scholarly journals Accuracy and Efficiency Comparison of Object Detection Open-Source Models

2021 ◽  
Vol 17 (05) ◽  
pp. 165
Author(s):  
Brahim Jabir ◽  
Noureddine Falih ◽  
Khalid Rahmani
Keyword(s):  
Computer Vision ◽  
Object Detection ◽  
Open Source ◽  
Large Scale ◽  
Performance Comparison ◽  
Yield Potential ◽  
Temperate Climate ◽  
Weed Species ◽  
Weed Detection ◽  
Cloudy Weather

In agriculture, weeds cause direct damage to the crop, and it primarily affects the crop yield potential. Manual and mechanical weeding methods consume a lot of energy and time and do not give efficient results. Chemical weed control is still the best way to control weeds. However, the widespread and large-scale use of herbicides is harmful to the environment. Our study's objective is to propose an efficient model for a smart system to detect weeds in crops in real-time using computer vision. Our experiment dataset contains images of two different weed species well known in our region strained in this region with a temperate climate. The first is the Phalaris Paradoxa. The second is Convolvulus, manually captured with a professional camera from fields under different lighting conditions (from morning to afternoon in sunny and cloudy weather). The detection of weed and crop has experimented with four recent pre-configured open-source computer vision models for object detection: Detectron2, EfficientDet, YOLO, and Faster R-CNN. The performance comparison of weed detection models is executed on the Open CV and Keras platform using python language.

ON METHODS OF OBJECT DETECTION IN VIDEO STREAMS

2017 ◽  
Vol 2 (1) ◽  
pp. 80-87
Author(s):  
Puyda V. ◽  
◽  
Stoian. A.
Keyword(s):  
Computer Vision ◽  
Object Detection ◽  
Open Source ◽  
Feature Detection ◽  
Video Stream ◽  
Object Identification ◽  
Vision Systems ◽  
Modern Computer ◽  
Computer Vision Systems ◽  
Open Source Hardware

Detecting objects in a video stream is a typical problem in modern computer vision systems that are used in multiple areas. Object detection can be done on both static images and on frames of a video stream. Essentially, object detection means finding color and intensity non-uniformities which can be treated as physical objects. Beside that, the operations of finding coordinates, size and other characteristics of these non-uniformities that can be used to solve other computer vision related problems like object identification can be executed. In this paper, we study three algorithms which can be used to detect objects of different nature and are based on different approaches: detection of color non-uniformities, frame difference and feature detection. As the input data, we use a video stream which is obtained from a video camera or from an mp4 video file. Simulations and testing of the algoritms were done on a universal computer based on an open-source hardware, built on the Broadcom BCM2711, quad-core Cortex-A72 (ARM v8) 64-bit SoC processor with frequency 1,5GHz. The software was created in Visual Studio 2019 using OpenCV 4 on Windows 10 and on a universal computer operated under Linux (Raspbian Buster OS) for an open-source hardware. In the paper, the methods under consideration are compared. The results of the paper can be used in research and development of modern computer vision systems used for different purposes. Keywords: object detection, feature points, keypoints, ORB detector, computer vision, motion detection, HSV model color

scholarly journals A Survey on Contrastive Self-Supervised Learning

Technologies ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 2
Author(s):  
Ashish Jaiswal ◽  
Ashwin Ramesh Babu ◽  
Mohammad Zaki Zadeh ◽  
Debapriya Banerjee ◽  
Fillia Makedon
Keyword(s):  
Computer Vision ◽  
Supervised Learning ◽  
Language Processing ◽  
Large Scale ◽  
Performance Comparison ◽  
Extensive Review ◽  
Future Directions ◽  
Dominant Component ◽  
Supervised Methods ◽  
The Cost

Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudolabels as supervision and use the learned representations for several downstream tasks. Specifically, contrastive learning has recently become a dominant component in self-supervised learning for computer vision, natural language processing (NLP), and other domains. It aims at embedding augmented versions of the same sample close to each other while trying to push away embeddings from different samples. This paper provides an extensive review of self-supervised methods that follow the contrastive approach. The work explains commonly used pretext tasks in a contrastive learning setup, followed by different architectures that have been proposed so far. Next, we present a performance comparison of different methods for multiple downstream tasks such as image classification, object detection, and action recognition. Finally, we conclude with the limitations of the current methods and the need for further techniques and future directions to make meaningful progress.

scholarly journals Salient Object Detection Techniques in Computer Vision—A Survey

Entropy ◽  
2020 ◽  
Vol 22 (10) ◽  
pp. 1174
Author(s):  
Ashish Kumar Gupta ◽  
Ayan Seal ◽  
Mukesh Prasad ◽  
Pritee Khanna
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Object Detection ◽  
Large Scale ◽  
Research Work ◽  
Salient Object Detection ◽  
Future Research ◽  
Automatic Identification ◽  
Salient Object ◽  
Detection Techniques

Detection and localization of regions of images that attract immediate human visual attention is currently an intensive area of research in computer vision. The capability of automatic identification and segmentation of such salient image regions has immediate consequences for applications in the field of computer vision, computer graphics, and multimedia. A large number of salient object detection (SOD) methods have been devised to effectively mimic the capability of the human visual system to detect the salient regions in images. These methods can be broadly categorized into two categories based on their feature engineering mechanism: conventional or deep learning-based. In this survey, most of the influential advances in image-based SOD from both conventional as well as deep learning-based categories have been reviewed in detail. Relevant saliency modeling trends with key issues, core techniques, and the scope for future research work have been discussed in the context of difficulties often faced in salient object detection. Results are presented for various challenging cases for some large-scale public datasets. Different metrics considered for assessment of the performance of state-of-the-art salient object detection models are also covered. Some future directions for SOD are presented towards end.

scholarly journals OpenWeedLocator (OWL): an open-source, low-cost device for fallow weed detection

2022 ◽  
Vol 12 (1) ◽  
Author(s):  
Guy Coleman ◽  
William Salter ◽  
Michael Walsh
Keyword(s):  
Open Source ◽  
Weed Control ◽  
Technology Development ◽  
Low Cost ◽  
Yield Potential ◽  
Low Density ◽  
Weed Detection ◽  
Site Specific ◽  
South Wales ◽  
Control Community

AbstractThe use of a fallow phase is an important tool for maximizing crop yield potential in moisture limited agricultural environments, with a focus on removing weeds to optimize fallow efficiency. Repeated whole field herbicide treatments to control low-density weed populations is expensive and wasteful. Site-specific herbicide applications to low-density fallow weed populations is currently facilitated by proprietary, sensor-based spray booms. The use of image analysis for fallow weed detection is an opportunity to develop a system with potential for in-crop weed recognition. Here we present OpenWeedLocator (OWL), an open-source, low-cost and image-based device for fallow weed detection that improves accessibility to this technology for the weed control community. A comprehensive GitHub repository was developed, promoting community engagement with site-specific weed control methods. Validation of OWL as a low-cost tool was achieved using four, existing colour-based algorithms over seven fallow fields in New South Wales, Australia. The four algorithms were similarly effective in detecting weeds with average precision of 79% and recall of 52%. In individual transects up to 92% precision and 74% recall indicate the performance potential of OWL in fallow fields. OWL represents an opportunity to redefine the approach to weed detection by enabling community-driven technology development in agriculture.

scholarly journals OpenWeedLocator (OWL): an open-source, low-cost 1 device for fallow weed detection.

2021 ◽  
Author(s):  
Guy Coleman ◽  
William Salter ◽  
Michael Walsh
Keyword(s):  
Open Source ◽  
Weed Control ◽  
Technology Development ◽  
Low Cost ◽  
Yield Potential ◽  
Low Density ◽  
Weed Detection ◽  
Living Plant ◽  
Detection Technology ◽  
Assembly Instructions

Abstract The use of a fallow phase is an important tool for maximizing yield potential in moisture limited environments. There is a focus on ensuring these phases are maintained weed-free as even low weed densities can be detrimental to fallow efficiency. Repeated whole field herbicide treatment to control low-density weed populations is expensive and wasteful. Site-specific application of herbicide treatments to low density fallow weed populations is currently facilitated by sensor-based devices that detect chlorophyll fluorescence from living plant tissue. The use of image-based weed detection technology for fallow weed detection is an opportunity to develop an approach that can be translated for in-crop weed recognition. Here we present the OpenWeedLocator (OWL), an open-source, low-cost image-based approach for fallow weed detection that improves accessibility to this technology for the weed control community. A comprehensive repository, containing all code and assembly instructions, has been developed that will allow for community driven improvement over time. Four different colour-based weed detection algorithms were tested with the OWL system over seven fallow field scenarios under varying light, soil and stubble conditions. Across all scenarios, the four algorithms were similarly effective in detecting fallow weeds with average precision and recall of 79% and 52%, respectively. In individual transects, precision and recall values of up to 92% and 74%, respectively, suggest the potential fallow weed detection performance of the colour-based system. OWL represents an opportunity to redefine the approach to weed detection by enabling community-driven technology development and implementation in the weed control industry.

A Hardware-Software Co-Design for Object Detection Using High-Level Synthesis Tools

2019 ◽  
Vol 8 (1) ◽  
pp. 63-73
Author(s):  
Aiman Badawi ◽  
Muhammad Bilal
Keyword(s):  
Computer Vision ◽  
Object Detection ◽  
Open Source ◽  
Video Processing ◽  
Modular Design ◽  
High Level Synthesis ◽  
Unified Framework ◽  
Daunting Task ◽  
High Level ◽  
Rapid Deployment

Object detection is a vital component of modern video processing systems, and despite the availability of several efficient open-source feature-classifier frameworks and their corresponding implementation schemes, inclusion of this feature as a drop-in module in larger computer vision systems is still considered a daunting task. To this end, this work describes an open-source unified framework which can be used to train, test, and deploy an SVM-based object detector as a hardware-software co-design on FPGA using Simulink high-level synthesis tool. The proposed modular design can be seamlessly integrated within full systems developed using Simulink Computer Vision toolbox for rapid deployment. FPGA synthesis results show that the proposed hardware architecture utilizes fewer logic resources than the contemporary designs for similar operation. Moreover, experimental evidence has been provided to prove the generalization of the framework in efficiently detecting a variety of objects of interest including pedestrians, faces and traffic signs.

scholarly journals Monitoring the Spread of Water Hyacinth (Pontederia crassipes): Challenges and Future Developments

2021 ◽  
Vol 9 ◽  
Author(s):  
Aviraj Datta ◽  
Savitri Maharaj ◽  
G. Nagendra Prabhu ◽  
Deepayan Bhowmik ◽  
Armando Marino ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Water Hyacinth ◽  
Large Scale ◽  
Ecological Impacts ◽  
Automated Image Analysis ◽  
Machine Learning Techniques ◽  
Yield Potential ◽  
Effective Control ◽  
Weed Species ◽  
Invasive Weed

Water hyacinth (Pontederia crassipes, also referred to as Eichhornia crassipes) is one of the most invasive weed species in the world, causing significant adverse economic and ecological impacts, particularly in tropical and sub-tropical regions. Large scale real-time monitoring of areas of chronic infestation is critical to formulate effective control strategies for this fast spreading weed species. Assessment of revenue generation potential of the harvested water hyacinth biomass also requires enhanced understanding to estimate the biomass yield potential for a given water body. Modern remote sensing technologies can greatly enhance our capacity to understand, monitor, and estimate water hyacinth infestation within inland as well as coastal freshwater bodies. Readily available satellite imagery with high spectral, temporal, and spatial resolution, along with conventional and modern machine learning techniques for automated image analysis, can enable discrimination of water hyacinth infestation from other floating or submerged vegetation. Remote sensing can potentially be complemented with an array of other technology-based methods, including aerial surveys, ground-level sensors, and citizen science, to provide comprehensive, timely, and accurate monitoring. This review discusses the latest developments in the use of remote sensing and other technologies to monitor water hyacinth infestation, and proposes a novel, multi-modal approach that combines the strengths of the different methods.

PEMBUATAN PENDETEKSI OBYEK DENGAN METODE YOU ONLY LOOK ONCE (YOLO) UNTUK AUTOMATED TELLER MACHINE (ATM)

2019 ◽  
Vol 17 (1) ◽  
pp. 69-76
Author(s):  
Mohammad Shiddiq Ghozali
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Object Detection ◽  
Open Source ◽  
Automated Teller Machine

Perkembangan Teknologi Informasi dan Komunikasi begitu pesat di zaman sekarang ini. Diikuti pula dengan perkembangan di bidang Artificial Intelligence (AI) atau Kecerdasan Buatan. Di Indonesia sendiri masih belum begitu populer dikalangan masyarakat akan tetapi perusahaan-perusahaan IT berlomba-lomba menciptakan inovasi dibidang Kecerdasan Buatan dan penerapan Kecerdasan Buatan disegala aspek kehidupan. Contoh kasus di Automated Teller Machine (ATM), seringkali terjadi kejahatan di ATM seperti pengintaian nomor pin, skimming, lebanese loop dan kejahatan lainnya. Walaupun di ATM sudah terdapat CCTV akan tetapi penjahat menggunakan alat bantu untuk menutupi wajahnya seperti helm, topi, masker dan kacamata hitam. Biasanya didepan pintu masuk ATM terpampang larangan untuk tidak menggunakan helm, topi, masker dan kacamata hitam serta tidak membawa rokok. Akan tetapi larangan itu masih tetap ada yang melanggar, dikarenakan tidak ada tindak lanjut ketika seseorang menggunakan benda-benda yang dilarang dibawa kedalam ATM. Oleh karena itu penulis membuat sistem pendeteksi obyek di bidang Kecerdasan Buatan untuk mendeteksi benda-benda yang dilarang digunakan ketika berada di ATM. Salah satu metode yang digunakan untuk menciptakan Object Detection yaitu You Only Look Once (YOLO). Implementasi ide ini tersedia pada DARKNET (open source neural network). Cara kerja YOLO yaitu dengan melihat seluruh gambar sekali, kemudian melewati jaringan saraf sekali langsung mendeteksi object yang ada. Oleh karena itu disebut You Only Look Once (YOLO). Pada penelitian ini, penulis membuat sistem yang masih dalam bentuk pengembangan, sehingga menjalankannya masih menggunakan command prompt. Keywords : Automated Teller Machine (ATM), Kecerdasan Buatan, Pendeteksi Obyek, You Only Look Once (YOLO)  

Performance Comparison of Web Backend And Database: A Case Study Of Node.JS, Golang and MySQL, MongoDB

2019 ◽  
Vol 13 ◽  
Author(s):  
Faried Effendy ◽  
Taufik ◽  
Bramantyo Adhilaksono
Keyword(s):  
Response Time ◽  
Open Source ◽  
Poisson Distribution ◽  
Mobile Application ◽  
Web Applications ◽  
Performance Comparison ◽  
Memory Usage ◽  
Data Traffic ◽  
Cpu Utilization

: Substantial research has been conducted to compare web servers or to compare databases, but very limited research combines the two. Node.js and Golang (Go) are popular platforms for both web and mobile application back-ends, whereas MySQL and Go are among the best open source databases with different characters. Using MySQL and MongoDB as databases, this study aims to compare the performance of Go and Node.js as web applications back-end regarding response time, CPU utilization, and memory usage. To simulate the actual web server workload, the flow of data traffic on the server follows the Poisson distribution. The result shows that the combination of Go and MySQL is superior in CPU utilization and memory usage, while the Node.js and MySQL combination is superior in response time.

Sign in / Sign up

Export Citation Format

Share Document