scholarly journals Low-Cost Image Compressive Sensing with Multiple Measurement Rates for Object Detection

Sensors ◽  
2019 ◽  
Vol 19 (9) ◽  
pp. 2079 ◽  
Author(s):  
Longlong Liao ◽  
Kenli Li ◽  
Canqun Yang ◽  
Jie Liu

When measurement rates grow, most Compressive Sensing (CS) methods suffer from an increase in overheads of transmission and storage of CS measurements, while reconstruction quality degrades appreciably when measurement rates reduce. To solve these problems in real scenarios such as large-scale distributed surveillance systems, we propose a low-cost image CS approach called MRCS for object detection. It predicts key objects using the proposed MYOLO3 detector, and then samples the regions of the key objects as well as other regions using multiple measurement rates to reduce the size of sampled CS measurements. It also stores and transmits half-precision CS measurements to further reduce the required transmission bandwidth and storage space. Comprehensive evaluations demonstrate that MYOLO3 is a smaller and improved object detector for resource-limited hardware devices such as surveillance cameras and aerial drones. They also suggest that MRCS significantly reduces the required transmission bandwidth and storage space by declining the size of CS measurements, e.g., mean Compression Ratios (mCR) achieves 1.43–22.92 on the VOC-pbc dataset. Notably, MRCS further reduces the size of CS measurements by half-precision representations. Subsequently, the required transmission bandwidth and storage space are reduced by one half as compared to the counterparts represented with single-precision floats. Moreover, it also substantially enhances the usability of object detection on reconstructed images with half-precision CS measurements and multiple measurement rates as compared to its counterpart, using a single low measurement rate.

2020 ◽  
Vol 71 (Supplement_2) ◽  
pp. S102-S110 ◽  
Author(s):  
Megan E Carey ◽  
William R MacWright ◽  
Justin Im ◽  
James E Meiring ◽  
Malick M Gibani ◽  
...  

Abstract Building on previous multicountry surveillance studies of typhoid and others salmonelloses such as the Diseases of the Most Impoverished program and the Typhoid Surveillance in Africa Project, several ongoing blood culture surveillance studies are generating important data about incidence, severity, transmission, and clinical features of invasive Salmonella infections in sub-Saharan Africa and South Asia. These studies are also characterizing drug resistance patterns in their respective study sites. Each study answers a different set of research questions and employs slightly different methodologies, and the geographies under surveillance differ in size, population density, physician practices, access to healthcare facilities, and access to microbiologically safe water and improved sanitation. These differences in part reflect the heterogeneity of the epidemiology of invasive salmonellosis globally, and thus enable generation of data that are useful to policymakers in decision-making for the introduction of typhoid conjugate vaccines (TCVs). Moreover, each study is evaluating the large-scale deployment of TCVs, and may ultimately be used to assess post-introduction vaccine impact. The data generated by these studies will also be used to refine global disease burden estimates. It is important to ensure that lessons learned from these studies not only inform vaccination policy, but also are incorporated into sustainable, low-cost, integrated vaccine-preventable disease surveillance systems.


2013 ◽  
Vol 18 (2-3) ◽  
pp. 91-99
Author(s):  
Jaromir Przybylo

Abstract Automated and intelligent video surveillance systems play important role in the modern world. Since the amount of various video streams that must be analyzed grows, such artificial intelligence systems can assist humans in performing tiresome tasks. As a result, the effectiveness of response to a dangerous situations is increasing (detect unexpected movement or unusual behavior that may pose a threat to people, property and infrastructure). Video surveillance systems have to meet several requirements: must be accurate and not produce too many false alarms, moreover it must be able to process the received video stream in real-time to provide a sufficient response time. The work presented here focuses on the selected challenges of scene analysis in video surveillance systems (object detection/tracking, effectiveness of the whole system). The aim of the research is to design a low-budget surveillance system, that can be used for example in a home security monitoring. Such solution can be use not only to surveillance but also to monitor elderly person at home or provide new ways of interacting in human-computer interaction systems.


2018 ◽  
Vol 7 (3.27) ◽  
pp. 252
Author(s):  
Ranjeet V. Powar ◽  
B Arunkumar

Nowadays the volume of digital data generated and used by enterprises is increasing at an enormous rate. The survey says that more than 80% of data that were generated in the last two years are unstructured in nature. Hence storage space requirement for storing this big volume of unstructured data is very high.  It has gained attention to large-scale storage systems. Deduplication is a space efficient method mainly used to solve storage space optimization problem. This paper focuses on the effect of massive volume of unstructured data and review various storage optimization techniques and survey of various storage types. In addition, it elaborates specific challenges with regard to storage optimization using deduplication and technology that handles a huge amount of unstructured data.  


2010 ◽  
Vol 10 (1) ◽  
pp. 80-88
Author(s):  
IGRM Temaja ◽  
G. Suastika ◽  
S.H. Hidayat ◽  
U. Kartosuwondo

Antiserum production and serological assay of Chrysanthemum B Carlavirus (CVB). Virus identification based on spesific reaction between antigen and antibody  in serological assay has been widely applied as a tool for plant virus detection. The aims of this research is  to produce  antiserum of the CVB by  guinea pig immunization using  purified CVB of Cianjur isolate. The antiserum   was used further  for  the  serological test. Serological methods for detection of CVB were I-ELISA, TBIA, western blot and ISEM. The result showed that  guinea pig immunization  using 150 µg of purified virus was able to produce 10.75 ml of antiserum. The antiserum produced had high sensitivity for detection of CVB when examined by I-ELISA and TBIA. Besides its low cost, TBIA allows the samples to be blotted on the nitrocellulose membranes in the field and storage of the membranes for later processing in the laboratory. This feature makes it the metode of  choice for large-scale CVB surveying.


Nanoscale ◽  
2016 ◽  
Vol 8 (21) ◽  
pp. 11291-11305 ◽  
Author(s):  
Manickam Minakshi ◽  
David Mitchell ◽  
Rob Jones ◽  
Feraih Alenazey ◽  
Teeraphat Watcharatharapong ◽  
...  

Electrochemical energy production and storage at large scale and low cost, is a critical bottleneck in renewable energy systems.


Author(s):  
Yijia Yang ◽  
Xiaoning Zhu ◽  
Ali Haghani

The rail–water coordinated operation area in a container terminal is the key place to operate the transshipment of intermodal containers between the rail and the sea—the handling efficiency in which can affect the overall transport turnover efficiency. A complicated operational process for various handling equipment exists in this coordinated operation area and can lead to a large amount of energy consumption and environmental pollution. This study proposes an integrated optimization approach to manage the multiple equipment integrated scheduling and storage space allocation problem in an energy-efficient way. A bi-objective optimization model is proposed to minimize the overall operation time and energy consumption, in which the handling operations of imported and exported intermodal containers are considered simultaneously. A genetic algorithm based heuristic algorithm is developed to solve the problem. Results from computational experiments indicate the feasibility and effectiveness of the proposed model and algorithm, verifying that a near-optimum solution can be obtained for large-scale problems efficiently, which contributes to the improvement of operation services in rail–water intermodal container terminals.


2021 ◽  
Vol 10 (8) ◽  
pp. e40610817515
Author(s):  
Giovani Mansani de Araujo Avila ◽  
Gislaine Gabardo ◽  
Djalma Cesar Clock ◽  
Osmair Silva de Lima Junior

The interest in the use of microorganisms in agricultural practices has increased significantly in recent years, both in the promotion of plant growth and in the biological control of plant pests and diseases. This literature review work aimed to address information on the use of isolation, multiplication, use and storage methodologies for efficient microorganisms (Effective Microorganisms, EM) in agriculture. These microorganisms have important functions for their hosts, as they have symbiotic interactions with them, and are capable of protecting plants from attack by insects, diseases and herbivorous mammals through the production of toxins. The use of EM in agriculture aims to accelerate the natural composition of organic matter and promote the balance of microbial flora contributing to plant development. EMs are potential substitutes for chemical products, and can thus favor the preservation of the environment. They are collected from fertile forest soils through simple and inexpensive methodologies, consisting of a tool with potential to be used both by family farmers and on a small and large scale. They can be used in different ways, the main ones being in soil, plant, water and animals. The use of EM is an accessible and low-cost technique, in addition to being easy to prepare within the property itself, contributing to the sustainability of agricultural systems.


2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Liuzhang Ouyang ◽  
Jun Jiang ◽  
Kang Chen ◽  
Min Zhu ◽  
Zongwen Liu

AbstractAs an environmentally friendly and high-density energy carrier, hydrogen has been recognized as one of the ideal alternatives for fossil fuels. One of the major challenges faced by “hydrogen economy” is the development of efficient, low-cost, safe and selective hydrogen generation from chemical storage materials. In this review, we summarize the recent advances in hydrogen production via hydrolysis and alcoholysis of light-metal-based materials, such as borohydrides, Mg-based and Al-based materials, and the highly efficient regeneration of borohydrides. Unfortunately, most of these hydrolysable materials are still plagued by sluggish kinetics and low hydrogen yield. While a number of strategies including catalysis, alloying, solution modification, and ball milling have been developed to overcome these drawbacks, the high costs required for the “one-pass” utilization of hydrolysis/alcoholysis systems have ultimately made these techniques almost impossible for practical large-scale applications. Therefore, it is imperative to develop low-cost material systems based on abundant resources and effective recycling technologies of spent fuels for efficient transport, production and storage of hydrogen in a fuel cell-based hydrogen economy.


Sign in / Sign up

Export Citation Format

Share Document