Objects In Scene Research Articles

Research on motion target detection based on infrared biomimetic compound eye camera.

The cooled mid-wave infrared biomimetic compound eye camera has wide range of applications, such as industrial inspection, military project, and security. Due to the low resolution of individual eyes and the large field view of the imaging system, existing motion target enhancement and detection algorithms cannot effectively detect all potential targets. To address this issue, we propose an improved elementary motion detector model that combines a double-layer ON_OFF channel and a cross-type computational architecture, which is able to suppress a stationary background and enhance moving targets. In order to further reduce the missed detection, we designed the spatial and temporal consistency detection methods of the compound eye structure, which further improved the accuracy and stability of the detection results. The experimental results show that our method can fully utilize the features of the image and can be applied to the enhancement and detection of moving objects in complex scenes, and the detection efficiency is significantly improved.

Smart Caption: Intelligent Image Description Using Transformer Decoder

The need for automated image description systems has grown significantly with the rise of multimedia content across diverse domains such as social media, digital libraries, and accessibility technologies. Smart Caption presents a novel approach for generating intelligent and context-aware image descriptions by utilizing a combination of Vision Transformers (ViTs) and Natural Language Processing (NLP) Transformer decoders. Unlike traditional convolution-based methods, Vision Transformers treat images as sequences of patches, enabling them to capture global image features more effectively. These extracted visual features are then processed by a Transformer-based decoder to produce coherent and contextually appropriate captions, bridging the gap between image recognition and natural language generation. Our approach focuses on leveraging the attention mechanisms inherent in both Vision and NLP Transformers to enhance the quality of image descriptions. The ViT architecture is designed to focus on relevant regions within an image, while the NLP Transformer decoder is adept at generating fluent and detailed descriptions by attending to the most significant visual features. This two-stage process improves the precision of object detection, relationship understanding, and scene context in generated captions. Experimental results demonstrate that Smart Caption out performs traditional methods in terms of accuracy, contextual relevance, and fluency, marking a significant step forward in the field of automated image captioning. Through this research, we aim to provide a scalable, efficient, and intelligent solution for image description, with potential applications in areas such as accessibility tools for visually impaired users, digital content indexing, and automated content generation. Our findings highlight the strengths of transformer-based models in bridging vision and language tasks, offering promising directions for future research in multimodal AI..

Research on image recognition and processing application technology of unmanned vehicle based on deep learning

Abstract. Image recognition technology is critically important in various fields, including the rapidly advancing sector of autonomous vehicles. As one of the core components enabling driverless cars to perceive their environment and make informed decisions, image recognition has seen significant advancements due to deep learning. This paper focuses on the application of deep learning in image recognition for self-driving cars and explores its implications for the future of autonomous driving technology. To begin with, this paper examines the empirical evaluation of deep learning models in highway driving scenarios. By employing Convolutional Neural Networks (CNN), these models achieve high detection rates and superior accuracy in recognizing vehicles and lanes. The robustness of these models is tested under varying weather conditions and times, demonstrating their effectiveness compared to classical computer vision techniques. Next, the paper discusses radar-camera fusion technology, highlighting different fusion strategies such as data-level, feature-level, object-level, and hybrid-level. The findings suggest that while feature-level fusion excels in detecting small objects in complex scenes, hybrid-level fusion is optimal for diverse driving situations. This section provides valuable insights into the integration of multimodal data for improved object recognition and semantic segmentation. After discussing fusion technologies, the paper finally reviews the security challenges posed by adversarial attacks on deep learning-based unmanned systems.

A Scene–Object–Economy Framework for Identifying and Validating Urban–Rural Fringe Using Multisource Geospatial Big Data

Rapid urbanization has led to the emergence of urban–rural fringes, complex transitional zones that challenge traditional urban–rural dichotomies. While these areas play a crucial role in urban development, their precise identification remains a significant challenge. Existing methods often rely on single-dimensional metrics or administrative boundaries, failing to capture the multi-faceted nature of these zones. This study introduces a novel “Scene–Object–Economy” (SOE) framework to address these limitations and enhance the precision of urban–rural fringe identification. Our approach integrates multisource geospatial big data, including remote sensing imagery, nightlight data, buildings, and Points of Interest (POI), leveraging machine learning techniques. The SOE framework constructs feature from three dimensions: scene (image features), object (buildings), and economy (POIs). This multidimensional methodology allows for a more comprehensive and nuanced mapping of urban–rural fringes, overcoming the constraints of traditional methods. The study demonstrates the effectiveness of the SOE framework in accurately delineating urban–rural fringes through multidimensional validation. Our results reveal distinct spatial patterns and characteristics of these transitional zones, providing valuable insights for urban planners and policymakers. Furthermore, the integration of dynamic population data as a separate layer of analysis offers a unique perspective on population distribution patterns within the identified fringes. This research contributes to the field by offering a more robust and objective approach to urban–rural fringe identification, laying the groundwork for improved urban management and sustainable development strategies. The SOE framework presents a promising tool for future studies in urban spatial analysis and planning.

Understanding the Implications of Non-Accused DNA at Crime Scenes for Criminal Defence Lawyers

While DNA evidence has revolutionized criminal investigations, its presence in legal cases becomes problematic when the DNA of non-accused individuals is detected at crime scenes. This essay explores the issue of unintentional DNA transfer and its implications for defence attorneys. This study questions the prevailing assumption that DNA presence equates to guilt by analyzing a burglary case study, demonstrating how DNA can be unintentionally deposited by those not involved in the crime. The findings reveal the complexities surrounding forensic evidence, showing that individuals who haven't physically interacted with crime scene objects can still leave their DNA behind. This complexity underscores the need for lawyers to adopt a more nuanced perspective, emphasizing the importance of expert testimony, rigorous investigative methods, and contextual evaluations in accurately assessing the implications of DNA evidence within the judicial system. Understanding these intricacies is vital for police officers and legal professionals including judiciary to navigate carefully and sincerely cases where DNA evidence plays a critical role in proving or disproving the guilt of the accused person.

Visual Search Interactive Model for Artificial Intelligence Robotics Model forthe Agricultural Field Analysis

The Visual Search Interactive Model for Artificial Intelligence (AI) is designed to enhance the efficiency and effectiveness of visual data analysis across various applications. By leveraging advanced computer vision techniques and machine learning algorithms, this model enables AI systems to interpret and analyze visual information in real-time, facilitating tasks such as object recognition, image classification, and scene understanding. The interactive nature of the model allows users to engage with the AI, refining searches and improving outcomes through iterative feedback. This paper introduces the Auxiliary Clustering k-means Machine Learning (AC k-means ML) model, designed to enhance agricultural efficiency through advanced data analysis and robotic integration. The study evaluates the performance of the AC k-means ML model using a dataset comprising 1,950 samples, achieving an overall accuracy of 91.5% and a precision of 89.2%. Key performance metrics such as F1 scores averaged 88.6%, with the highest individual cluster accuracy reaching 96% for Cluster 10. In addition to data classification, the model facilitated the completion of 250 tasks with a remarkable success rate of 92%, while maintaining an average task completion time of 15.4 minutes and an energy consumption of just 0.5 kWh per task. The implementation of the AC k-means ML model resulted in a 15% increase in crop yield and substantial cost savings estimated at $2,000. With a user satisfaction score averaging 8.7 and an adaptability score of 9.0, the findings indicate that the integration of machine learning and robotics significantly optimizes agricultural processes, promoting sustainability and efficiency in farming practices.

Research on Deep Learning Detection Model for Pedestrian Objects in Complex Scenes Based on Improved YOLOv7.

Pedestrian detection is very important for the environment perception and safety action of intelligent robots and autonomous driving, and is the key to ensuring the safe action of intelligent robots and auto assisted driving. In response to the characteristics of pedestrian objects occupying a small image area, diverse poses, complex scenes and severe occlusion, this paper proposes an improved pedestrian object detection method based on the YOLOv7 model, which adopts the Convolutional Block Attention Module (CBAM) attention mechanism and Deformable ConvNets v2 (DCNv2) in the two Efficient Layer Aggregation Network (ELAN) modules of the backbone feature extraction network. In addition, the detection head is replaced with a Dynamic Head (DyHead) detector head with an attention mechanism; unnecessary background information around the pedestrian object is also effectively excluded, making the model learn more concentrated feature representations. Compared with the original model, the log-average miss rate of the improved YOLOv7 model is significantly reduced in both the Citypersons dataset and the INRIA dataset. The improved YOLOv7 model proposed in this paper achieved good performance improvement in different pedestrian detection problems. The research in this paper has important reference significance for pedestrian detection in complex scenes such as small, occluded and overlapping objects.

Recognizing objects in complex scenes: A Recent Systematic Review

This systematic review provides a comprehensive examination of recent advancements in object recognition within complex scenes, focusing on addressing challenges such as clutter, occlusion, and diverse environmental conditions. Leveraging the PRISMA framework, the study meticulously analysed a diverse range of literature from esteemed sources, employing advanced search methods on Scopus and WoS databases to identify and analyse primary research studies (n = 25). The review encompasses three key themes: Theme 1 concentrates on Image Noise Identification and Removal Techniques, while Theme 2 delves into Image Classification and Recognition under Noise. Additionally, Theme 3 explores Innovative Models and Approaches for Noise-Robust Image Analysis. Despite the progress achieved, contemporary recognition systems struggle with real-world complexities such as varied scales, lighting variations, and different viewpoints. The synthesis of findings emphasizes the necessity for innovative strategies that capitalize on contextual cues and harness the potential of deep learning to enhance precision in object recognition within intricate visual environments. The insights gleaned from this synthesis are poised to guide future research directions, informing the development of more resilient algorithms capable of navigating challenges and catalysing advancements in the field of object recognition.

ADDON FOR BLENDER3D. AUTOMATION OF THE OBJECT TEXTURING PROCESS

Abstract. Today, the use of 3D visualization technologies is one of the key directions in the field of information technologies. The 3D direction has become extremely popular in many fields, such as architecture, interior design, game industry, medicine, automotive and other fields. This method opens up new opportunities for perception and interpretation of information, adding it to a three-dimensional virtual space. The topic of the research work is the creation of a software module (addon) for the Blender3D program, which will provide the user with a library of ready-made materials, divided by categories. This addon has similar functionality to Substance Painter and Quixel Mixer, the main functions of which are to create and adjust materials and textures for imported ready-made 3D models. The addon has its own name "QuickShader" and will provide the user with 8 shaders and 35 PBR materials. Throughout the development of the project, the Waterfall life cycle model was used, stability and a clear structure were put first, which helped to efficiently work through each step of creating an addon for the Blender program. In the conclusion to the scientific work, it can also be noted that the development of a software addon for Blender3D, which includes a library of shader operators and PBR materials, will greatly facilitate the work of users when assigning textures to objects on the scene. A library of shader operators makes it easy to implement and customize shaders for light, glass, and some metals, giving you more control over the visual aspect of the scene. PBR materials provide realism due to the accurate representation of physical properties using Physically Based Rendering technologies. This addon gives users the ability to interact more effectively with procedural materials, providing a quick means to create realistic renders. This module automates the creation of materials by providing a list of prepared shaders and textures that can be applied to scene objects. The user will be provided with a set of ready-made shaders (glass, light material, metals) and PBR materials (wood, fabric, metals, and others), which can be applied with one button on the module panel.

AMW-YOLOv8n: Road Scene Object Detection Based on an Improved YOLOv8

This study introduces an improved YOLOv8 model tailored for detecting objects in road scenes. To overcome the limitations of standard convolution operations in adapting to varying targets, we introduce Adaptive Kernel Convolution (AKconv). AKconv dynamically adjusts the convolution kernel’s shape and size, enhancing the backbone network’s feature extraction capabilities and improving feature representation across different scales. Additionally, we employ a Multi-Scale Dilated Attention (MSDA) mechanism to focus on key target features, further enhancing feature representation. To address the challenge posed by YOLOv8’s large down sampling factor, which limits the learning of small target features in deeper feature maps, we add a small target detection layer. Finally, to improve model training efficiency, we introduce a regression loss function with a Wise-IoU dynamic non-monotonic focusing mechanism. With these enhancements, our improved YOLOv8 model excels in road scene object detection tasks, achieving a 5.6 percentage point improvement in average precision over the original YOLOv8n on real road datasets.

Visual SLAM system based on dynamic semantic features

Aiming at the problem that dynamic objects (such as pedestrians, vehicles, and animals) in real scenes affect the positioning and mapping accuracy of visual SLAM (Simultaneous Localization and Mapping), a YOLOv3-ORB-SLAM3 algorithm is proposed based on ORB-SLAM3 (Oriented FAST and Rotated BRIEF-Simultaneous Localization and Mapping 3). The algorithm adds a semantic thread on the basis of ORB-SLAM3, and adopts a dual-thread mechanism for dynamic and static scene feature extraction: the semantic thread uses YOLOv3 to perform semantic recognition target detection on dynamic objects in the scene, and removes outliers from the extracted dynamic area feature points; the tracking thread extracts scene area features through ORB features, and obtains static scene features combined with semantic information and sends them to the backend, thereby eliminating the interference of dynamic scenes on the system and improving the positioning accuracy of the visual SLAM algorithm. Verified using the TUM (Technical University of Munich) dataset, the results show that the ATE (Average Treatment Effect) index of the YOLOv3-ORB-SLAM3 algorithm in the monocular mode is about 30% lower than that of the ORB-SLAM3 algorithm, and the ATE index of the dynamic sequence in the RGB-D (Red, Green and Blue-Depth) mode is reduced 10%, while the static sequence has no significant decrease.

Efficient object recognition under cluttered scenes via descriptor-based matching and single point voting

This paper addresses the problem of recognizing multiple objects and multiple instances from point clouds. Whereas existing methods utilize descriptors on 3D fields or pointwise voting to achieve this task, our framework takes advantage of both descriptor-based and voting-based schemes to realize more robust and efficient prediction. Specifically, we propose a novel and robust descriptor called an orientation-enhanced fast point feature histogram (OE-FPFH) to describe points in both the object model and scene, and further to build the correspondence set. The OE-FPFH integrates an orientation vector through mining the geometric tensor of the local structure of a surface point, which is more representative than the original FPFH descriptor. To improve voting efficiency, we devise a novel single-point voting mechanism (SPVM), which constructs a unique local reference frame (LRF) on a single point using the orientation vector. The SPVM takes as input the corresponding point set and can generate a pose candidate for each correspondence. The process is realized by matching LRFs from two corresponding points. All pose candidates are subsequently divided into clusters and aggregated using the K-means clustering algorithm to deduce the poses for different objects or instances in the scene. Experiments on three challenging datasets demonstrate that our method is effective, efficient, and robust to occlusions and multiple instances.

Local contour features contribute to figure-ground segregation in monkey V4 neural populations and human perception

Figure-ground (FG) segregation is a crucial step towards the recognition of objects in natural scenes. Gestalt psychologists have emphasized the importance of contour features in perception of FG. Recent electrophysiological studies have identified a neural population in V4 that shows FG-dependent modulation (FG neurons). However, whether the contour features contribute to the modulation of the response patterns of the neural population remains unclear. In the present study, we quantified the contour features associated with Gestalt factors in local natural stimuli and examined whether salient contour-features evoked reliable perceptual and neural responses by analyzing response consistency (stability) across trials. The results showed the tendency that the more salient contour-features evoked the greater consistencies in the perceptual FG judgments and population-based neural responses in FG determination; a greater partial correlation for curvature and weaker correlations for closure and parallelism. Multiple linear regression analyses demonstrated that the perceptual consistency depended similarly on curvature and closure, and the neural consistency depended significantly on curvature but weakly on closure. We further observed a strong correlation between the consistencies in the perceptual and neural responses, i.e., stimuli that evoked more stable percepts tended to evoke more stable neural responses. These results indicate that local contour-features modulate the responses of the neural population in V4 and contribute to the perception of FG organization.

Complex Scene Understanding and Object Detection Algorithm Assisted by Artificial Intelligence

The purpose of this paper is to study the algorithm of object detection and scene understanding in complex scenes assisted by AI(Artificial Intelligence), so as to improve the machine's perception of the surrounding environment. Aiming at occlusion and dense scenes, this paper proposes a series of innovative algorithms by introducing technologies such as multi-scale detection, occlusion processing and real-time optimization. Experimental results show that the proposed algorithm has achieved excellent performance on several public data sets. Compared with the current mainstream object detection algorithm -YOLO, the method proposed in this paper has a significant improvement in accuracy. Especially in multi-scale object detection, occlusion and dense scene processing and real-time optimization, the proposed algorithm shows obvious advantages. The research results provide an effective solution for object detection and scene understanding in complex scenes, and promote the application of AI system in related fields.

Leveraging Multimodal Large Language Models (MLLMs) for Enhanced Object Detection and Scene Understanding in Thermal Images for Autonomous Driving Systems

Leveraging Multimodal Large Language Models (MLLMs) for Enhanced Object Detection and Scene Understanding in Thermal Images for Autonomous Driving Systems

Is a knife the same as a plunger? Comparing the attentional effects of weapons and non-threatening unusual objects in dynamic scenes.

Observers' memory for a person's appearance can be compromised by the presence of a weapon, a phenomenon known as the weapon-focus effect (WFE). According to the unusual-item hypothesis, attention shifts from the perpetrator to the weapon because a weapon is an unusual object in many contexts. To test this assumption, we monitored participants' eye movements while they watched a mock-crime video. The video was presented with sound and featured a female perpetrator holding either a weapon, a non-threatening unusual object, or a neutral object. Contrary to the predictions of current theories, there were no significant differences in total viewing times for the three objects. For the perpetrator, total viewing time was reduced when she held the non-threatening unusual object, but not when she held the weapon. However, weapon presence led to an attentional shift from the perpetrator's face toward her body. Detailed time-course analyses revealed that the effects of object type were more pronounced during early scene viewing. Thus, our results do not support the idea of extended attentional shifts from the perpetrator toward the unusual objects, but instead suggest more complex attentional effects. Contrary to previous research, memory for the perpetrator's appearance was not affected by object type. Thus, there was no WFE. An additional online experiment using the same videos and methodology produced a WFE, but this effect disappeared when the videos were presented without sound.

ETFE: Efficient transformer with feature enhancement for semantic segmentation

Abstract Despite the powerful capabilities of Transformers in relation to modeling, their effectiveness in capturing multi-scale object features in image-based tasks is often limited. This limitation arises from the diverse shapes and distances between objects in natural scenes, which pose challenges for Transformers to accurately capture object sizes and distances. To overcome this problem, we propose an effective Transformer which extracts multi-scale features at different resolutions. First, we leverage a multi-head attention mechanism to extract richer semantic features at various resolutions. The semantic features are then passed through the Feature Gate to aggregate multi-scale semantic features. Finally, Attentional Feature Enhancement further strengthens the semantic information of target features, enabling the modeling of dependencies among multi-scale features. Comprehensive experiments conducted on the Cityscapes and ADE20K datasets have shown that our model outperforms competing methods in both performance and accuracy.

Consistency-based semi-supervised learning for oriented object detection

Semi-Supervised Object Detection (SSOD) has emerged as a potent framework that leverages unlabeled data to reduce annotation costs while enhancing model performance. Nevertheless, existing SSOD methods primarily concentrate on the conventional localization of horizontal objects, overlooking the common arbitrary-oriented objects in aerial scenes. Extending semi-supervised learning to oriented object detection still encounters two major challenges: (1) There is an inconsistency between classification and localization in oriented object detectors, which means that pseudo-labels selected solely based on classification scores cannot properly represent the localization quality. (2) The static and monotonic pseudo-label selection process fails to dynamically filter pseudo-labels for different tasks and categories throughout the iteration process, inevitably introducing accumulated noise and bias into the supervisory signals for the student model. To mitigate this problems, we proposed a novel consistency-based semi-supervised oriented object detection framework, named CSLO-Det. Specifically, Task Alignment Learning (TAL) is proposed to improve the consistency in terms of both features and learning objectives, thereby facilitating a more robust selection of pseudo-labels. Noise-Resistant Pseudo-label Mining (NR-PM) is introduced to separately and dynamically exploits positives for the classification and localization task. Moreover, diverging from the conventional semi-supervised learning frameworks that utilize pseudo-boxes, our method applies pixel-level dense supervision during unsupervised training, which improves detection performance. Comprehensive experiment results reveal that the proposed CSLO-Det attains state-of-the-art performance under multiple semi-supervised datasets.

3D Visual Grounding-Audio: 3D scene object detection based on audio

3D Visual Grounding (3DVG) is a prevalent multi-modal information fusion task capable of accurately localizing target objects referenced in natural language descriptions within a point cloud scene. Nevertheless, the stringent demands for input and output devices present substantial hurdles for the application and integration of 3DVG in fields like remote robotic control and telemedicine. To address this challenge, we introduce several innovative approaches. Firstly, we have initiated a novel multi-modal task, termed 3D Visual Grounding-Audio (3DVG-Audio), which is based on the fusion of audio and point cloud. To the best of our knowledge, this represents the first instance of an Audio-Point Cloud multi-modal task. 3DVG-Audio achieves precise localization of audio-mentioned objects within the point cloud by utilizing the point cloud in conjunction with the corresponding audio input. Secondly, building upon the ScanRefer, we have developed a novel dataset named 3DVG-AudioSet, specifically designed for the training and evaluation of the 3DVG-Audio method. Finally, we have crafted a tailored loss function to further enhance the performance of 3DVG-Audio and introduced a method named AP-Refer, which serves as a benchmark for the task. Extensive experimental results demonstrate the potential for deep integration of audio and point cloud to tackle complex real-world challenges. AP-Refer has successfully addressed the 3DVG-Audio, circumventing the limitations of conventional 3DVG methods, and exhibits significant application potential.

A pixel-level grasp detection method based on Efficient Grasp Aware Network

Abstract This work proposes a novel grasp detection method, the Efficient Grasp Aware Network (EGA-Net), for robotic visual grasp detection. Our method obtains semantic information for grasping through feature extraction. It efficiently obtains feature channel weights related to grasping tasks through the constructed ECA-ResNet module, which can smooth the network’s learning. Meanwhile, we use concatenation to obtain low-level features with rich spatial information. Our method inputs an RGB-D image and outputs the grasp poses and their quality score. The EGA-Net is trained and tested on the Cornell and Jacquard datasets, and we achieve 98.9% and 95.8% accuracy, respectively. The proposed method only takes 24 ms for real-time performance to process an RGB-D image. Moreover, our method achieved better results in the comparison experiment. In the real-world grasp experiments, we use a 6-degree of freedom (DOF) UR-5 robotic arm to demonstrate its robust grasping of unseen objects in various scenes. We also demonstrate that our model can successfully grasp different types of objects without any processing in advance. The experiment results validate our model’s exceptional robustness and generalization.