Visual Feature Detection Research Articles

Visual Edge Feature Detection and Guidance under 3D Interference: A Case Study on Deep Groove Edge Features for Manufacturing Robots with 3D Vision Sensors

For manufacturing robots equipped with 3D vision sensors, the presence of environmental interference significantly impedes the precision of edge extraction. Existing edge feature extraction methods often enhance adaptability to interference at the expense of final extraction precision. This paper introduces a novel 3D visual edge detection method that ensures greater precision while maintaining adaptability, capable of addressing various forms of interference in real manufacturing scenarios. To address the challenge, data-driven and traditional visual approaches are integrated. Deep groove edge feature extraction and guidance tasks are used as a case study. R-CNN and improved OTSU algorithm with adaptive threshold are combined to identify groove features. Subsequently, a scale adaptive average slope sliding window algorithm is devised to extract groove edge points, along with a corresponding continuity evaluation algorithm. Real data is used to validate the performance of the proposed method. The experiment results show that the average error in processing interfered data is 0.29mm, with an average maximum error of 0.54mm, exhibiting superior overall performance and precision compared to traditional and data-driven methods.

Social state alters vision using three circuit mechanisms in Drosophila

Animals are often bombarded with visual information and must prioritize specific visual features based on their current needs. The neuronal circuits that detect and relay visual features have been well studied1, 2, 3, 4, 5, 6, 7–8. Much less is known about how an animal adjusts its visual attention as its goals or environmental conditions change. During social behaviours, flies need to focus on nearby flies9, 10–11. Here we study how the flow of visual information is altered when female Drosophila enter an aggressive state. From the connectome, we identify three state-dependent circuit motifs poised to modify the response of an aggressive female to fly-sized visual objects: convergence of excitatory inputs from neurons conveying select visual features and internal state; dendritic disinhibition of select visual feature detectors; and a switch that toggles between two visual feature detectors. Using cell-type-specific genetic tools, together with behavioural and neurophysiological analyses, we show that each of these circuit motifs is used during female aggression. We reveal that features of this same switch operate in male Drosophila during courtship pursuit, suggesting that disparate social behaviours may share circuit mechanisms. Our study provides a compelling example of using the connectome to infer circuit mechanisms that underlie dynamic processing of sensory signals.

Autonomous Positioning for Mobile Vehicles Based on Visual‐Inertial Fusion in Challenging Dark Roadway Scenes

ABSTRACTAccurate positioning for autonomous driven underground mining vehicles (UMVs) and coal mine robots (CMRs) is indeed one of the cores in the intelligentization of coal mining. Completely different from positioning on the ground and in parking scenes, there will be great difficulties in realizing the accurate active positioning for UMVs shuttled in dark and narrow roadways. We propose an effective visual and inertial fusion positioning method for autonomous CMRs and roadheaders in challenging roadway scenarios based on the odometer‐aided inertial navigation system and visual pose estimation system. Velocity information of the odometer is adapted to restrain the error accumulation of inertial positioning based on a Kalman filter. The hybrid visual feature detection algorithm is put forward to improve the accuracy and robustness of visual observation information in a dark environment. Autonomous experiments for CMRs and roadheaders are separately performed in the narrow roadway and dark passageway to demonstrate the applicability of our localization method. The proposed approach outperforms the subsystems and existing methods in accuracy and has outstanding stability.

From Cats to the Cortex: Unravelling the Hierarchical Processing System of Vision and Brain Plasticity.

The groundbreaking research conducted by neurophysiologists David Hubel and Torsten Wiesel during the late 1950s and 1960s revolutionized the field of visual neuroscience. Through single-unit recordings in the visual cortex of cats, they made several key discoveries that fundamentally changed our understanding of visual processing. Their work introduced the concept of orientation selectivity, revealing that neurons in the visual cortex are specifically tuned to line orientations, thereby illustrating how the brain constructs visual representations through edge detection. Additionally, they discovered ocular dominance columns, the specialized cortical regions that respond preferentially to input from one eye, providing crucial insights into the organization of visual processing and the importance of binocular vision. Hubel and Wiesel's research also established the concept of a critical period in visual development, demonstrating that early visual experiences are essential for the proper maturation of the visual system. This discovery has had significant implications for understanding neural plasticity and the role of sensory input in neural development. The impact of their work goes beyond theoretical knowledge, contributing to the development of therapeutic strategies for some visual disorders and guiding current research into brain plasticity and visual processing. This review synthesizes the monumental contributions of Hubel and Wiesel, evaluating how their key discoveries have shaped subsequent research in visual neuroscience. It traces the evolution of knowledge related to visual pathways, feature detection, and brain plasticity, highlighting the enduring influence of their foundational work on contemporary studies. By exploring the progression from their pioneering findings to modern advancements, this review emphasizes the legacy of Hubel and Wiesel's contributions to our understanding of vision and neural function.

A Synchronous Localization Method for Multiple Mobile Robots Based on Visual SLAM Algorithm in the Context of the Internet of Things

Abstract Aiming at the problem that traditional methods cannot meet the problem of synchronous positioning of multi-mobile robots in different motion states, a synchronous positioning method of multi-mobile robots based on visual simultaneous localization and mapping (SLAM) algorithm is proposed. Analyze the general model of SLAM problem, realize visual SLAM feature detection through scale invariant feature transform algorithm, and match image features based on active vision. A multi-mobile robot motion state estimation model is constructed, an octree model is used to construct a multi-robot synchronous localization map, and the camera pose tracking is realized by using the oriented fast accelerated segment test and rotated binary robust independent elementary features points that are not in the target bounding box. The three-dimensional points in the environment recovered by visual SLAM separate the background target and the moving target, and match the corresponding target in the previous frame through the feature to realize the synchronous positioning of the multi-mobile robot. The experimental results show that the method can realize the synchronous positioning of multi-robots under the state of multi-robot linear motion, curvilinear motion and mixed motion, and the positioning accuracy is high.

Advanced Underwater Measurement System for ROVs: Integrating Sonar and Stereo Vision for Enhanced Subsea Infrastructure Maintenance

In the realm of ocean engineering and maintenance of subsea structures, accurate underwater distance quantification plays a crucial role. However, the precision of such measurements is often compromised in underwater environments due to backward scattering and feature degradation, adversely affecting the accuracy of visual techniques. Addressing this challenge, our study introduces a groundbreaking method for underwater object measurement, innovatively combining image sonar with stereo vision. This approach aims to supplement the gaps in underwater visual feature detection with sonar data while leveraging the distance information from sonar for enhanced visual matching. Our methodology seamlessly integrates sonar data into the Semi-Global Block Matching (SGBM) algorithm used in stereo vision. This integration involves introducing a novel sonar-based cost term and refining the cost aggregation process, thereby both elevating the precision in depth estimations and enriching the texture details within the depth maps. This represents a substantial enhancement over existing methodologies, particularly in the texture augmentation of depth maps tailored for subaquatic environments. Through extensive comparative analyses, our approach demonstrates a substantial reduction in measurement errors by 1.6%, showing significant promise in challenging underwater scenarios. The adaptability and accuracy of our algorithm in generating detailed depth maps make it particularly relevant for underwater infrastructure maintenance, exploration, and inspection.

Application research of interior space design elements based on image processing

In order to quantitatively analyze the application performance of elements in interior space design, a detection method of texture visual features of elements distribution images in interior space design based on image processing and texture edge contour features detection is proposed. A multi-resolution visual information collection model for detecting the texture visual characteristics of element distribution images in indoor space design is constructed, and a visual characteristic identification model for element application configuration in indoor space design is established. Multi-texture grid block area combination design method is adopted to realize the fusion of element application configuration visual images in indoor space design. Through the edge feature detection method of texture grid area, Establish a visual parameter identification model of element application configuration in interior space design, extract the visual information feature quantity of element application configuration in interior space design, adopt Harris corner feature matching method, realize distributed detection of texture edge contour features of element application configuration visual features in interior space design, and fuse detection of high-resolution texture information through combined filtering and collaborative filtering. The collection and optimization of visual features of element application configuration in interior space design are realized, and the distributed detection algorithm of texture edge contour features is adopted to improve the convergence level of detection of texture visual features of element distribution images in interior space design, and the application of elements in interior space design based on image processing is realized. The simulation results show that this method has good resolution and strong visual expression ability in extracting the texture visual features of element distribution images in interior space design, which improves the quantitative analysis ability of elements in interior space design.

Age-Specific Effects of Visual Feature Binding.

Temporary binding of visual features enables objects to be stored and maintained in the visual working memory as a singular structure, irrespective of its inherent complexity. Although working memory capacity is reduced in aging, previous behavioral studies suggest that binding is preserved. Using event-related brain potentials (ERPs), we tested whether stimulus encoding is different in younger (N = 26, mean age = 28.5) and older (N = 22; mean age = 67.4) participants in a change detection task. The processing costs of binding were defined by the difference between feature-alone (color or shape) and feature-binding (color-shape) conditions. The behavioral data revealed that discrimination ability was reduced in the feature-binding condition, and that this effect was more attenuated in older participants. A corresponding ERP effect was not found in early components related to visual feature detection and processing (posterior N1 and frontal P2). However, the late positive complex (LPC) was more often expressed in the feature-binding condition, and the increase in amplitude was more pronounced in older participants. The LPC can be related to attentional allocation processes which might support the maintenance of the more complex stimulus representation in the binding task. However, the selective neural overactivation in the encoding phase observed in older participants does not prevent swap errors in the subsequent retrieval phase.

Asymetric Event-Related Potential Priming Effects Between English Letters and American Sign Language Fingerspelling Fonts.

Letter recognition plays an important role in reading and follows different phases of processing, from early visual feature detection to the access of abstract letter representations. Deaf ASL-English bilinguals experience orthography in two forms: English letters and fingerspelling. However, the neurobiological nature of fingerspelling representations, and the relationship between the two orthographies, remains unexplored. We examined the temporal dynamics of single English letter and ASL fingerspelling font processing in an unmasked priming paradigm with centrally presented targets for 200 ms preceded by 100 ms primes. Event-related brain potentials were recorded while participants performed a probe detection task. Experiment 1 examined English letter-to-letter priming in deaf signers and hearing non-signers. We found that English letter recognition is similar for deaf and hearing readers, extending previous findings with hearing readers to unmasked presentations. Experiment 2 examined priming effects between English letters and ASL fingerspelling fonts in deaf signers only. We found that fingerspelling fonts primed both fingerspelling fonts and English letters, but English letters did not prime fingerspelling fonts, indicating a priming asymmetry between letters and fingerspelling fonts. We also found an N400-like priming effect when the primes were fingerspelling fonts which might reflect strategic access to the lexical names of letters. The studies suggest that deaf ASL-English bilinguals process English letters and ASL fingerspelling differently and that the two systems may have distinct neural representations. However, the fact that fingerspelling fonts can prime English letters suggests that the two orthographies may share abstract representations to some extent.

Divided attention impairs detection of simple visual features

Divided attention impairs detection of simple visual features

Biomarkers and clinical presentations in Creutzfeldt‐Jakob Disease

AbstractBackgroundThe ability to detect malformed prion proteins using real‐time quaking‐induced conversion (RT‐QuIC) assays has transformed the diagnostic approach to sporadic Creutzfeldt‐Jakob disease (CJD), facilitating earlier recognition of affected patients. Recognizing this, we evaluated the frequency of clinical features and biomarker results at initial evaluation in patients with CJD and determined the relationship between these early features and CJD diagnosis and prognosis.MethodClinical data were extracted from the electronic medical records of patients with probable or definite (pathologically confirmed) CJD assessed at Mayo Clinic from 2014‐2021. Diagnoses of probable CJD were established by clinical consensus, referencing the Centers for Disease Control and Prevention diagnostic criteria. Clinical features and biomarkers results were evaluated at presentation, and associations with CJD diagnosis and symptomatic disease duration determined.ResultOne‐hundred fifteen patients were included (40, [35%] with definite CJD). Mean age‐at‐symptom onset was 64.8±9.4 years; 68 patients were female (59%). The sensitivity of clinical markers (myoclonus) and tests historically considered in patients with suspected CJD (e.g., stereotyped EEG abnormalities (16%), CSF 14‐3‐3 (60%)) was poor. Biomarkers with good diagnostic sensitivity included RT‐QuIC (93%), t‐tau levels >1149 pg/mL (88%), and characteristic signal abnormalities on MRI (77%). Multivariable linear regression confirmed shorter survival for patients with myoclonus (125.9 days, 95%CI 23.3‐15.5, p=0.026), visual/cerebellar signs (180.19 days, 95%CI 282.2‐78.2, p<0.001), positive 14‐3‐3 (193 days, 95%CI 304.9‐82.9; p<0.001), and elevated t‐tau levels (each 1000 pg/ml increase was associated with a nine‐day shorter time‐to‐death, 95%CI 1‐18; p=0.041).ConclusionCSF RT‐QuIC and elevated t‐tau levels, and stereotyped MRI abnormalities continue to be strongly associated with the diagnosis in the modern era, while other clinical findings (myoclonus) and biomarkers results traditionally ascribed to CJD (e.g., PSWC on EEG, 14‐3‐3) offered less value in the diagnostic evaluation. Detection of visual or cerebellar features, myoclonus, CSF 14‐3‐3, and t‐tau levels may predict disease duration, justifying inclusion in the evaluation of CJD‐suspected patients.

The cost of divided attention for detection of simple visual features primarily reflects limits in post-perceptual processing.

Covert spatial attention allows us to prioritize processing at relevant locations. Perception is generally poorer when attention is distributed across multiple locations than when attention is focused on a single location. However, while divided attention typically impairs performance, recent work suggests that divided attention does not seem to impair detection of simple visual features. Here, we re-examined this possibility. In two experiments, observers detected a simple target (a vertical Gabor), and we manipulated whether attention was focused at one location (focal-cue condition) or distributed across two locations (distributed-cue condition). In Experiment 1, targets could appear independently at each location, such that observers needed to judge target presence for each location separately in the distributed-cue condition. Under these conditions, we found a robust cost of dividing attention. Next, we further probed what stage of processing gave rise to this cost. In Experiment 1, the cost of dividing attention could reflect a limit in the ability to make concurrent judgments about target presence. In Experiment 2, we simplified the task to test whether this was the case: just one target could appear on each trial, such that observers made a single judgment (“was a target present?”) in both the focal-cue and distributed-cue conditions. Here, we found a marginal cost of dividing attention that was weaker than the cost in Experiment 1. Together, our results suggest that divided attention does impair detection of simple visual features, but that this cost is primarily due to a limit in post-perceptual processes.

Identifying Inputs to Visual Projection Neurons in Drosophila Lobula by Analyzing Connectomic Data.

Electron microscopy (EM)-based connectomes provide important insights into how visual circuitry of fruit fly Drosophila computes various visual features, guiding and complementing behavioral and physiological studies. However, connectomic analyses of the lobula, a neuropil putatively dedicated to detecting object-like features, remains underdeveloped, largely because of incomplete data on the inputs to the brain region. Here, we attempted to map the columnar inputs into the Drosophila lobula neuropil by performing connectivity-based and morphology-based clustering on a densely reconstructed connectome dataset. While the dataset mostly lacked visual neuropils other than lobula, which would normally help identify inputs to lobula, our clustering analysis successfully extracted clusters of cells with homogeneous connectivity and morphology, likely representing genuine cell types. We were able to draw a correspondence between the resulting clusters and previously identified cell types, revealing previously undocumented connectivity between lobula input and output neurons. While future, more complete connectomic reconstructions are necessary to verify the results presented here, they can serve as a useful basis for formulating hypotheses on mechanisms of visual feature detection in lobula.

Brain Tumor Detection Using Selective Search and Pulse-Coupled Neural Network Feature Extraction

The identification of tumorous tissues in the brain based on Magnetic Resonance Images (MRI) analysis is a challenging and time consuming task that highly depends on radiologists expertise. As prompt diagnosis of tumors can often be inherent to the patient's survival, it is however crucial to decrease the amount of time spent on the manual analysis of MRI while increasing the accuracy of the detection process. To tackle these issues, many research works have already investigated efficient computer vision systems. They offer new opportunities to assist health care providers in the establishment of fast and more accurate tumor detection, classification and segmentation. However, often based on deep learning methods, the development and tuning of these solutions remains time and energy consuming while inducing a lack of explainability in the decision making system. In this study, we respond to these issues by solving a brain tumor detection task using the Selective Search (SS) algorithm coupled with a simplified Pulse-Coupled Neural Network (PCNN) for visual feature extraction and detection validation. The performed experiments showed promising results in terms of computational cost and detection accuracy. This leads to the development of a light-weight brain tumor detection system.

The Brain Activation-Based Sexual Image Classifier (BASIC): A Sensitive and Specific fMRI Activity Pattern for Sexual Image Processing.

Previous studies suggest there is a complex relationship between sexual and general affective stimulus processing, which varies across individuals and situations. We examined whether sexual and general affective processing can be distinguished at the brain level. In addition, we explored to what degree possible distinctions are generalizable across individuals and different types of sexual stimuli, and whether they are limited to the engagement of lower-level processes, such as the detection of visual features. Data on sexual images, nonsexual positive and negative images, and neutral images from Wehrum et al. (2013) (N = 100) were reanalyzed using multivariate support vector machine models to create the brain activation-based sexual image classifier (BASIC) model. This model was tested for sensitivity, specificity, and generalizability in cross-validation (N = 100) and an independent test cohort (N = 18; Kragel et al. 2019). The BASIC model showed highly accurate performance (94–100%) in classifying sexual versus neutral or nonsexual affective images in both datasets with forced choice tests. Virtual lesions and tests of individual large-scale networks (e.g., visual or attention networks) show that individual networks are neither necessary nor sufficient to classify sexual versus nonsexual stimulus processing. Thus, responses to sexual images are distributed across brain systems.

Harnessing high-level concepts, visual, and auditory features for violence detection in videos

In detecting sensitive media, violence is one of the hardest to define objectively, and thus, a significant challenge to detect automatically. While many studies were conducted in detecting aspects of violence, very few try to approach the general concept. We propose a method that aims to enable machines to understand a high-level concept of violence by first breaking it down into smaller, more objective ones, such as fights, explosions, blood, and gunshots, to combine them later, leading to a better understanding of the scene. For this, we leverage characteristics of each individual sub-concept of violence (relying upon custom-tailored convolutional neural networks) to guide how they should be described. A fight scene should incorporate temporal features that a scene with blood does not need to describe. A scene with explosions or gunshots should weigh more on its audio features. With this multimodal approach, we trained visual and auditory feature detectors and later combined them into a decision neural network to give us a violence detector that considers several different aspects of the problem. This robust and modular approach allows different cultures and users to adapt the detector to their specific needs.

Outfit compatibility prediction with multi-layered feature fusion network

Clothing plays a critical role in people’s daily lives, a perfect styling clothing is able to help people to avoid weaknesses and show their personal temperament, however, not everyone is good at styling. Compatibility is the core of styling, however, determining whether a pair of garments are compatible with each other is a challenging styling issue. Years of research have been devoted to fashion compatibility learning, whereas there are still several drawbacks in visual feature detection and compatibility calculation. In this paper, we propose an end-to-end framework to learn the compatibility among tops and bottoms. In order to improve the effects of visual feature extraction, a Multi-layer Non-local Feature Fusion framework (MNLFF) is developed. Feature fusion model is used to combine both high and low-level features, while non-local block is for global feature detection. We compare our technique with the prior state-of-the-art methods in the outfit compatibility prediction task and extensive experiments on existing datasets demonstrate its effectiveness.

Learned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matching

Successful visual navigation depends upon capturing images that contain sufficient useful information. In this letter, we explore a data-driven approach to account for environmental lighting changes, improving the quality of images for use in visual odometry (VO) or visual simultaneous localization and mapping (SLAM). We train a deep convolutional neural network model to predictively adjust camera gain and exposure time parameters such that consecutive images contain a maximal number of matchable features. The training process is fully self-supervised: our training signal is derived from an underlying VO or SLAM pipeline and, as a result, the model is optimized to perform well with that specific pipeline. We demonstrate through extensive real-world experiments that our network can anticipate and compensate for dramatic lighting changes (e.g., transitions into and out of road tunnels), maintaining a substantially higher number of inlier feature matches than competing camera parameter control algorithms.

Examining the Temporal Limits of Enhanced Visual Feature Detection in Children With Autism.

The enhanced perceptual processing of visual features in children with autism spectrum disorder (ASD) is supported by an abundance of evidence in the spatial domain, with less robust evidence regarding whether this extends to information presented across time. The current study aimed to replicate and extend previous work finding that children with an ASD demonstrated enhanced perceptual accuracy in detecting feature-based (but not categorically defined) targets in time, when these were presented quickly, at a stimulus onset asynchrony (SOA) of 50 ms per item. Specifically, we extend the range of SOAs to examine the temporal boundaries of this enhanced accuracy and examine whether there is a relationship between ASD-related traits and detection accuracy on temporal visual search tasks. Individuals with autism perceived feature-based targets with statistically higher accuracy than their typically developing peers between SOAs of 39 and 65 ms and were numerically faster at all SOAs. No group differences were noted for category-based task accuracy. Our results also demonstrated that ASD-related traits measured by the autism spectrum quotient were positively correlated with accuracy on the feature-based task. Overall, results suggest that accurate visual perception of features (particularly color) is enhanced in children with ASD across time. LAY SUMMARY: Our results suggest that children with autism are able to process visual features, such as color, more accurately than typically developing children, even when these are presented very rapidly. Accuracy was higher in children with higher levels of autism-related traits and symptoms. Our findings suggest that more accurate visual perception exists not only across space in children with autism, as much of the existing literature demonstrates, but also over time. Autism Res 2020, 13: 1561-1572. © 2020 International Society for Autism Research, Wiley Periodicals, Inc.

Non-canonical Receptive Field Properties and Neuromodulation of Feature-Detecting Neurons in Flies

Several fundamental aspects of motion vision circuitry are prevalent across flies and mice. Both taxa segregate ON and OFF signals. For any given spatial pattern, motion detectors in both taxa are tuned to speed, selective for one of four cardinal directions, and modulated by catecholamine neurotransmitters. These similarities represent conserved, canonical properties of the functional circuits and computational algorithms for motion vision. Less is known about feature detectors, including how receptive field properties differ from the motion pathway or whether they are under neuromodulatory control to impart functional plasticity for the detection of salient objects from a moving background. Here, we investigated 19 types of putative feature selective lobula columnar (LC) neurons in the optic lobe of the fruit fly Drosophila melanogaster to characterize divergent properties of feature selection. We identified LC12 and LC15 as feature detectors. LC15 encodes moving bars, whereas LC12 is selective for the motion of discrete objects, mostly independent of size. Neither is selective for contrast polarity, speed, or direction, highlighting key differences in the underlying algorithms for feature detection and motion vision. We show that the onset of background motion suppresses object responses by LC12 and LC15. Surprisingly, the application of octopamine, which is released during flight, reverses the suppressive influence of background motion, rendering both LCs able to track moving objects superimposed against background motion. Our results provide a comparative framework for the function and modulation of feature detectors and new insights into the underlying neuronal mechanisms involved in visual feature detection.