In this work, an object detection method using variable convolution-improved YOLOv8 is proposed to solve the problem of low accuracy and low efficiency in detecting spanning and irregularly shaped samples. Aiming at the problems of the irregular shape of a target, the low resolution of labeling frames, dense distribution, and the ease of overlap, a deformable convolution module is added to the original backbone network. This allows the model to deal flexibly with the problem of the insufficient perceptual field of the target corresponding to the detection point, and the situations of leakage and misdetection can be effectively improved. In order to solve the issue that small target detection is susceptible to image background and noise interference, the Sim-AM (simple parameter-free attention mechanism) module is added to the backbone network of YOLOv8, which enhances the attention to the underlying features and, thus, improves the detection accuracy of the model. More importantly, the Sim-AM module does not need to add parameters to the original network, which reduces the computation of the model. To address the problem of complex model structures that can lead to slower detection, the spatial pyramid pooling of the backbone network is replaced with focal modulation networks, which greatly simplifies the computation process. The experimental validation was carried out on the scrap steel dataset containing a large number of targets of multiple shapes and sizes. The results showed that the improved YOLOv8 network model improves the AP (average precision) by 2.1%, the mAP (mean average precision value) by 0.8%, and reduces the FPS (frames per second) by 5.4, which meets the performance requirements of real-time industrial inspection.

Large Span Sizes and Irregular Shapes Target Detection Methods Using Variable Convolution-Improved YOLOv8

This article aims to address the issue of low recognition accuracy in existing sorting robots caused by lighting, occlusion, and environmental factors. A fruit recognition method based on a flexible tactile sensor array is described. This method enables the robot to directly perceive the attributes of the objects and identify fruits using a flexible gripper, facilitating intelligent sorting. A novel flexible tactile sensor array is utilized to construct a flexible hand tactile information acquisition platform, which collects tactile time series data for the fruits. Principal component analysis is then employed for dimensionality reduction, followed by the development of an improved particle swarm optimization for the support vector machine model. Through an experimental study, the optimized model is compared with four other models, demonstrating better classification performance. The optimized model achieves an average tactile classification accuracy of up to 98.10% for the five types of fruits. A comparison between the improved optimization algorithm, genetic algorithm, and grid search algorithm reveals the superior optimization performance of the new approach. In the future, this method is expected to be implemented in industrial sorting robots for intelligent sorting on automatic production lines. Furthermore, the algorithm will be further refined to enhance the classification accuracy and efficiency. 

Identification of fruit using a flexible tactile sensor array

WatchOverGPT: A Framework for Real-Time Crime Detection and Response Using Wearable Camera and Large Language Model

Skin cancer is recognized as one of the most perilous diseases globally. In the field of medical image classification, precise identification of early-stage skin lesions is imperative for accurate diagnosis. However, deploying these algorithms on low-cost devices and attaining high-efficiency operation with minimal energy consumption poses a formidable challenge due to their intricate computational demands. This study proposes a lightweight hardware design based on a convolutional neural network (CNN) for real-time processing of skin disease classifiers on portable devices. Our skin cancer recognition processor utilizes an optimally parallel designed processing engine (PE) for global computation, which greatly reduces hardware resource utilization by multiplexing of computational unit circuits. In addition, a design approach that provides loop unrolling effectively reduces the number of data accesses, thereby reducing computational complexity and logic resource requirements. The hardware circuits in this design perform data inference in convolutional, pooling, and fully connected layers based on 16-bit floating-point numbers. Evaluation of the HAM10000 database dataset shows that the architecture achieves an average classification accuracy of 97.8 %. We are the first to implement an all-hardware FPGA-based skin cancer detection platform that offers a 3.5x speedup in recognition compared to existing skin cancer accelerators at 50 MHz while consuming only 0.48 W of power. The implementation of this hardware architecture meets the major constraints of portable devices, featuring low resource utilization, low power consumption, and cost-effectiveness, while still providing efficient classification and high accuracy results. 

Lightweight skin cancer detection IP hardware implementation using cycle expansion and optimal computation arrays methods

An advanced security system utilizing the YOLOv8 algorithm for comprehensive object detection enables real-time identification of individuals and weapons. Innovative features include precise distance estimation and email alerts upon weapon detection, enhancing communication during security breaches. Rigorous testing ensures reliability, while ethical considerations ensure adherence to standards. This project represents a significant contribution to automated threat detection and response, exemplifying advancements in security technology within ethical boundaries, effectively addressing contemporary challenges. The integration of YOLOv8 for object, person, and weapon detection in audio, alongside distance estimation and email notification, marks a substantial leap in security surveillance technology, offering swift threat detection and coordinated response capabilities. Rigorous validation confirms its efficacy, promising to fortify security protocols and proactive threat mitigation strategies, thereby paving the way for further advancements in audio-based threat detection systems.

YOLOv8-Based Person Detection, Distance Monitoring, Speech Alerts, and Weapon Identification with Email Notifications

A high-speed reusable quantized hardware accelerator design for CNN on constrained edge device

. Surgical telementoring is an advanced telemedicine concept where the expert surgeon guides the onsite novice present at the remote location. The efficient telementoring system requires the wireless transmission of high-quality surgical video with less bitrate in less time. The bit rate of the surgical video can be decreased by segmenting the surgical incision region and removing the background region. The High Efficiency Video Coding (HEVC) standard has provided promising results for surgical telementoring applications. But the Rate-Distortion Optimization (RDO) search process in HEVC increases the complexity that in turn increases the encoding time. We propose the method which involves the segmentation of the surgical incision region using the Kernelized Correlation Filter (KCF) object tracking technique. The segmented region is encoded by the complexity-efficient Scalable HEVC (SHVC) to meet the resolution of an end-user device. The complexity of SHVC is decreased by using the Convolutional Neural Network (CNN) and Long- and Short- Term Memory (LSTM) to predict the Coding Tree Unit (CTU) structure. The results show that the proposed method decreases the bitrate significantly for segmented surgical video sequences without degradation in Peak Signal-to-Noise Ratio (PSNR). These results are obtained for the surgical video sequences with slow-moving objects. Furthermore, the CNN + LSTM approach reduces the encoding time of standard SHVC by 51% with negligible Rate-Distortion (RD) performance loss.

/pdf/object-tracking-based-surgical-incision-region-encoding-u9iatkij.pdf

Object Tracking Based Surgical Incision Region Encoding using Scalable High Efficiency Video Coding for Surgical Telementoring Applications

Nowadays the ability of Convolutional Neural Networks (CNN) to mimic the behavioral characteristics of the biological visual neuron makes it a popular choice for image identification. It comprises a deep structure and a high network that performs convolutional calculations. Most of the operations are in CONV layers, hence they are compute-intensive. The need for more computing power for CNN is a key factor in the creation of robust parallel computing platforms like GPUs, or specialized hardware accelerators. Therefore an efficient implementation of CNNs to improve performance using limited resources without accuracy reduction is a challenge. A configurable template-based single convolution layer which includes convolution, relu, and pooling sub-layers is designed and it is used to match all CONV layers of CNN. It contains a processing element array with twenty-five processing elements inside for making parallel computations and data reuse. Pipelining, Loop unrolling, and array partitioning are the techniques for increasing the speed of computing the CONV layer. This design is verified with MNIST handwritten digit image classification on a low-cost, low-memory 32-bit PYNQ-Z2 system on chip edge device. The computation time of the proposed hardware design achieved 86.14% lesser than INTEL core3 CPU, 82.24 % lesser than Haswell core2 CPU, 76.48% lesser than NVIDIA Tesla K80 GPU and 29.26% reduction in compute time when compared to the conventional accelerator. The implementation results show that there was no accuracy drop with an increase in the speed of the computations in the proposed hardware design.

An Efficient Configurable Hardware Accelerator Design for CNN on Low Memory 32-Bit Edge Device

Convolutional neural networks (CNNs) are now often used in deep learning and computer vision applications. Its convolutional layer accounts for most calculations and should be computed fast in a local edge device. Field‐programmable gate arrays (FPGAs) have been adequately explored as promising hardware accelerators for CNNs due to their high performance, energy efficiency, and reconfigurability. This paper developed an efficient FPGA‐based 16‐bit fixed‐point hardware accelerator unit for deep learning applications on the 32‐bit low‐memory edge device (PYNQ‐Z2 board). Additionally, singular value decomposition is applied to the fully connected layer for dimensionality reduction of weight parameters. The accelerator unit was designed for all five layers and employed eight processing elements in convolution layers 1 and 2 for parallel computations. In addition, array partitioning, loop unrolling, and pipelining are the techniques used to increase the speed of calculations. The AXI‐Lite interface was also used to communicate between IP and other blocks. Moreover, the design is tested with grayscale image classification on MNIST handwritten digit dataset and color image classification on the Tumor dataset. The experimental results show that the proposed accelerator unit implementation performs faster than the software‐based implementation. Its inference speed is 89.03% more than INTEL 3‐core CPU, 86.12% higher than Haswell 2‐core CPU, and 82.45% more than NVIDIA Tesla K80 GPU. Furthermore, the throughput of the proposed design is 4.33GOP/s, which is better than the conventional CNN accelerator architectures.

Empowering edge devices: FPGA‐based 16‐bit fixed‐point accelerator with SVD for CNN on 32‐bit memory‐limited systems

Physical Unclonable Functions (PUFs) are significant hardware primitives that use physical variations in the manufacturing process to build unclonable keys. They exploit the process variations (PVs) in transistors across the Integrated Circuits (ICs) that generate a unique signature for each chip for identification and authentication. In this article, a novel Recursive Challenge Feed Arbiter Physical Unclonable Function (RC-FAPUF) is proposed to generate unique, unpredictable, and reliable keys which are independent of the challenges that are generally fed by the user. Subsequently, the uncertainty in the prediction of the key increases while performing the security breach on IoT-enabled access systems like smartcards. The proposed design has a significant advantage in the feed-forward arbitration mechanism to generate reliable keys against PVs. Moreover, the robustness of the keys is measured by reliability is achieved as 99.91% when performed over a temperature that ranges from −40°C to +125°C and 99.23% with ±10% variations in supply voltage. The proposed RC-FAPUF is implemented in a 180 nm CMOS process and the responses regarding PVs are validated through a prediction analysis of 48% with Linear Regression (LR) against security attacks. It is confirmed that a significant improvement over previous works is witnessed with our design. 

Recursive Challenge Feed Arbiter Physical Unclonable Function (RC-FAPUF) In 180nm Process For Reliable Key Generation In IOT Security

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

M. Pullakandam

Author Tools

Chat about Author