Object Categories Research Articles

Industrial defect detection and location based on greedy membrane clustering algorithm

This paper introduces a related model of membrane calculation in the defect detection and positioning of industrial components. It has the characteristics of distributed and parallel computing, and can efficiently search for better solutions in a given feature space. Inspired by the membrane clustering algorithm, this paper proposes a greedy membrane clustering algorithm and names it GMCA. GMCA is applied after the extraction of local features of normal samples. It uses a greedy strategy to construct a sub-feature set that describes the local characteristics of normal samples. During training, GMCA can learn the membrane cluster center of normal image blocks and each sub-feature within the cluster. At test time, the anomaly map is obtained by calculating the distance from the test sample block to the corresponding cluster center and the maximum distance from the cluster center to the nearest neighbor in the training sample. This solves the limitation of traditional algorithms requiring dataset alignment. In the unsupervised dataset MvTec AD, samples can be divided into object categories and texture categories according to the background of images. The pixel-level anomaly location index (AUROC) of this method on object category data reaches 98.3%. The image-level anomaly detection index (AUROC) on texture category data reaches 99.1%.

Children and adults privilege linguistic over visual information when creating comparison classes for prenominal gradable adjectives

Mastering the semantics of gradable adjectives is a complex acquisition task, since their interpretation requires the calculation of a threshold relative to a comparison class. Context plays a role in determining the comparison class in multiple ways; empirical research has focused on non-linguistic cues, such as world knowledge and visual context, and less on linguistic cues, such as the modified head noun. The present study is the first to examine how preschoolers and adults use the taxonomic category encoded by the modified head noun as well as visual cues to interpret relative (big, small) and absolute (clean, dirty) gradable adjectives. Using existing objects from different taxonomic categories (basic-level and superordinate-level), we developed a picture-choice task that allowed us to infer the comparison class and the threshold from participants’ choices. Forty-three children (aged 3 to 5) and 26 adults, all monolingual German-speaking, were tested. Confirming previous research, children, like adults, showed a context-sensitive interpretation of relative but not of absolute gradable adjectives. The taxonomic label was preferred to visual cues in creating the comparison class already by age three; this advantage of linguistic over non-linguistic information was also present in the adults. We explain this finding with the privileged role of information provided by the taxonomic label: the modified head noun encodes the cognitive representation of an object category and the corresponding taxonomic hierarchy. Accordingly, this representation is easily accessible while creating the comparison class, which provides further evidence that language is a powerful tool to modulate our mental computations.

Decay pattern of SARS-CoV-2 RNA surface contamination in real residences

The COVID-19 pandemic has provided valuable lessons that deserve deep thought to prepare for the future. The decay pattern of surface contamination by SARS-CoV-2 RNA in the residences of COVID-19 patients is important but still unknown. We collected 2,233 surface samples from 21 categories of objects in 141 residences of COVID-19 patients in Shanghai when attacked by the omicron variant in spring 2022. Several characteristics of the patients and their residences were investigated to identify relevant associations. The decay of contamination was explored to determine the persistence. Approximately 8.7% of the surface samples were tested positive for SARS-CoV-2 RNA. The basin, water tap, and sewer inlet had the highest positive rates, all exceeding 20%. Only time was significantly associated with the level of surface contamination with SARS-CoV-2, showing a negative association. The decrease fit a first-order decay model with a decay rate of 0.77 ± 0.07 day−1, suggesting a 90% reduction in three days. Positive associations between the cumulative number of newly diagnosed patients in the same building and the positive rate of SARS-CoV-2 RNA in the public corridor were significant during the three days. Our results, in conjunction with the likely lower infectivity or viability, demonstrate that fomite transmission played a limited role in COVID-19 spread. The time determined SARS-CoV-2 RNA contamination, which was reduced by three days. This study is the first to show the decay patterns of SARS-CoV-2 contamination in real residential environments, providing insight into the patterns of transmission, as well as community-based prevention and control of similar threats.

Industrial defect detection and location based on greedy particle swarm optimization algorithm

ABSTRACT Particle swarm optimization algorithm is a branch of evolutionary computing and can search for a better solution in a given feature space. This paper introduces the particle swarm optimization algorithm and greedy strategy for the defect detection and location of industrial components and then proposes a greedy particle swarm optimization algorithm. This paper employs sparse random projection to map the vast high-dimensional information to the low-dimensional space while maintaining the relative distance between the data. This employment helps to accelerate the training and prediction speed of the model and remove some unimportant features or noise. This algorithm first adopts particle swarm optimization (PSO) to initialize the cluster centers in an effort to minimize the maximum distance between all unlabeled data points and these centers. The algorithm then utilizes the greedy strategy to select a batch of data points to represent the corresponding features of the normal image, thereby improving the coverage of the model to the data. Experiments have shown that the results of most categories of data sets are close to or better than the current existing methods, especially in defect detection. In terms of defect localization for object categories, our method achieves a pixel-level anomaly localization index (AUROC) of 98.3% on the MVTec AD dataset.

An examination of measures of young children's interest in natural object categories

Developmental research utilizes various different methodologies and measures to study the cognitive development of young children; however, the reliability and validity of such measures have been a critical issue in all areas of research practices. To address this problem, particularly in the area of research on infants' interests, we examined the convergent validity of previously reported measures of children's interests in natural object categories, as indexed by (1) parents' estimation of their child's interest in the categories, (2) extrinsic (overt choices in a task), (3) intrinsic (looking time toward objects), and (4) physiological (pupil dilation) responses to objects of different categories. Additionally, we also examined the discriminant validity of all the aforementioned measures against the well-established and validated measure of parents' estimations of children's vocabulary knowledge. Children completed two tasks: (a) an eye-tracking task, where they were presented with images from a range of defined categories, which collected indices of looking time and pupillary activity; (b) a sticker-choice task, where they were asked to choose between two sticker-images from two different categories belonging to the range of categories assessed in the previous task. Parents completed two questionnaires to estimate (i) their child's interests and (ii) vocabulary knowledge in the categories presented. We first analyzed the discriminant validity between the two parent measures, and found a significant positive association between them. Our successive analyses showed no strong or significant associations between any of our measures, apart from a significant positive association between children's looking time and parents' estimations of children's vocabulary knowledge. From our findings, we conclude that measures of infants' interests thus far may not have sufficient reliability to adequately capture any potential relationship between these measures, or index different components of interest in young children. We suggest next steps for further validation studies in infant research.

An efficient algorithm for multi-scale maritime object detection and recognition

Due to the complexity of the maritime environment and the diversity of the volume and shape of monitored objects in the maritime, existing object detection algorithms based on Convolutional Neural Networks (CNN) are challenging to balance the requirements of high accuracy and high real-time simultaneously in the field of maritime object detection. In response to the characteristics of complex backgrounds, significant differences in object size between categories, and the characteristic of having a large number of small objects in maritime surveillance videos and images, the Maritime dataset with rich scenes and object categories was self-made, and the OS-YOLOv7 algorithm was proposed based on the YOLOv7 algorithm. Firstly, a feature enhancement module named the TC-ELAN module based on the self-attention mechanism was designed, which enables the feature map used for detection to obtain enhanced semantic information fused from multiple scale features. Secondly, in order to enhance the attention to the area of dense small objects and further improve the positioning accuracy of occluded small objects, this study redesigned the SPPCSPC structure. Then, the network structure was improved to alleviate the problem of decreased object detection accuracy caused by the loss of semantic feature information. Finally, experimental results on self-made datasets and mainstream maritime object detection datasets show that OS-YOLOv7 has a better object detection effect compared to other state-of-the-art (SOTA) object detection algorithms at the cost of reasonable inference time and parameter quantity and can achieve good object detection accuracy on mainstream datasets with high real-time performance.

Measuring object recognition ability: Reliability, validity, and the aggregate z-score approach.

Measurement of domain-general object recognition ability (o) requires minimization of domain-specific variance. One approach is to model o as a latent variable explaining performance on a battery of tests which differ in task demands and stimuli; however, time and sample requirements may be prohibitive. Alternatively, an aggregate measure of o can be obtained by averaging z-scores across tests. Using data from Sunday et al., Journal of Experimental Psychology: General, 151, 676-694, (2022), we demonstrated that aggregate scores from just two such object recognition tests provide a good approximation (r = .79) of factor scores calculated from a model using a much larger set of tests. Some test combinations produced correlations of up to r = .87 with factor scores. We then revised these tests to reduce testing time, and developed an oddoneout task, using a unique object category on nearly every trial, to increase task and stimuli diversity. To validate our measures, 163 participants completed the object recognition tests on two occasions, one month apart. Providing the first evidence that o is stable over time, our short aggregate o measure demonstrated good test-retest reliability (r = .77). The stability of o could not be completely accounted for by intelligence, perceptual speed, and early visual ability. Structural equation modeling suggestedthat our tests load significantly onto the same latent variable, and revealed that as a latent variable, o is highly stable (r = .93). Aggregation is an efficient method for estimating o, allowing investigation of individual differences in object recognition ability to be more accessible in future studies.

Human Visual Cortex and Deep Convolutional Neural Network Care Deeply about Object Background.

Deep convolutional neural networks (DCNNs) are able to partially predict brain activity during object categorization tasks, but factors contributing to this predictive power are not fully understood. Our study aimed to investigate the factors contributing to the predictive power of DCNNs in object categorization tasks. We compared the activity of four DCNN architectures with EEG recordings obtained from 62 human participants during an object categorization task. Previous physiological studies on object categorization have highlighted the importance of figure-ground segregation-the ability to distinguish objects from their backgrounds. Therefore, we investigated whether figure-ground segregation could explain the predictive power of DCNNs. Using a stimulus set consisting of identical target objects embedded in different backgrounds, we examined the influence of object background versus object category within both EEG and DCNN activity. Crucially, the recombination of naturalistic objects and experimentally controlled backgrounds creates a challenging and naturalistic task, while retaining experimental control. Our results showed that early EEG activity (< 100 msec) and early DCNN layers represent object background rather than object category. We also found that the ability of DCNNs to predict EEG activity is primarily influenced by how both systems process object backgrounds, rather than object categories. We demonstrated the role of figure-ground segregation as a potential prerequisite for recognition of object features, by contrasting the activations of trained and untrained (i.e., random weights) DCNNs. These findings suggest that both human visual cortex and DCNNs prioritize the segregation of object backgrounds and target objects to perform object categorization. Altogether, our study provides new insights into the mechanisms underlying object categorization as we demonstrated that both human visual cortex and DCNNs care deeply about object background.

NIMBY or YIMBY? Understanding the complex relationships between foreign military bases and host societies

Abstract Based on a scoping review of English-language scientific literature for the period of 1990–2022, the article presents a synthetic outline of previous research, focusing on factors influencing the specifics of foreign military bases (FMBs) as examples of facilities that mostly generate negative attitudes known as ‘Not In My Backyard’ (NIMBY). The specific characteristics of different categories of objects that generate various social attitudes are also presented. The results of the analyses include a classification of factors and aspects related to the local impacts of foreign military bases, which have not been analysed before.

Shxwelí li te shxwelítemelh xíts'etáwtxw: The museum's confinement of Indigenous kin

AbstractAcross the globe, museums filled with glass and plexiglass vitrines display collections of Indigenous belongings. The typical display scenario for such belongings places them upon plinths, underneath plexiglass. These cases render the life they contain into objects of display, things to be seen but not touched. For Indigenous people, experiencing this objectifying system of display is often traumatic because that which is on display fits neither category of object nor thing. They hold life, and are beings or ancestors; they are treated as kin. Alongside the life of ancestors who take material form, thousands of Indigenous songs collected by ethnographers on wax cylinder recordings and reel‐to‐reel tape are similarly confined in museum collections. These songs also hold life, but of different kinds from their material cousins. To reassess the role of the museum as a place that confines life is to put into question its relationship to incarceration. If the museum is a carceral space, how then, might we define repatriation alongside practices of “reentry” and kinship reconnection?

Hyperspectral Image Classification Using Multi-Scale Lightweight Transformer

The distinctive feature of hyperspectral images (HSIs) is their large number of spectral bands, which allows us to identify categories of ground objects by capturing discrepancies in spectral information. Convolutional neural networks (CNN) with attention modules effectively improve the classification accuracy of HSI. However, CNNs are not successful in capturing long-range spectral–spatial dependence. In recent years, Vision Transformer (VIT) has received widespread attention due to its excellent performance in acquiring long-range features. However, it requires calculating the pairwise correlation between token embeddings and has the complexity of the square of the number of tokens, which leads to an increase in the computational complexity of the network. In order to cope with this issue, this paper proposes a multi-scale spectral–spatial attention network with frequency-domain lightweight Transformer (MSA-LWFormer) for HSI classification. This method synergistically integrates CNN, attention mechanisms, and Transformer into the spectral–spatial feature extraction module and frequency-domain fused classification module. Specifically, the spectral–spatial feature extraction module employs a multi-scale 2D-CNN with multi-scale spectral attention (MS-SA) to extract the shallow spectral–spatial features and capture the long-range spectral dependence. In addition, The frequency-domain fused classification module designs a frequency-domain lightweight Transformer that employs the Fast Fourier Transform (FFT) to convert features from the spatial domain to the frequency domain, effectively extracting global information and significantly reducing the time complexity of the network. Experiments on three classic hyperspectral datasets show that MSA-LWFormer has excellent performance.

Few-shot segmentation based on multi-level and cross-scale clustering

The problem of image segmentation with few-shot learning is addressed in this paper, which is a challenging task due to the lack of sufficient high-precision annotated data. A novel method that consists of two modules is proposed: a multi-level fuzzy clustering guidance module and a cross-scale feature fusion module. The former module can extract image features in a class-independent feature space and fuse them with different scale information, while the latter module can reduce the information loss caused by cross-scale transmission. The feature association map between the support image and the query image can be learned by the proposed method, and the inconsistency of target object categories can be overcome. The proposed method is evaluated on Pascal and COCO datasets, and it is shown that it outperforms the state-of-the-art algorithms in both one-shot and k-shot segmentation scenarios.

Object Knowledge Integration for Skeleton-Based Action Recognition

3D-Skeleton-based action recognition has been widely adopted due to its efficiency and robustness to complex backgrounds. While it is capable of conveying a significant amount of information regarding the dynamics of human poses, we argue that its performance is curtailed when confronted with actions involving interactions between humans and objects due to the absence of the study of the surrounding objects. It is of great importance to delve deeper into the study of human-object interactions for skeleton-based action recognition. This paper proposes a novel approach to represent the spatial-temporal skeleton features, along with the present nearby objects and their dynamics. To accomplish this, a new formulation named object knowledge is presented, which entails the categorization of object characteristics, based on whether or not the object necessitates a motion analysis. With a piece of prior knowledge, in cases where it is required, the motion is calculated, while for those where it is not necessary, only the category of object is considered. This object knowledge is then early-fusion along with the skeleton representation, in such a way that it fits into the self-attention model. The experimental results on different popular action recognition datasets (NTU RGB+D 60, NTU RGB+ D 120 illustrate that the proposed approach outperforms the current state-of-the-art methods.

Few-shot object detection: Research advances and challenges

Object detection as a subfield within computer vision has achieved remarkable progress, which aims to accurately identify and locate a specific object from images or videos. Such methods rely on large-scale labeled training samples for each object category to ensure accurate detection, but obtaining extensive annotated data is a labor-intensive and expensive process in many real-world scenarios. To tackle this challenge, researchers have explored few-shot object detection (FSOD) that combines few-shot learning and object detection techniques to rapidly adapt to novel objects with limited annotated samples. This paper presents a comprehensive survey to review the significant advancements in the field of FSOD in recent years and summarize the existing challenges and solutions. Specifically, we first introduce the background and definition of FSOD to emphasize potential value in advancing the field of computer vision. We then propose a novel FSOD taxonomy method and survey the plentifully remarkable FSOD algorithms based on this fact to report a comprehensive overview that facilitates a deeper understanding of the FSOD problem and the development of innovative solutions. Finally, we discuss the advantages and limitations of these algorithms to summarize the challenges, potential research direction, and development trend of object detection in the data scarcity scenario.

Robust Classification and 6D Pose Estimation by Sensor Dual Fusion of Image and Point Cloud Data

It is an important aspect to fully leverage complementary sensors of images and point clouds for objects classification and six-dimensional (6D) pose estimation tasks. Prior works extract objects category from a single sensor such as RGB camera or LiDAR, limiting their robustness in the event that a key sensor is severely blocked or fails. In this work, we present a robust objects classification and 6D object pose estimation strategy by dual fusion of image and point cloud data. Instead of solely relying on 3D proposals or mature 2D object detectors, our model deeply integrates 2D and 3D information of heterogeneous data sources by a robustness dual fusion network and an attention-based nonlinear fusion function Attn-fun(.), achieving efficiency as well as high accuracy classification for even missed some data sources. Then, our method is also able to precisely estimate the transformation matrix between two input objects by minimizing the feature difference to achieve 6D object pose estimation, even under strong noise or with outliers. We deploy our proposed method not only to ModelNet40 datasets but also to a real fusion vision rotating platform for tracking objects in outer space based on the estimated pose.

IDENTIFICATION OF LARD ON PROCESSED PRODUCTS IN MEDAN CITY USING UV SPECTROPHOTOMETER WITH LINEAR DISCRIMINANT ANALYSIS AND PRINCIPAL COMPONENT ANALYSIS METHODS

Objective: Processed meat products are highly popular among the community. However, deceptive traders sometimes adulterate these products with pork elements, necessitating thorough inspections. The qualitative detection of lard in processed products can be analyzed using UV spectrophotometry with chemometric techniques such as Linear Discriminant Analysis and Principal Component Analysis. These methods facilitate data analysis derived from spectra and wavelengths, enabling the categorization of objects and providing high accuracy.&#x0D; Methods: This study aimed to determine whether processed products in Medan contain lard using UV spectrophotometry, Linear Discriminant Analysis, and Principal Component Analysis methods.&#x0D; Results: The highest fat yield was obtained from lard at 14.24%, while the lowest was from chicken fat at 7.00%. The maximum wavelength results for control samples were 234 nm for chicken fat, 237 nm for beef fat, and 268 nm for lard. Data processing using Linear Discriminant Analysis and Principal Component Analysis showed that the processed products of three random samples, nugget, meatball, and sausage type A and C, fell within the same quadrant as chicken fat. Meatball and sausage type B were in the same quadrant as beef fat.&#x0D; Conclusion: Based on the identification of lard in processed products in Medan City using UV spectrophotometer by LDA and PCA, all random samples of nuggets, meatballs, and sausages do not contain lard, and this method can classify chicken fat, beef fat, lard well.

ОСОБЕННОСТИ ИССЛЕДОВАНИЯ ПОЖАРОВ, СВЯЗАННЫХ СО ВЗРЫВАМИ ТОПЛИВОВОЗДУШНЫХ СМЕСЕЙ

Explosions of fuel-air mixtures and their accompanying fires are perhaps the most common emergencies. A high probability of this kind of emergency is typical for both industrial facilities and the residential sector.&#x0D; When studying fires associated with deflagration (explosive) gorenje fuel-air mixtures, experts often face a number of questions that are difficult to solve when using the standard methodological approach used in the study of a classic fire. The article presents an expert analysis of fires caused by the ignition (explosion) of a fuel-air mixture. The paper also presents statistics of fires associated with explosions of fuel-air mixtures over the past five years, which provides data on the categories of objects and the nature of fuel-air mixtures.

Rights of Nature? Shifting Patterns in Environmental Constitutionalism1

Abstract The article outlines improvements in environment and climate protection in constitutional law and practice all over the world, examining constitutional texts, case law and constitution-like legislation. A legal standing of individuals to defend the environment is increasingly added to programmatic provisions addressed to public authorities. In some cases Nature is granted legal personality. The latter innovation connects well to traditions established in the global South, where it was introduced first, but not so to legal systems of the Occident, where it was recently introduced for the first time. In strictly legal terms the effects of this innovation can also be achieved by classical legal instruments, while its metaphoric dimension promises a change in people’s attitudes towards nature. A second innovation concerns the shift from an anthropocentric to a bio-cultural or ecocentric approach. This would render constitutional law on the environment fully effective and convey a substantive meaning to a personalised concept of Nature. Such a development is, however, uncertain. The rights of Nature risk remaining trapped in anthropocentric categories of subject and object of law when transposed to Occidental legal thinking and practice. To avoid such inadvertent contradictions, the article pleads for reconciling both approaches by seeking more equilibrium in the Human-Nature relationship.

Commentary

Greer offers an excellent primer on some Black Studies scholars’ critiques of humanism, for which he uses the label ‘counter-humanism’ after Erasmus (2020), distinguishing these approaches from ‘posthumanism.’ He identifies two primary strains of posthumanism relevant to archaeological interpretation, symmetrical archaeology and posthuman feminism, though examples of the latter are drawn from a broader body of academic literature and are subject to less critique. Posthumanists are shown to prioritize dismantling a human–object divide, while counter-humanists critique the human–non-human split. This may appear to be more or less the same project, but the framing of ‘A/not-A’ rather than ‘A–B’ emphasizes the hegemonic relationships between these categories, the continuity within, and makes more explicit the fact that people are included in both the non-human and object categories.

Words and arbitrary actions in early object categorization: weak evidence for a word advantage.

Both words and gestures have been shown to influence object categorization, often even overriding perceptual similarities to cue category membership. However, gestures are often meaningful to infants while words are arbitrarily related to an object they refer to, more similar to arbitrary actions that can be performed on objects. In this study, we examine how words and arbitrary actions shape category formation. Across three conditions (word cue, action cue, word-action cue), we presented infants (N = 90) with eight videos of single-category objects which vary in colour and other perceptual features. The objects were either accompanied by a word and/or an action that is being performed on the object. Infants in the word and action condition showed a decrease in looking over the course of the familiarization phase indicating habituation to the category, but infants in the word-action condition did not. At test, infants saw a novel object of the just-learned category and a novel object from another category side-by-side on the screen. There was some evidence for an advantage for words in shaping early object categorization, although we note that this was not robust across analyses.