Object Identification Research Articles

Using spatial video and deep learning for automated mapping of ground-level context in relief camps

BackgroundThe creation of relief camps following a disaster, conflict or other form of externality often generates additional health problems. The density of people in a highly stressed environment with questionable safe food and water access presents the potential for infectious disease outbreaks. These camps are also not static data events but rather fluctuate in size, composition, and level and quality of service provision. While contextualized geospatial data collection and mapping are vital for understanding the nature of these camps, various challenges, including a lack of data at the required spatial or temporal granularity, as well as the issue of sustainability, can act as major impediments. Here, we present the first steps toward a deep learning-based solution for dynamic mapping using spatial video (SV).MethodsWe trained a convolutional neural network (CNN) model on a SV dataset collected from Goma, Democratic Republic of Congo (DRC) to identify relief camps from video imagery. We developed a spatial filtering approach to tackle the challenges associated with spatially tagging objects such as the accuracy of global positioning system and positioning of camera. The spatial filtering approach generates smooth surfaces of detection, which can further be used to capture changes in microenvironments by applying techniques such as raster math.ResultsThe initial results suggest that our model can detect temporary physical dwellings from SV imagery with a high level of precision, recall, and object localization. The spatial filtering approach helps to identify areas with higher concentrations of camps and the web-based tool helps to explore these areas. The longitudinal analysis based on applying raster math on the detection surfaces revealed locations, which had a considerable change in the distribution of tents over space and time.ConclusionsThe results lay the groundwork for automated mapping of spatial features from imagery data. We anticipate that this work is the building block for a future combination of SV, object identification and automatic mapping that could provide sustainable data generation possibilities for challenging environments such as relief camps or other informal settlements.

Developing a digital management system for museum collections using RFID and enhanced GIS technology

In recent years, the integration of Radio Frequency Identification (RFID) technology with deep learning has revolutionized the Internet of Things (IoT), leading to significant advancements in object identification, management, and control. Museums, which rely heavily on the meticulous management of collections, require precise and efficient systems to monitor and oversee their valuable assets. Traditional methods for tracking and managing museum collections often fall short in providing real-time updates and ensuring optimal environmental conditions for preservation. These shortcomings place a considerable burden on museum staff, who must manually track, inspect, and maintain extensive collections. This study addresses these challenges by proposing an advanced electronic management system that leverages the synergy between RFID technology and Geographical Information Systems (GIS). By integrating an enhanced LANDMARC algorithm into our geoinformation framework, the system visually represents the real-time location of museum collections on custom electronic maps, significantly improving the accuracy and timeliness of environmental monitoring. Additionally, RFID technology is utilized to continuously identify the real-time location of museum staff, facilitating the evaluation of their inspection tasks. This dual approach not only enhances the operational efficiency of collection management but also supports the development of intelligent, automated systems for museums, advancing the application of RFID technology in item identification and location management.

Ordinal information, but not metric information, matters in binding feature with depth location in three-dimensional contexts.

A basic function of human visual perception is the ability to recognize and locate objects in the environment. It has been shown that two-dimensional (2D) location can reliably bias judgments on object identity (spatial congruency bias; Golomb et al., 2014), suggesting that 2D location information is automatically bound with object features to induce such a bias. Although the binding problem of feature and location has been vigorously studied under various 2D settings, it remains unclear how depth location can be bound with object features in a three-dimensional (3D) setting. Here we conducted five experiments in various 3D contexts using the congruency bias paradigm, and found that changes of object's depth location could influence perceptual judgments on object features differently depending on whether its relative depth order with respect to others changed or not. Experiments 1 and 2 showed that the judgments on an object's color could be affected by changes in its ordinal depth, but not by changes in its absolute metric depth. Experiment 3 showed that the bias was asymmetric-changes in an object's color did bias the judgments on metric-depth location, but not if its depth order had changed. Experiments 4 and 5 investigated whether these findings could be generalized to a peripersonal near space and a large-scale far space, respectively, using more ecological virtual environments. Our findings suggest that ordinal depth plays a special role in feature-location binding: an object may be automatically bound with its relative depth relation, but not with its absolute metric-depth location. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Deep Learning Model for Smart Wearables Device to Detect Human Health Conduction

With the proliferation of smart wearables, motion wristbands provide a wealth of data essential for comprehending the dynamic nature of health. However, outlier detection is typically necessary due to the presence of unknown outliers in their multidimensional activity data. Conventional approaches frequently result in incorrect object identification due to the curse of dimensionality. Using the Gaussian Mixture Generative Model (GMGM), we provide a method to identify outliers and address this problem. Training on raw data is done using a VariationalAutoencoder (VAE). While avoiding rebuilding mistakes, we want to achieve as many brief features as possible. To predict the likelihood that examples contain many types of data, a DBN will utilise feature extractions and latent distributions in the future. The model's robustness is enhanced by enhancing the VAE, deep learning components, and the GMM overall. When densities surpass the training level, the Gaussian Mixture Model identifies outliers. To achieve this, it makes educated guesses about the densities of each data point. Compared to the deep learning Autoencoding Gaussian Mixture Model (DAGMM), GMGM achieves a 5.5% higher area under the curve (AUC) on the ODDS standard dataset. Experiments conducted on real datasets further demonstrate the efficacy of this strategy.

A Comparison of Thunderstorm Identification Methods

Abstract Climatological analysis of thunderstorm occurrence is important since thunderstorms have far-reaching societal impacts. Historically, the majority of thunderstorm-related climatologies have focused on Eulerian frames of reference resulting in thunderstorm day or lightning density summaries. However, a Lagrangian frame of reference is required to answer more in-depth questions such as spatial distribution and variability in thunderstorm initiation. Lagrangian approaches generally utilize object identification and tracking algorithms with tracks then classified as being a thunderstorm or not. Prior methods for thunderstorm identification have been based on classification criteria such as radar reflectivity thresholds, a combination of radar reflectivity thresholds and temporal longevity thresholds, or a combination of radar reflectivity and cloud-to-ground lightning occurrence. However, a comparison of different methods and an evaluation of their accuracy have not been documented in the peer-reviewed literature. This study examines the impact of thunderstorm identification methodology choice. Differences in three thunderstorm identification methodologies are examined over the central plains of the United States during an 11-yr study period. Results show that there is a sensitivity to methodological choice with differences in the number of candidate thunderstorms classified as thunderstorms, as well as the resulting spatial pattern of thunderstorms. Additionally, this study provides insight into the accuracy of each method via a multiyear comparison of each method to regional lightning mapping array total lightning detections where significant differences were observed between methods with the method incorporating cloud-to-ground lightning data providing the best performance metrics. Significance Statement Previous research has utilized a variety of criteria to identify thunderstorms in order to generate datasets of thunderstorm occurrence. This study directly compares commonly used criteria, demonstrating that the choice of thunderstorm identification criteria impacts the composition and accuracy of resulting datasets of thunderstorm occurrence.

Optical Brewster interfaces enabled object identification and 3D reconstruction

Efficient and accurate object identification and 3D reconstruction are crucial for processing image information in visual imaging. Here, we propose a novel scheme for all-optical 2D contour identification and 3D reconstruction based on optical Brewster interfaces. It is revealed that 2D amplitude and phase contours for high-contrast and low-contrast objects can be identified, which is attributed to the 1D and 2D light fields manipulated by the photonic spin Hall and the Brewster effects. The 3D model can be reconstructed by rotating or slicing the high-contrast objects and by inverting the thickness of the low-contrast objects. The study potentially opens up opportunities in applications such as intelligent driving and microscopic imaging.

Design and development of machine vision robotic arm for vegetable crops in hydroponics

Modern agricultural machinery such as harvesting robotic arms are necessary to optimize the semi-automated agricultural processes to meet the ever-growing food needs of the population of the world. Production of low cost and highly efficient robotic arms are needed to meet the needs of the small-scale growers of underdeveloped countries. In this regard, mechanical design, sensor placement, and object identification are essential to optimize the performance of agricultural robots. This research is conducted to design a fully automated robotic arm for fruit picking in hydroponics system and research farm using machine vision to help the smallholders. For this purpose, a robotic arm with 1.3 m in height is designed using aluminum (18-gauge) and mild steel (MS-16) as fabrication material for the mechanical structure. The prototype design is tested for stress estimation at various payloads using SolidWorks simulations. The proposed robotic arm is based on a four degrees of freedom (4-DoF) design with the gripper having an opening range of 5.5 to 12 cm depending upon the task to handle various objects. The robotic arm is installed on an expandable vertical mobile platform that enables an expanded operational workspace with lower energy consumption. The total weight of the robotic arm is 60 kgs housing a payload capacity ranging between 8 and 10 kgs in accordance with industry-standard load-bearing specifications. The inverse kinematic algorithm using DH-table is computed with an accuracy of up to 95 % and target height of gripper is cross checked by mounting the ultrasonic sensor at the base of robotic arm. The YOLOv8 algorithm is used for object detection using the depth sense camera having angle range of 0.3 m to 3 m with the precision of up to 96 %. The time needed for recognition of fruits and pitching was about 15 s, with a success rate of up to 90 %. This research produces a low-cost and efficient solution for stallholders by developing a fully automated robotic arm for fruit picking. It optimizes agricultural productivity through improved mechanical design, sensor accuracy, and object detection which reduces labor costs by increasing efficiency of semi-automated farming systems. Further research is required to optimize the overall weight of the system and automation of the movement of robotic arm system between the consecutive rows to build a fully autonomous fruit picking operation in hydroponics.

Translated object identification for efficient ghost imaging

Alignment of a single-pixel quantum ghost imaging setup is complex and requires extreme precision. Due to misalignment, easily created by human error in the alignment process, reconstructed images are often translated off the central imaging axis. This becomes problematic for intelligent object detection and identification in fast imaging cases, as these algorithms are unable to achieve early image identification. Here, we implemented a U-net algorithm to correctly recognize images in the early reconstruction stage regardless of any off-axis translation. The U-net was trained on a uniquely curated blurred, noised, and off-axis translated dataset. We achieved a 5× reduction in imaging speeds by early image identification in four different translation directions.

Charting the growth through intelligence: A SWOC analysis on AI-assisted radiologic bone age estimation.

Bone age estimation (BAE) is based on skeletal maturity and degenerative process of the skeleton. The clinical importance of BAE is in understanding the pediatric and growth-related disorders; whereas medicolegally it is important in determining criminal responsibility and establishing identification. Artificial Intelligence (AI) has been used in the field of the field of medicine and specifically in diagnostics using medical images. AI can greatly benefit the BAE techniques by decreasing the intra observer and inter observer variability as well as by reducing the analytical time. The AI techniques rely on object identification, feature extraction and segregation. Bone age assessment is the classical example where the concepts of AI such as object recognition and segregation can be used effectively. The paper describes various AI based algorithms developed for the purpose of radiologic BAE and the performances of the models. In the current paper we have also carried out qualitative analysis using Strength, Weakness, Opportunities and Challenges (SWOC) to examine critical factors that contribute to the application of AI in BAE. To best of our knowledge, the SWOC analysis is being carried out for the first time to assess the applicability of AI in BAE. Based on the SWOC analysis we have provided strategies for successful implementation of AI in BAE in forensic and medicolegal context.

End-to-end multiple object tracking in high-resolution optical sensors of drones with transformer models

Drone aerial imaging has become increasingly important across numerous fields as drone optical sensor technology continues to advance. One critical challenge in this domain is achieving both accurate and efficient multi-object tracking. Traditional deep learning methods often separate object identification from tracking, leading to increased complexity and potential performance degradation. Conventional approaches rely heavily on manual feature engineering and intricate algorithms, which can further limit efficiency. To overcome these limitations, we propose a novel Transformer-based end-to-end multi-object tracking framework. This innovative method leverages self-attention mechanisms to capture complex inter-object relationships, seamlessly integrating object detection and tracking into a unified process. By utilizing end-to-end training, our approach simplifies the tracking pipeline, leading to significant performance improvements. A key innovation in our system is the introduction of a trajectory detection label matching technique. This technique assigns labels based on a comprehensive assessment of object appearance, spatial characteristics, and Gaussian features, ensuring more precise and logical label assignments. Additionally, we incorporate cross-frame self-attention mechanisms to extract long-term object properties, providing robust information for stable and consistent tracking. We further enhance tracking performance through a newly developed self-characteristics module, which extracts semantic features from trajectory information across both current and previous frames. This module ensures that the long-term interaction modules maintain semantic consistency, allowing for more accurate and continuous tracking over time. The refined data and stored trajectories are then used as input for subsequent frame processing, creating a feedback loop that sustains tracking accuracy. Extensive experiments conducted on the VisDrone and UAVDT datasets demonstrate the superior performance of our approach in drone-based multi-object tracking.

Establishing effective learning bridge cross multi-scale feature maps for object detection and semantic segmentation

ABSTRACT In the field of image object detection and semantic segmentation, improving the accuracy of object identification and segmentation is a primary goal. To achieve this, leveraging the potential of multi-scale information through feature map refinement and fusion has been widely recognized. However, existing feature fusion methods either design more complex feature pyramid networks, replace existing detectors, or incrementally introduce feature fusion modules, overlooking the effective approach of enhancing spatial information in deep feature maps. We propose a novel pluggable feature fusion paradigm termed ‘Effective Learning Bridge’. Our research introduces an efficient and adaptive learning mechanism that builds learning bridges between feature maps at different scales within the feature pyramid, thereby enhancing the spatial information of objects in deep feature maps. This mechanism is specifically designed for multi-scale feature maps and can be seamlessly integrated into any network incorporating feature maps. By altering the model’s backpropagation path, we successfully improve learning efficiency, which in turn enhances the accuracy of object detection and segmentation. Our proposed paradigm and method were extensively evaluated through experiments on SIMD, HRSID, and WHDLD datasets and benchmark models. The results unequivocally demonstrate the effectiveness of our approach in significantly improving the accuracy of object detection and semantic segmentation, as well as the overall learning efficiency of the model.

Survivor detection approach for post earthquake search and rescue missions based on deep learning inspired algorithms

Rapid and reliable detection of human survivors trapped under debris is crucial for effective post-earthquake search and rescue (SAR) operations. This paper presents a novel approach to survivor detection using a snake robot equipped with deep learning (DL) based object identification algorithms. We evaluated the performance of three main algorithms: Faster R-CNN, Single Shot MultiBox Detector (SSD), and You Only Look Once (YOLO). While these algorithms are initially trained on the PASCAL VOC 2012 dataset for human identification, we address the lack of a dedicated dataset for trapped individuals by compiling a new dataset of 200 images that specifically depicts this scenario, featuring cluttered environment and occlusion. Our evaluation takes into account detection accuracy, confidence interval, and running time. The results demonstrate that the YOLOv10 algorithm achieves the 98.4 mAP@0.5, accuracy of 98.5% for inference time of 15 ms. We validate the performance of these algorithms using images of human survivors trapped under debris and subjected to various occlusions.

ACT-FRCNN: Progress Towards Transformer-Based Object Detection

Maintaining a high input resolution is crucial for more complex tasks like detection or segmentation to ensure that models can adequately identify and reflect fine details in the output. This study aims to reduce the computation costs associated with high-resolution input by using a variant of transformer, known as the Adaptive Clustering Transformer (ACT). The proposed model is named ACT-FRCNN. Which integrates ACT with a Faster Region-Based Convolution Neural Network (FRCNN) for a detection task head. In this paper, we proposed a method to improve the detection framework, resulting in better performance for out-of-domain images, improved object identification, and reduced dependence on non-maximum suppression. The ACT-FRCNN represents a significant step in the application of transformer models to challenging visual tasks like object detection, laying the foundation for future work using transformer models. The performance of ACT-FRCNN was evaluated on a variety of well-known datasets including BSDS500, NYUDv2, and COCO. The results indicate that ACT-FRCNN reduces over-detection errors and improves the detection of large objects. The findings from this research have practical implications for object detection and other computer vision tasks.

How Infants Link Nonce Phrases to Scenes With Objects and Predicates.

When infants hear sentences containing unfamiliar words, are some language-world links (such as noun-object) more readily formed than others (verb-predicate)? We examined English learning 14-15-month-olds' capacity for linking referents in scenes with bisyllabic nonce utterances. Each of the two syllables referred either to the object's identity, or the object's motion. Infants heard the syllables in either a Verb-Subject (VS) or Subject-Verb (SV) order. Learning was tested using preferential looking. The results showed that infants learned the nouns and verbs equally well. In addition, in both the VS- and SV-consistent conditions, infants learned the meaning of the utterance-final syllable, but not the utterance-initial one. A follow-up experiment that manipulated the prosodic cues of the test phrases confirmed that infants had decomposed the bisyllabic phrases into two distinct word-units. Thus, any biases potentially favoring noun or verb learning played a smaller role than utterance position did when noun and verb learning were equally supported by context.

Enhancing Surveillance Systems with Cost-Effective Ultrasonic Radar for Object Detection and Tracking

Object detection is critical in surveillance systems because it enables timely identification of unauthorized objects, which is essential for maintaining security and mitigating risks. Existing approaches to surveillance typically suffer from limited coverage, variable detection range, moderate accuracy, high cost, and complex setup requirements. This article presents an approach to object detection using microcontroller-based ultrasonic sensors. Our approach leverages four distinct processing phases to create a radar-like system capable of real-time detection and autonomous decision-making. In this study, we conducted experiments by integrating more than six peripheral modules with the Arduino platform. By evaluating 17 diverse test cases in various scenarios and environments, the approach demonstrated enhanced object tracking and robustness compared to existing methods. The system effectively detects objects within the targeted area, providing precise distance measurements (around 50 cm) and position information (0 to 360 degrees). Moreover, our approach enabled the identification of three risk zones—medium, high-risk, and mild danger—within the critical region, contributing to improved security and risk management. The results reveal the system’s effectiveness in real-time detection, accurate distance estimation, and comprehensive risk assessment. Overall, our study significantly contributes to the advancement of object detection technology by effectively addressing the limitations of existing methods and offering a cost-effective and practical solution. Our research has the potential to monitor objects in surveillance systems across various domains, with significant implications for enhancing security, risk mitigation, and monitoring in industries reliant on effective object detection systems. Jagannath University Journal of Science, Volume 11, Number 1, June 2024, pp. 157−171

Low power RTL implementation of Tiny-YOLO-v2 DCNN hardware accelerator on Virtex-7 FPGA

Deep Convolution Neural Networks (DCNNs) are widely used in real-time applications, including image classification, speech recognition, and object detection. However, there are challenges for real-time applications on portable devices like mobile phones or embedded systems. Most object detection models are optimized for desktop configurations, requiring fast GPUs. Shallower networks with fewer computational complexities have been proposed for real-time detection, but ultimately compromise detection accuracy. Performance and complexity trade-offs are significant for computationally complex deep networks. This work aims to implement the CNN-based object detection model Tiny-Yolo-v2 on a Field Programmable Gate Array (FPGA) using Register Transfer Logic (RTL) as a native language. Hardware implementation is synthesized on The AMD Virtex 7 FPGA VC709 Connectivity Kit using VHDL code on Vivado 2020.1. This is the first, up to the authors' knowledge, RTL implementation of the Tiny-Yolo-v2 object identification algorithm on FPGA. The power consumed by the CNN layers equals 7.09W at a frequency of 100MHz.

DroneSilient (drone + resilient): an anti-drone system

AbstractIt is imperative to take a holistic strategy to thwarting drone threats, including the identification of drones and drone-like gadgets like ornithopters that visually imitate birds. In this study, we present the DroneSilient System, a novel anti-drone system that combines different parts. The DroneSilient system includes components that connect to RF identification technology and image-capture technology. A modified bloom filter method is used to further identify the recognized object after a drone-like object has been found, allowing for the differentiation between regular drones, ornithopters, and genuine birds. The CNN (Convolutional Neural Network) method, created using the Google Cloud Platform and AutoML widget, is used in our model for object identification and categorization. DroneSilient has an RF sensor that can identify and imitate the threat presented by recognized drones. Convolutional Network, Modified Blooms Algorithm, RFID, and RF Sensor systems are all integrated into the DroneSilient system as part of this methodology combination, which provides a thorough method for identifying and eliminating drone threats. The bloom filter proposed takes 27.6 to 12.4 microseconds. Overall time for handling the unauthorized drone will be less than 180 s. By tackling every facet of the problem, our strategy outperforms many current anti-drone solutions in terms of functionality.

Van der Waals Heterojunction Based Self-Powered Biomimetic Dual-Mode Sensor for Precise Object Identification.

The design and fabrication of materials that can concurrently respond to light and gas within the dual-modal recognition domain present a significant challenge due to contradictory structural requirements. This innovative strategy introduces a type-I heterojunction, combining the properties of Sb2Te3 and WSe2 nanosheets, to overcome these obstacles. The heterojunction is prepared through a precise stacking approach to create a single-side barrier on the valence band and a near-zero offset on the conduction band. The resulting Sb2Te3/WSe2 heterojunction demonstrates unparalleled performance, showcasing the best integrated photoelectric and gas sensing performance in a single device to date. Based on the above features, the heterojunction successfully integrates visual and olfactory sensing performance, achieving the first biomimetic visual-olfactory dual-mode recognition in a single device. This simulation increased the accuracy of distinguishing electric and fuel-powered cars from ≈50% to ≈96%. This work introduces a novel approach to creating efficient, self-powered sensing materials, paving the way for next-generation biomimetic dual-model devices with broad applications in environmental protection, medical care, and other fields.

Using Eye-Tracking to Evaluate Novel Augmented Reality Applications for Maritime Operations

This paper presents the developments across a multi-year collaborative industry-academia R&D project designing and testing novel Augmented Reality (AR) solutions for differing maritime operations and work tasks. We describe the step-wise approach taken in our Human Factors testing program exploring the effects of AR on maritime operators. This paper focuses specifically on our empirical simulator laboratory experiments using differing data collection designs, tools and operational scenarios to investigate operator Situation Awareness, cognitive workload, performance and usability. Moving from comparatively rudimentary measures using static scenarios, desktop data collections and post hoc video analysis to implementing eye-tracking and automated object identification in dynamic scenarios and full-mission simulated environments, we present an overview of how our testing program has evolved and lessons learned. Further, we discuss ongoing research and future plans to better understand the effects of AR on maritime end-users to implement human-centred solutions more effectively in maritime settings.

Enhanced climate change resilience on wheat anther morphology using optimized deep learning techniques.

Wheat commands attention due to its significant impact on culture, nutrition, the economy, and the guarantee of food security. The anticipated rise in temperatures resulting from climate change is a key factor contributing to food insecurity, as it markedly reduces wheat harvests. Terminal heat stress mostly affects spike fertility in wheat, specifically influencing pollen fertility and anther morphology. This research especially focuses on the shape of anthers and examines the effects of heat stress. The DinoLite Microscope's high-resolution images are used to measure the length and width of wheat anthers. By using object identification techniques, the research accurately measures the length and width of each anther in images, offering valuable insights into the differences between various wheat varieties. Furthermore, Deep Learning (DL) methodologies are utilized to enhance agriculture, specifically employing record categorization to advance plant breeding management. Given the ongoing challenges in agriculture, there is a belief that incorporating the latest technologies is crucial. The primary objective of this study is to explore how Deep Learning algorithms can be beneficial in categorizing agricultural records, particularly in monitoring and identifying variations in spring wheat germplasm. Various Deep Learning algorithms, including Convolution Neural Network (CNN), LeNet, and Inception-V3 are implemented to classify the records and extract various patterns. LeNet demonstrates optimized accuracy in classifying the records, outperforming CNN by 52% and Inception-V3 by 70%. Moreover, Precision, Recall, and F1 Measure are utilized to ascertain accuracy levels. The investigation also enhances our comprehension of the distinct roles played by various genes in abiotic stress tolerance among diverse wheat varieties. The outcomes of the research hold the potential to transform agricultural practices by introducing a more effective, data-driven approach to plant breeding management.