shot 3D shape reconstruction for complex surface objects with colour texture based on deep learning

Three-dimensional (3D) shape reconstruction based on structured light technique is one of the most crucial techniques in the field of optical measurement due to the nature of non-contact and high-precision. In recent years, researchers found that the deep-learning method can significantly improve the quality and efficiency of 3D reconstruction. So far, the research object of structured light 3D reconstruction technology related to deep-learning methods usually adopts plaster models. However, the surface of the reconstructed objects always contains rich colour texture information in a real-world scenario, which affects the accuracy of the reconstruction, especially for some single-shot applications. To solve the above problem, we propose a deep-learning-based method single-shot 3D reconstruction method (SSR) for colour textured objects, and it can reconstruct colour textured objects with high precision. The experimental results show that the proposed method provides good guidance for the practical application and scientific research of fringe projection profilometry based on colour textured objects.

Geographic Scene Understanding of High-Spatial-Resolution Remote Sensing Images: Methodological Trends and Current Challenges

As one of the primary means of Earth observation, high-spatial-resolution remote sensing images can describe the geometry, texture and structure of objects in detail. It has become a research hotspot to recognize the semantic information of objects, analyze the semantic relationship between objects and then understand the more abstract geographic scenes in high-spatial-resolution remote sensing images. Based on the basic connotation of geographic scene understanding of high-spatial-resolution remote sensing images, this paper firstly summarizes the keystones in geographic scene understanding, such as various semantic hierarchies, complex spatial structures and limited labeled samples. Then, the achievements in the processing strategies and techniques of geographic scene understanding in recent years are reviewed from three layers: visual semantics, object semantics and concept semantics. On this basis, the new challenges in the research of geographic scene understanding of high-spatial-resolution remote sensing images are analyzed, and future research prospects have been proposed.

TIPTAB: A tangible interactive projection tabletop for virtual experiments

AbstractVirtual experiments are a new way of doing experiments. A visible difference between virtual and real experiments is the interaction mode. Such a difference causes unfamiliarity and induces unnecessary cognitive load and inefficiency during learning. The objective of the research is to reduce the interactive operation difference between virtual and real experiments as much as possible. TIPTAB, a tangible interactive projection tabletop, is proposed for virtual experiments. A depth camera is used to detect tangible objects in the real environment. These objects are printed by three‐dimensional (3D) printers in advance and tracked in real‐time. The tracked 3D poses are then used as inputs for further experiments. Both object textures and scene contents are augmented by projectors, and thus the virtual presentation of digital space is seamlessly registered and fused with physical space. An infrared (IR) camera and an IR transmitter are used to detect finger touch operations on the tabletop. During experimental learning, students can interact without wearing any devices as they do in real experiments, which greatly reduces their interaction burdens. Experimental results show that the proposed method is more efficient compared with other representative interaction methods. Based on the cognitive load theory and the statistical data, TIPTAB has a low cognitive load for students during virtual experiments. Questionnaire survey results also indicate that TIPTAB offers a good learning experience.

Effective connectivity within the neural system for object-directed action representation during aware and unaware tool processing

Previous brain functional specialization evidence has shown that both aware and unaware visual processing of manipulable objects activate left premotor, parietal, and posterior temporal cortices, which are thought to constitute object-directed action and object-function processing streams. An open question is whether, both under supraliminal and subliminal processing conditions, there is directional spread of activation along these functional streams, leading to causal inter-regional connectivity effects. In this study, we used Dynamic Causal Modelling to estimate the effective connectivity influences within the premotor-parieto-temporal network, as a function of factorial contrasts for Manipulability (manipulable vs non-manipulable objects) and Perceptual Awareness (above vs below perceptual threshold). We modeled forward and backward connections originating from visual area V4, as a region underlying object texture segregation, and spreading through the left premotor-parieto-temporal network. Both above and below perceptual threshold, the visual processing of manipulable objects was associated with a specific increase of reciprocal effective connectivity coupling among left premotor-parieto-temporal regions. Aware and unaware manipulable object processing differed from each other for their distinct patterns of top-down activation enhancement exerted, in the former case, by left premotor-parieto-temporal regions on area V4 and, in the latter case, by left premotor on temporal regions. Although it is only under aware processing conditions that effective connectivity in the action representation system may promote object visual contour segregation in area V4, our results suggest that the encoding of object-action and object-function information can occur through left-hemispheric premotor, parietal, and temporal causal interdependencies, even when the object is not consciously perceived.

A novel image segmentation utilizing FUZZY-based LBP and active contour model

ABSTRACT This work presents an object recognition algorithm that combines local binary pattern (LBP) based on fuzzy logic approach and active contour model for segmenting different images to detect textured objects. Initially, images containing objects are segmented using the fuzzy logic-optimized LBP method. Then, we eliminate the image noise. Finally, utilizing a Chan-Vese active contour method, the target object of the image is highlighted. The segmentation has been compared with the classical LBP technique and the results indicated higher accuracy and quality for highlighting the object from the background. The classification of highlighted objects is performed with a convolution neural network (CNN). To authenticate the proposed approach, 140 images with the classification of 10 different objects were used. The simulation depicted that the proposed method has better results than other methods both in terms of segmentation error and performance. Significantly, CNN classification also showed a classification accuracy of 92.8%.

Sim2Air - Synthetic Aerial Dataset for UAV Monitoring

In this paper we propose a novel approach to generate a synthetic aerial dataset for application in UAV monitoring. We propose to accentuate shape-based object representation by applying texture randomization. A diverse dataset with photorealism in all parameters such as shape, pose, lighting, scale, viewpoint, etc. except for atypical textures is created in a 3D modelling software Blender. Our approach specifically targets two conditions in aerial images where texture of objects is difficult to detect, namely challenging illumination and objects occupying only a small portion of the image. Experimental evaluation of YOLO and Faster R-CNN detectors trained on synthetic data with randomized textures confirmed our approach by increasing the mAP value (17 and 3.7 percentage points for YOLO; 20 and 1.1 percentage points for Faster R-CNN) on two test datasets of real images, both containing UAV-to-UAV images with motion blur. Testing on different domains, we conclude that the more the generalisation ability is put to the test, the more apparent are the advantages of the shape-based representation.

Holograms of a 3D object synthesized at the receiving end of the communication channel in Dot Matrix technology

The manuscript presents experimental results on the recording and restoration of 3D holographic frames suitable for transmitting 3D holographic images with the frame rate required for TV images and the resolution of the Full HD standard and higher. The method is based on the previously proposed technology for recording and transmitting a depth map and surface texture of the holographic object over the communication channel and digital synthesis of the hologram at the receiving end of the communication channel. The obtained result reduces the frequency band required for the transmission of 3D holographic information, similar to SSB technology, since the carrier spatial frequency of the hologram in this method is not transmitted through the communication channel, but is synthesized in the hologram already at its receiving end. Experimental results of hologram synthesis at the receiving end of the communication channel in DotMatrix technology are presented. The method considered in this manuscript is convenient for multiplexing 3D images, transferring them from one part of the electromagnetic spectrum to another, as well as for creating hyperspectral images. The work implements the technology of a holographic phototelegraph, which, when using high-speed dynamic holographic monitors, can solve the problems of creating 3D TV and augmented reality.

Object Texture Recognition Based on Grasping Force Data Using Feedforward Neural Network

Object Texture Recognition Based on Grasping Force Data Using Feedforward Neural Network

Diffeomorphic transforms for data augmentation of highly variable shape and texture objects

Background and objective: Training a deep convolutional neural network (CNN) for automatic image classification requires a large database with images of labeled samples. However, in some applications such as biology and medicine only a few experts can correctly categorize each sample. Experts are able to identify small changes in shape and texture which go unnoticed by untrained people, as well as distinguish between objects in the same class that present drastically different shapes and textures. This means that currently available databases are too small and not suitable to train deep learning models from scratch. To deal with this problem, data augmentation techniques are commonly used to increase the dataset size. However, typical data augmentation methods introduce artifacts or apply distortions to the original image, which instead of creating new realistic samples, obtain basic spatial variations of the original ones.Methods: We propose a novel data augmentation procedure which generates new realistic samples, by combining two samples that belong to the same class. Although the idea behind the method described in this paper is to mimic the variations that diatoms experience in different stages of their life cycle, it has also been demonstrated in glomeruli and pollen identification problems. This new data augmentation procedure is based on morphing and image registration methods that perform diffeomorphic transformations.Results: The proposed technique achieves an increase in accuracy over existing techniques of 0.47%, 1.47%, and 0.23% for diatom, glomeruli and pollen problems respectively.Conclusions: For the Diatom dataset, the method is able to simulate the shape changes in different diatom life cycle stages, and thus, images generated resemble newly acquired samples with intermediate shapes. In fact, the other methods compared obtained worse results than those which were not using data augmentation. For the Glomeruli dataset, the method is able to add new samples with different shapes and degrees of sclerosis (through different textures). This is the case where our proposed DA method is more beneficial, when objects highly differ in both shape and texture. Finally, for the Pollen dataset, since there are only small variations between samples in a few classes and this dataset has other features such as noise which are likely to benefit other existing DA techniques, the method still shows an improvement of the results.

Fine Texture Detection Based on a Solid-Liquid Composite Flexible Tactile Sensor Array.

Surface texture information plays an important role in the cognition and manipulation of an object. Vision and touch are the two main methods for extracting an object’s surface texture information. However, vision is often limited since the viewing angle is uncertain during manipulation. In this article, we propose a fine surface texture detection method based on a stochastic resonance algorithm through a novel solid–liquid composite flexible tactile sensor array. A thin flexible layer and solid–liquid composite conduction structure on the sensor effectively reduce the attenuation of the contact force and enhance the sensitivity of the sensor. A series of ridge texture samples with different heights (0.9, 4, 10 μm), different widths (0.3, 0.5, 0.7, 1 mm), but the same spatial period (2 mm) of ridges were used in the experiment. The experimental results prove that the stochastic resonance algorithm can significantly improve the signal characteristic of the output signal of the sensor. The sensor has the capability to detect fine ridge texture information. The mean relative error of the estimation for the spatial period was 1.085%, and the ridge width and ridge height, respectively, have a monotonic mapping relationship with the corresponding model output parameters. The sensing capability to sense a fine texture of tactile senor surpasses the limit of human fingers.

The main methods of introducing design elements and graphics in video

The subject of the study is the process of many aspects of audiovisual creativity that must be taken into account when creating a video. The object of the work is to create a movie trailer through the use of design elements and graphics in the video sequence. The study examines the trailer of a post-apocalyptic fantasy genre called "Genesis", in which the two main characters are depicted as opposites. The work examines and describes in detail all the stages of creating a video trailer for the film, including visual representation (rendering the texture of the central objects, choosing a font to display the title of the film, controlling the movement of actors and moving frames), audio accompaniment of the video sequence (music, voiceover, sound effects). The paper notes that the main goal of all the stages of trailer development considered in the article is to create an audiovisual project of professional quality. The main methods used in the study are visual effects modeling and 3D modeling in Houdini, creating realistic matte paintings in Photoshop and video compositing in Nuke. The main conclusions of the study are those specialized programs that allow you to create a high-quality author's product. This software will become the core of the project, since it is in it that all the elements will be combined into one final clip due to the high-quality integration of various objects of the scene. The novelty of the research lies in the fact that within the framework of the work, the characteristics of the possibilities of working with various video editors and graphic programs were carried out, which together help the creators of movie trailers and other similar products to realize the tasks of entertainment and quality of the projects produced.

Multispectral and SAR Image Fusion Based on Laplacian Pyramid and Sparse Representation

Complementary information from multi-sensors can be combined to improve the availability and reliability of stand-alone data. Typically, multispectral (MS) images contain plentiful spectral information of the Earth’s surface that is beneficial for identifying land cover types, while synthetic aperture radar (SAR) images can provide abundant information on the texture and structure of target objects. Therefore, this paper presents a fusion framework to integrate the information from MS and SAR images based on the Laplacian pyramid (LP) and sparse representation (SR) theory. LP is performed to decompose both the multispectral and SAR images into high-frequency components and low-frequency components, so that different processing strategies can be applied to multi-scale information. Low-frequency components are merged based on SR theory, whereas high-frequency components are combined based on a certain activity-level measurement, identifying salient features. Finally, LP reconstruction is performed to obtain the integrated image. We conduct experiments on several datasets to verify the effectiveness of the proposed method. Both visual interpretation and statistical analyses demonstrate that the proposed method strikes a satisfactory balance between spectral information preservation and the enhancement of spatial and textual characteristics. In addition, a further discussion regarding the adjustability property of the proposed method shows its flexibility for further application scenarios.

Affective function of touch and the neurophysiological mechanism

<p id="p00005">Touch is an important sensory channel for individuals to explore the external world in everyday life. The sense of touch helps us to discriminate the location of a stimulus on the skin surface, to identify the shape, size and texture of objects. However, touch can also be affective. The motivational-affective dimension of touch is involved in coding its valence and motivational relevance. This aspect of tactile sensation plays an important role in maintaining social bonding and promoting interpersonal communication. <p id="p00006">The affective function of interpersonal touch can be achieved through unimodal presentations or multimodal information integration processing. That is, tactile action itself, either a strong handshake or a tender hug, can directly convey emotions. Although the accuracy of decoding six basic emotions (anger, fear, happiness, sadness, disgust, and surprise) from interpersonal touch are slightly less than from the facial expression and vocal information, interpersonal touch has advantages in conveying social emotions such as "love", "gratitude" and "sympathy". Such advantages reflect the important significance of affective touch in establishing social bonding and promoting cooperative relationships. Further more, the affective meaning and social attributes carried by interpersonal touch can provide social background for emotion of other modal （e.g., visual or auditory） information processing, so as to enhance participants’ attention and to sharpen their social evaluation of emotional cues. <p id="p00007">Compared with sensory-discriminative subsystem, the motivational-affective subsystem has a special neurophysiological mechanism. For example, C-tactile (CT) afferents are strongly implicated as the neurobiological substrate underlying the affective property of touch. CTs, a class of slowly conducting mechanoreceptors, are specially tuned to the properties of human physical contact. They fire maximally to skin-temperature, light-pressure stroking at a rate of 1-10 cm per s. C-tactile-mediated affective tactile stimulation project in spinothalamic tract (STT) pathway (the spinal signaling of orofacial C-fiber mediated affective touch is still unclear), bypass the primary somatosensory cortex, directly project to the insular cortex, and then process in the amygdala, medial prefrontal cortex (mPFC), posterior superior temporal sulcus (pSTS) and other core areas of the “social brain” neural network. In addition, evidence from EEG research shows that, beta oscillation at parietal scalp sites, may be related to the affective representation of tactile stimuli, and theta oscillation at frontal, parietal, temporal, occipital scalp sites, may reflect an attentional-emotional regulatory mechanism of affective touch. <p id="p00008">Another complex facet of touch is that, affective touch would be complicated by its inextricable links to context, gender and sexuality, culture, and other individual, interpersonal, and societal factors. Moreover, learned from the previous research on facial emotion perception, a considerable body of work about affective touch are also around the topic of coding-decoding of basic emotions, so that the results fail to fully reveal the specificity of tactile channel in transmitting social emotions. Therefore, we should pay more attention to top-down contextual factors in the future researches, such as personal relationship, cultural difference, and social context, that may influence how to define and interpret the emotion and motivation of interpersonal touch. Meanwhile, although the time course of emotional touch perception was explored with electrophysiological measures, however no clear index has been identified till now. In addition, in order to reveal the relevance and independence between the sensory-discriminative and motivational-affective subsystems, such as activation likelihood estimate (ALE) meta-analysis and meta-analytic connectivity modeling (MACM) analysis can be used to reveal the cortical functional neuroanatomy supporting a distinction between affective and discriminative touch.

Artist-specific style transfer for semantic segmentation of paintings: The value of large corpora of surrogate artworks

Deep neural networks for semantic segmentation have recently outperformed other methods for natural images, partly due to the abundance of training data for this case. However, applying these networks to pictures from a different domain often leads to a significant drop in accuracy. Fine art paintings for highly stylized works, such as from Cubism or Expressionism, in particular, are challenging due to large deviations in shape and texture of certain objects when compared to natural images. In this paper, we demonstrate that style transfer can be used as a form of data augmentation during the training of CNN based semantic segmentation models to improve the accuracy of semantic segmentation models in art pieces of a specific artist. For this, we pick a selection of paintings from a specific style for the painters Egon Schiele, Vincent Van Gogh, Pablo Picasso and Willem de Kooning, create stylized training dataset by transferring artist-specific style to natural photographs and show that training the same segmentation network on surrogate artworks improves the accuracy for fine art paintings. We also provide a dataset with pixel-level annotation of 60 fine art paintings to the public and for evaluation of our method.

Data-Driven Haptic Modeling and Rendering of Viscoelastic Behavior Using Fractional Derivatives

Data-driven modeling and rendering is a general approach in haptics aiming to provide highly accurate haptic perceptual experiences simulating complex real physical dynamics, such as deformable or textured objects. A prevalent problem in the present methods for data-driven haptics is that the computational cost for modeling grows rapidly, even becoming intractable, as the interaction complexity or the number of data increases. This paper proposes one data-driven method featured with greatly improved computational efficiency for modeling viscoelastic deformable objects. This advantage is enabled by the use of fractional derivatives for modeling features and regression forests for data-interpolation models. For the benchmark of normal interaction on deformable objects, we describe a computational framework for data-driven haptic modeling and rendering. Its performance is validated by physical experiments for modeling accuracy and cost and a perceptual experiment for the similarity between real and virtual objects. The experiments demonstrate that our method offers highly realistic haptic perceptual experiences with markedly better modeling cost (at least ten times) than other state-of-the-art methods.

Electrical Fault Detection Equipment Based on Infrared Image Fusion

Maintaining the safe and stable operation of power equipment is the first task of power system operation and maintenance. The equipment in normal operation may have various faults, so it needs to be located, detected and repaired. In order to improve the on-line detection efficiency of electrical equipment, diagnose the operation state of equipment in time and locate faults, this project proposes a multi focus infrared and visible image fusion algorithm based on NSST and adaptive PCNN. Taking the power equipment as the research object, the infrared image of the power equipment is compared with the visible image, and the feature points are selected, so as to realize the image registration. After image registration, the registered visible and infrared images are fused and reconstructed, and the effective features of the two kinds of images are integrated into one image. The target image constructed by fusion not only has thermal energy information, but also has object texture, highlights the target, and can detect the fault location without power failure. It has certain practical significance for quickly removing the fault point of power equipment.

FindNet: Can You Find Me? Boundary-and-Texture Enhancement Network for Camouflaged Object Detection.

Camouflaged objects share very similar colors but have different semantics with the surroundings. Cognitive scientists observe that both the global contour (i.e., boundary) and the local pattern (i.e., texture) of camouflaged objects are key cues to help humans find them successfully. Inspired by the cognitive scientist's observation, we propose a novel boundary-and-texture enhancement network (FindNet) for camouflaged object detection (COD) from single images. Different from most of existing COD methods, FindNet embeds both the boundary-and-texture information into the camouflaged object features. The boundary enhancement (BE) module is leveraged to focus on the global contour of the camouflaged object, and the texture enhancement (TE) module is utilized to focus on the local pattern. The enhanced features from BE and TE, which complement each other, are combined to obtain the final prediction. FindNet performs competently on various conditions of COD, including slightly clear boundaries but very similar textures, fuzzy boundaries but slightly differentiated textures, and simultaneous fuzzy boundaries and textures. Experimental results exhibit clear improvements of FindNet over fifteen state-of-the-art methods on four benchmark datasets, in terms of detection accuracy and boundary clearness. The code will be publicly released.

A Deep Learning Approach to Manage and Reduce Plastic Waste in the Oceans

The accumulation of plastic objects in the Earth’s environment will adversely affect wildlife, wildlife habitat, and humans. The huge amount of unrecycled plastic ends up in landfill and thrown into unregulated dump sites. In many cases, specifically in the developing countries, plastic waste is thrown into rivers, streams and oceans. In this work, we employed the power of deep learning techniques in image processing and classification to recognize plastic waste. Our work aims to identify plastic texture and plastic objects in images in order to reduce plastic waste in the oceans, and facilitate waste management. For this, we use transfer learning in two ways: in the first one, a pre-trained CNN model on ImageNet is used as a feature extractor, then an SVM classifier for classification, the second strategy is based on fine tuning the pre-trained CNN model. Our approach was trained and tested using two (02) challenging datasets one is a texture recognition dataset and the other is for object detection, and achieves very satisfactory results using two (02) deep learning strategies.

Performance analysis of texture characterization techniques for lung nodule classification

Lung cancer ranks very high on a global index for cancer-related casualties. With early detection of lung cancer, the rate of survival increases to 80-90%. The standard method for diagnosing lung cancer from Computed Tomography (CT) scans is by manual annotation and detection of the cancerous regions, which is a tedious task for radiologists. This paper proposes a machine learning approach for multi-class classification of the lung nodules into solid, semi-solid, and Ground Glass Object texture classes. We employ feature extraction techniques, such as gray-level co-occurrence matrix, Gabor filters, and local binary pattern, and validate the performance on the LNDb dataset. The best performing classifier displays an accuracy of 94% and an F1-score of 0.92. The proposed approach was compared with related work using the same dataset. The results are promising, and the proposed method can be used to diagnose lung cancer accurately.