Towards a Machine Vision-Based Yield Monitor for the Counting and Quality Mapping of Shallots

In comparison to field crops such as cereals, cotton, hay and grain, specialty crops often require more resources, are usually more sensitive to sudden changes in growth conditions and are known to produce higher value products. Providing quality and quantity assessment of specialty crops during harvesting is crucial for securing higher returns and improving management practices. Technical advancements in computer and machine vision have improved the detection, quality assessment and yield estimation processes for various fruit crops, but similar methods capable of exporting a detailed yield map for vegetable crops have yet to be fully developed. A machine vision-based yield monitor was designed to perform size categorization and continuous counting of shallots in-situ during the harvesting process. Coupled with a software developed in Python, the system is composed of a video logger and a global navigation satellite system. Computer vision analysis is performed within the tractor while an RGB camera collects real-time video data of the crops under natural sunlight conditions. Vegetables are first segmented using Watershed segmentation, detected on the conveyor, and then classified by size. The system detected shallots in a subsample of the dataset with a precision of 76%. The software was also evaluated on its ability to classify the shallots into three size categories. The best performance was achieved in the large class (73%), followed by the small class (59%) and medium class (44%). Based on these results, the occasional occlusion of vegetables and inconsistent lighting conditions were the main factors that hindered performance. Although further enhancements are envisioned for the prototype system, its modular and novel design permits the mapping of a selection of other horticultural crops. Moreover, it has the potential to benefit many producers of small vegetable crops by providing them with useful harvest information in real-time.

Download Full-text

Design and Implementation of Scalable Autonomous Centralized Fault-Tolerant Scheme for Satellite System

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.532-533.813 ◽

2012 ◽

Vol 532-533 ◽

pp. 813-817 ◽

Cited By ~ 1

Author(s):

Hao Zhou ◽

Yu Hua Tang ◽

Jing Fei Jiang

Keyword(s):

Real Time ◽

System Reliability ◽

Fault Tolerant ◽

Functional Module ◽

Satellite System ◽

Prototype System ◽

Control Node ◽

System Node ◽

Application Requirements ◽

And Control

Depending on application requirements, the number of processing nodes in parallel satellite system varies. Currently, fault-tolerant design for satellite system often aims to solve specific problems, lacking in universality. This paper presents a scalable autonomous centralized fault-tolerant (SACFt) architecture. Based on it, functional module framework of each system node and autonomous fault-tolerant strategy are designed. This scheme is insensitive to scale change of the processing nodes. It can ensure autonomous fault tolerance and control node parallelism on demand flexibly at the same time, balancing system reliability, scalability, autonomy, real-time feature and many other factors. The validity and real-time feature of the proposed scheme has been verified and evaluated on the prototype system.

Download Full-text

REAL-TIME PHOTOGRAMMETRY AS USED FOR MACHINE VISION APPLICATIONS

The Canadian Surveyor ◽

10.1139/tcs-1987-0015 ◽

1987 ◽

Vol 41 (2) ◽

pp. 201-208

Author(s):

Henrik Haggrén

Keyword(s):

Machine Vision ◽

Real Time ◽

Vision System ◽

Research Centre ◽

Prototype System ◽

Machine Vision System ◽

Technical Research ◽

Industrial Inspection

A photogrammetric machine vision system, called Mapvision, has been developed at the Technical Research Centre of Finland. The paper deals with the principles of real-time photogrammetry as applied to machine vision. There is a brief overview of the present machine vision markets and the commercial systems available. The practical examples presented concern the tentative experiences in applying the Mapvision and its preceding prototype system for industrial inspection and assembly control.

Download Full-text

Machine Vision-Based Intelligent Fire Fighting Robot

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.450.312 ◽

2010 ◽

Vol 450 ◽

pp. 312-315 ◽

Cited By ~ 2

Author(s):

Chao Ching Ho ◽

Ming Chen Chen ◽

Chih Hao Lien

Keyword(s):

Machine Vision ◽

Real Time ◽

Monitoring System ◽

Visual Servoing ◽

Detection System ◽

Detection Algorithm ◽

Video Data ◽

Fire Fighting ◽

Fire Source ◽

Fire Flame

Designing a visual monitoring system to detect fire flame is a complex task because a large amount of video data must be transmitted and processed in real time. In this work, an intelligent fire fighting and detection system is proposed which uses a machine vision to locate the fire flame positions and to control a mobile robot to approach the fire source. This real-time fire monitoring system uses the motion history detection algorithm to register the possible fire position in transmitted video data and then analyze the spectral, spatial and temporal characteristics of the fire regions in the image sequences. The fire detecting and fighting system is based on the visual servoing feedback framework with portable components, off-the-shelf commercial hardware, and embedded programming. Experimental results show that the proposed intelligent fire fighting system is successfully detecting the fire flame and extinguish the fire source reliably.

Download Full-text

A Machine Vision Yield Monitor for Vegetable Crops

10.13031/aim.201701104 ◽

2017 ◽

Keyword(s):

Machine Vision ◽

Vegetable Crops ◽

Yield Monitor

Download Full-text

Performance of Multi-GNSS Real-Time UTC(NTSC) Time and Frequency Transfer Service Using Carrier Phase Observations

Remote Sensing ◽

10.3390/rs13204184 ◽

2021 ◽

Vol 13 (20) ◽

pp. 4184

Author(s):

Pengfei Zhang ◽

Rui Tu ◽

Xiaochun Lu ◽

Lihong Fan ◽

Rui Zhang

Keyword(s):

Real Time ◽

Global Navigation Satellite System ◽

Carrier Phase ◽

Satellite System ◽

National Standard ◽

Prototype System ◽

Navigation Satellite ◽

Frequency Transfer ◽

Global Navigation ◽

Global Navigation Satellite

The technique of carrier phase (CP), based on the global navigation satellite system (GNSS), has proven to be a highly effective spatial tool in the field of time and frequency transfer with sub-nanosecond accuracy. The rapid development of real-time GNSS satellite orbit and clock determinations has enabled GNSS time and frequency transfer using the CP technique to be performed in real-time mode, without any issues associated with latency. In this contribution, we preliminarily built the prototype system of real-time multi-GNSS time and frequency transfer service in National Time Service Center (NTSC) of the Chinese Academy of Sciences (CAS), which undertakes the task to generate, maintains and transmits the national standard of time and frequency UTC(NTSC). The comprehensive assessment of the availability and quality of the service system were provided. First, we assessed the multi-GNSS state space representation (SSR) correction generated in real-time multi-GNSS prototype system by combining broadcast ephemeris through a comparison with the GeoForschungsZentrum (GFZ) final products. The statistical results showed that the orbit precision in three directions was smaller than 6 cm for global positioning system (GPS) and smaller than approximately 10 cm for BeiDou satellite system (BDS). The root mean square (RMS) values of clock differences for GPS were approximately 2.74 and 6.74 ns for the GEO constellation of BDS, 3.24 ns for IGSO, and 1.39 ns for MEO. The addition, the GLObal NAvigation Satellite System (GLONASS) and Galileo satellite navigation system (Galileo) were 4.34 and 1.32 ns, respectively. In order to assess the performance of real-time multi-GNSS time and frequency transfer in a prototype system, the four real-time time transfer links, which used UTC(NTSC) as the reference, were employed to evaluate the performance by comparing with the solution determined using the GFZ final products. The RMS could reach sub-nanosecond accuracy in the two solutions, either in the SSR or GFZ solution, or in GPS, BDS, GLONASS, and Galileo. The frequency stability within 10,000 s was 3.52 × 10−12 for SSR and 3.47 × 10−12 for GFZ and GPS, 3.63 × 10−12 for SSR and 3.53 × 10−12 for GFZ for BDS, 3.57 × 10−12 for SSR and 3.52 × 10−12 for GFZ for GLONASS, and 3.56 × 10−12 for SSR and 3.48 × 10−12 for GFZ for Galileo.

Download Full-text

Adapting Nitrogen Fertilization to Unpredictable Seasonal Conditions with the Least Impact on the Environment

HortTechnology ◽

10.21273/horttech.16.3.0408 ◽

2006 ◽

Vol 16 (3) ◽

pp. 408-412 ◽

Cited By ~ 23

Author(s):

Nicolas Tremblay ◽

Carl Bélec

Keyword(s):

Best Management Practices ◽

Management Practices ◽

Saturation Index ◽

N Fertilization ◽

Soil Conditions ◽

Vegetable Crops ◽

N Budget ◽

Reference Plot ◽

Weather Events ◽

Primary Driver

Weather is the primary driver of both plant growth and soil conditions. As a consequence of unpredictable weather effects on crop requirements, more inputs are being applied as an insurance policy. Best management practices (BMPs) are therefore about using minimal input for maximal return in a context of unpredictable weather events. This paper proposes a set of complementary actions and tools as BMP for nitrogen (N) fertilization of vegetable crops: 1) planning from an N budget, 2) reference plot establishment, and 3) crop sensing prior to in-season N application based on a saturation index related to N requirement.

Download Full-text

Research on Video Encryption and Privacy Protection in Cloud Monitoring System Based on H.264

Recent Patents on Computer Science ◽

10.2174/2213275912666191019141453 ◽

2019 ◽

Vol 12 ◽

Author(s):

Qingtao Wu ◽

Zaihui Cao

Keyword(s):

Real Time ◽

Monitoring System ◽

Video Data ◽

Encryption Algorithm ◽

Management Tool ◽

Video Encryption ◽

Wireless Multimedia ◽

Monitoring Technology ◽

Security Issues ◽

Cloud Monitoring

: Cloud monitoring technology is an important maintenance and management tool for cloud platforms.Cloud monitoring system is a kind of network monitoring service, monitoring technology and monitoring platform based on Internet. At present, the monitoring system is changed from the local monitoring to cloud monitoring, with the flexibility and convenience improved, but also exposed more security issues. Cloud video may be intercepted or changed in the transmission process. Most of the existing encryption algorithms have defects in real-time and security. Aiming at the current security problems of cloud video surveillance, this paper proposes a new video encryption algorithm based on H.264 standard. By using the advanced FMO mechanism, the related macro blocks can be driven into different Slice. The encryption algorithm proposed in this paper can encrypt the whole video content by encrypting the FMO sub images. The method has high real-time performance, and the encryption process can be executed in parallel with the coding process. The algorithm can also be combined with traditional scrambling algorithm, further improve the video encryption effect. The algorithm selects the encrypted part of the video data, which reducing the amount of data to be encrypted. Thus reducing the computational complexity of the encryption system, with faster encryption speed, improve real-time and security, suitable for transfer through mobile multimedia and wireless multimedia network.

Download Full-text

Research on real-time error measurement in curve grinding process based on machine vision

International Technology and Innovation Conference 2006 (ITIC 2006) ◽

10.1049/cp:20060841 ◽

2006 ◽

Author(s):

Y.M. Luo ◽

D. Hu ◽

T.L. Gu

Keyword(s):

Machine Vision ◽

Real Time ◽

Grinding Process ◽

Error Measurement ◽

Time Error

Download Full-text

Low-Cost Embedded System Using Convolutional Neural Networks-Based Spatiotemporal Feature Map for Real-Time Human Action Recognition

Applied Sciences ◽

10.3390/app11114940 ◽

2021 ◽

Vol 11 (11) ◽

pp. 4940

Author(s):

Jinsoo Kim ◽

Jeongho Cho

Keyword(s):

Embedded System ◽

Real Time ◽

Action Recognition ◽

Processing Speed ◽

Recognition Accuracy ◽

Low Cost ◽

Human Action Recognition ◽

Human Action ◽

Video Data ◽

Feature Maps

The field of research related to video data has difficulty in extracting not only spatial but also temporal features and human action recognition (HAR) is a representative field of research that applies convolutional neural network (CNN) to video data. The performance for action recognition has improved, but owing to the complexity of the model, some still limitations to operation in real-time persist. Therefore, a lightweight CNN-based single-stream HAR model that can operate in real-time is proposed. The proposed model extracts spatial feature maps by applying CNN to the images that develop the video and uses the frame change rate of sequential images as time information. Spatial feature maps are weighted-averaged by frame change, transformed into spatiotemporal features, and input into multilayer perceptrons, which have a relatively lower complexity than other HAR models; thus, our method has high utility in a single embedded system connected to CCTV. The results of evaluating action recognition accuracy and data processing speed through challenging action recognition benchmark UCF-101 showed higher action recognition accuracy than the HAR model using long short-term memory with a small amount of video frames and confirmed the real-time operational possibility through fast data processing speed. In addition, the performance of the proposed weighted mean-based HAR model was verified by testing it in Jetson NANO to confirm the possibility of using it in low-cost GPU-based embedded systems.

Download Full-text