scholarly journals A Convolutional Neural Network-Based Method for Corn Stand Counting in the Field

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 507
Author(s):  
Le Wang ◽  
Lirong Xiang ◽  
Lie Tang ◽  
Huanyu Jiang
Keyword(s):  
Frame Rate ◽  
Flying Height ◽  
Battery Life ◽  
Growth Stages ◽  
Camera Motion ◽  
Long Duration ◽  
Manual Counting ◽  
Detection And Counting ◽  
Plant Image ◽  
Early Seedling

Accurate corn stand count in the field at early season is of great interest to corn breeders and plant geneticists. However, the commonly used manual counting method is time consuming, laborious, and prone to error. Nowadays, unmanned aerial vehicles (UAV) tend to be a popular base for plant-image-collecting platforms. However, detecting corn stands in the field is a challenging task, primarily because of camera motion, leaf fluttering caused by wind, shadows of plants caused by direct sunlight, and the complex soil background. As for the UAV system, there are mainly two limitations for early seedling detection and counting. First, flying height cannot ensure a high resolution for small objects. It is especially difficult to detect early corn seedlings at around one week after planting, because the plants are small and difficult to differentiate from the background. Second, the battery life and payload of UAV systems cannot support long-duration online counting work. In this research project, we developed an automated, robust, and high-throughput method for corn stand counting based on color images extracted from video clips. A pipeline developed based on the YoloV3 network and Kalman filter was used to count corn seedlings online. The results demonstrate that our method is accurate and reliable for stand counting, achieving an accuracy of over 98% at growth stages V2 and V3 (vegetative stages with two and three visible collars) with an average frame rate of 47 frames per second (FPS). This pipeline can also be mounted easily on manned cart, tractor, or field robotic systems for online corn counting.

scholarly journals Allumo: Preprocessing and Calibration Software for Wearable Accelerometers Used in Posture Tracking

Sensors ◽  
2019 ◽  
Vol 20 (1) ◽  
pp. 229 ◽  
Author(s):  
Alexis Fortin-Côté ◽  
Jean-Sébastien Roy ◽  
Laurent Bouyer ◽  
Philip Jackson ◽  
Alexandre Campeau-Lecours
Keyword(s):  
Joint Angle ◽  
Calibration Procedure ◽  
Battery Life ◽  
Inertial Measurement Units ◽  
Ecological Studies ◽  
Ecological Value ◽  
Inertial Measurement ◽  
Long Duration ◽  
Measurement Units ◽  
Wearable Accelerometers

Inertial measurement units have recently shown great potential for the accurate measurement of joint angle movements in replacement of motion capture systems. In the race towards long duration tracking, inertial measurement units increasingly aim to ensure portability and long battery life, allowing improved ecological studies. Their main advantage over laboratory grade equipment is their usability in a wider range of environment for greater ecological value. For accurate and useful measurements, these types of sensors require a robust orientation estimation that remains accurate over long periods of time. To this end, we developed the Allumo software for the preprocessing and calibration of the orientation estimate of triaxial accelerometers. This software has an automatic orientation calibration procedure, an automatic erroneous orientation-estimate detection and useful visualization to help process long and short measurement periods. These automatic procedures are detailed in this paper, and two case studies are presented to showcase the usefulness of the software. The Allumo software is open-source and available online.

scholarly journals Waterlogging tolerance in pigeonpea (Cajanus cajan (L.) Millsp.): genotypic variability and identification of tolerant genotypes

2012 ◽  
Vol 151 (5) ◽  
pp. 659-671 ◽  
Author(s):  
R. SULTANA ◽  
M. I. VALES ◽  
K. B. SAXENA ◽  
A. RATHORE ◽  
S. RAO ◽  
...  
Keyword(s):  
Phenotypic Variation ◽  
Survival Rates ◽  
Growth Stages ◽  
Waterlogging Tolerance ◽  
Breeding Lines ◽  
Legume Crop ◽  
Breeding Programmes ◽  
Early Seedling ◽  
Elite Breeding Lines

SUMMARYPigeonpea is an important legume crop of the semi-arid tropics. In India, pigeonpea is mostly grown in areas prone to waterlogging, resulting in major production losses. It is imperative to identify genotypes that show tolerance at critical crop growth stages to prevent these losses. A selection of 272 diverse pigeonpea accessions was evaluated for seed submergence tolerance for different durations (0, 120, 144, 168 and 192 h) under in vitro conditions in the laboratory. All genotypes exhibited high (0·79–0·98) survival rates for up to 120 h of submergence. After 192 h of submergence, the hybrids as a group exhibited significantly higher survival rates (0·79) than the germplasm (0·71), elite breeding lines (0·68) and commercial varieties (0·58). Ninety-six genotypes representing the phenotypic variation observed during laboratory screening were further evaluated for waterlogging tolerance at the early seedling stage using pots, and survival rates were recorded for 8 days after completion of the stress treatment. Forty-nine of these 96 genotypes, representing the phenotypic variation for waterlogging tolerance, were chosen in order to evaluate their performance under natural field conditions. The following cultivated varieties and hybrids were identified as tolerant after three levels of testing (in vitro, in pots and in the field): ICPH 2431, ICPH 2740, ICPH 2671, ICPH 4187, MAL 9, LRG 30, Maruti, ICPL 20128, ICPL 332, ICPL 20237, ICPL 20238, Asha and MAL 15. These materials can be used as sources of waterlogging tolerance in breeding programmes.

scholarly journals Probability of Low Temperature Stress at Different Growth Stages of Boro Rice

2016 ◽  
Vol 19 (2) ◽  
pp. 19-27 ◽  
Author(s):  
MS Kabir ◽  
M Howlader ◽  
JK Biswas ◽  
MAA Mahbub ◽  
M Nur E Elahi
Keyword(s):  
High Temperature ◽  
Low Temperature ◽  
Short Duration ◽  
Rice Crop ◽  
Growth And Yield ◽  
Maximum Temperature ◽  
Growth Stages ◽  
Growth Duration ◽  
Long Duration ◽  
Boro Rice

CORRECTION: Due to a number of formatting and layout issues, the PDF of this paper was replaced on 10th October 2016.The most sensitive stages of Boro rice against the low temperature are agronomic panicle initiation (API), reduction division (RD) and flowering/anthesis. The critical low temperature is growth stage specific. The time and intensity of the critical low temperature during Boro season has a direct impact on the growth and yield of a crop. Therefore, it is necessary to understand the probability of the critical low temperature with respect to the growth stages to have a good planning for safe harvest. Long term weekly low temperature data have been used to estimate the probability of falling low temperature on those stages and the return period was computed. The growth durations of 1- and 30- November seeded Boro rice crop from 45-day-old seedling of BRRI dhan28 (short duration) and BRRI dhan29 (long duration) are considered to observe the probability. A Boro crop encountering critical low temperature is appeared to suffer from cool injury. The extent of cool injury depends on the nature and duration of low temperature and diurnal change of low (night) and high (day) temperature. The critical low temperature for a rice crop at API, RD and anthesis are 18, 19 and 22°C, respectively. Boro rice is grown between November and May. The low temperature occurs from October to early March. There is, therefore, the probability of low temperature occurrence from the crop establishment to the flowering stage is a great concern. The probability of experiencing stage-wise critical temperature approaches to 100% for early established and short duration crop. However, the late established and long duration crop has the probability little less than the early and short duration crop. In a study it has been observed that short duration BRRI dhan28 having 64.6% sterility to yield 2.5 t ha-1 and BRRI dhan29, 40.8% sterility to yield 6.5 t ha-1. The percentages of corresponding sterility for late established crops were 35.9 and 32.8%. Irrespective of growth duration, the yield is affected a little of the late established crop. Despite low temperature along with the reproductive phase, the late established crop is quite safe due to the parallel high (day) temperature (31-35°C). The high maximum temperature appears to play an important role through the alleviating effect of low temperature. But for early-established particularly short duration variety could not escape the low temperature at some of its sensitive growth stages as the high temperature appears to stay a several degree low (27-29°C) at that time. The low level of high temperature is appeared to drag down the low temperature to aggravate the growth and development of a crop. Therefore, not only the variation of high temperature of the day but also the variation of critical low temperature might have some role in alleviating effect of cool-injury. The periodic return of critical low temperature (10-15°C) during the reproductive stage may occur every year or every alternate year depending on the time across the cropping season and the region as well. Therefore, the critical low temperature, the high temperature during the low temperature period, periodic return of the critical low temperature with respect to growing region and concerned factors should be a consideration for planning a Boro crop.Bangladesh Rice j. 2015, 19(2): 19-27

scholarly journals Effect of Stand Reduction at Different Growth Stages on Yield of Paprika-Type Chile Pepper

Horticulturae ◽  
2020 ◽  
Vol 6 (1) ◽  
pp. 16
Author(s):  
Israel Joukhadar ◽  
Stephanie Walker
Keyword(s):  
Plant Population ◽  
Extreme Weather Events ◽  
Growth Stages ◽  
Phenological Stage ◽  
Weather Events ◽  
Early Seedling ◽  
Direct Seeded ◽  
Four Levels ◽  
Main Effects ◽  
Different Growth Stages

Paprika-type chile (Capsicum annuum L.) crops are susceptible to plant population losses through pest activity, disease, and extreme weather events such as hail storms. This study was conducted to determine the influence of intensity and timing of plant population reductions on the final harvested yield of paprika-type chile so that informed decisions can be made regarding continuing or ending a damaged field. Two trials, one per year, were conducted in southern New Mexico. ‘LB-25’, a standard commercial cultivar, was direct seeded on 29 March 2016 and 4 April 2017. Plants were thinned at three different growth stages; early seedling, first bloom, and peak bloom. Plants were thinned to four levels at each phenological stage; 0% stand reduction (control; ~200,000 plants/ha), 60% stand reduction (~82,000 plants/ha), 70% stand reduction (~60,000 plants/ha), and 80% stand reduction (~41,000 plant/ha). In both years, the main effects of stand reduction had a significant impact on harvested yield, emphasizing the percentage of stand reduction has more of an impact on yield than timing in paprika-type red chile. Consistently, an 80% stand reduction in paprika-type chile significantly reduced fresh red chile yield by 26% to 38%.

TDMA-Based Time Slots Assignment Algorithm

2012 ◽  
Vol 241-244 ◽  
pp. 2445-2453
Author(s):  
Jun Lu ◽  
De Zhi An
Keyword(s):  
Large Scale ◽  
Mac Protocols ◽  
Sensor Nodes ◽  
Battery Life ◽  
Medium Access ◽  
Central Node ◽  
Assignment Algorithm ◽  
Long Duration ◽  
Shared Channel ◽  
To Receive

In this paper we studied timeliness of TDMA-based MAC scheduling mechanisms. TDMA-based MAC protocols require sensor nodes to deliver data individually so as to eliminate collisions in shared channel. This scheduling mechanism can assist sensor nodes in managing energy efficiently since data resending that collisions induced has a significant impact on battery life. But during medium access arbitration, the elected central node has to receive other nodes’ state messages one by one before assigning time slots for each node. While in large-scale sensor networks, the waiting time would be a relatively long duration and result in timeliness decrease in time-sensitive environments. We propose a novel time slots assignment algorithm for TDMA-based MAC protocols that allows sensor nodes to deliver state messages simultaneously to central node for medium access arbitration and present an analysis in which these two approaches are compared in respect to timeliness. The algorithm is evaluated through simulation. Simulation results have confirmed the timeliness of our new algorithm.

Presenting the Snowflake Video Imager (SVI)

2009 ◽  
Vol 26 (2) ◽  
pp. 167-179 ◽  
Author(s):  
Andrew J. Newman ◽  
Paul A. Kucera ◽  
Larry F. Bliven
Keyword(s):  
Imaging System ◽  
Weather Conditions ◽  
Video Camera ◽  
Frame Rate ◽  
Size Distributions ◽  
Long Duration ◽  
New Instrument ◽  
Data Products ◽  
Diverse Data ◽  
Insight Into

Abstract Herein the authors introduce the Snowflake Video Imager (SVI), which is a new instrument for characterizing frozen precipitation. An SVI utilizes a video camera with sufficient frame rate, pixels, and shutter speed to record thousands of snowflake images. The camera housing and lighting produce little airflow distortion, so SVI data are quite representative of natural conditions, which is important for volumetric data products such as snowflake size distributions. Long-duration, unattended operation of an SVI is feasible because datalogging software provides data compression and the hardware can operate for months in harsh winter conditions. Details of SVI hardware and field operation are given. Snowflake size distributions (SSDs) from a storm near Boulder, Colorado, are computed. An SVI is an imaging system, so SVI data can be utilized to compute diverse data products for various applications. In this paper, the authors present visualizations of frozen particles (i.e., snowflake aggregates as well as individual crystals), which provide insight into the weather conditions such as temperature, humidity, and winds.

scholarly journals Robust video content analysis schemes for human action recognition

2021 ◽  
Vol 104 (2) ◽  
pp. 003685042110054
Author(s):  
Cherry A. Aly ◽  
Fazly S. Abas ◽  
Goh H. Ann
Keyword(s):  
Action Recognition ◽  
High Performance ◽  
General Scheme ◽  
Human Action Recognition ◽  
Human Action ◽  
Extraction Methods ◽  
Machine Learning Algorithms ◽  
Frame Rate ◽  
Camera Motion ◽  
Video Content Analysis

Introduction: Action recognition is a challenging time series classification task that has received much attention in the recent past due to its importance in critical applications, such as surveillance, visual behavior study, topic discovery, security, and content retrieval. Objectives: The main objective of the research is to develop a robust and high-performance human action recognition techniques. A combination of local and holistic feature extraction methods used through analyzing the most effective features to extract to reach the objective, followed by using simple and high-performance machine learning algorithms. Methods: This paper presents three robust action recognition techniques based on a series of image analysis methods to detect activities in different scenes. The general scheme architecture consists of shot boundary detection, shot frame rate re-sampling, and compact feature vector extraction. This process is achieved by emphasizing variations and extracting strong patterns in feature vectors before classification. Results: The proposed schemes are tested on datasets with cluttered backgrounds, low- or high-resolution videos, different viewpoints, and different camera motion conditions, namely, the Hollywood-2, KTH, UCF11 (YouTube actions), and Weizmann datasets. The proposed schemes resulted in highly accurate video analysis results compared to those of other works based on four widely used datasets. The First, Second, and Third Schemes provides recognition accuracies of 57.8%, 73.6%, and 52.0% on Hollywood2, 94.5%, 97.0%, and 59.3% on KTH, 94.5%, 95.6%, and 94.2% on UCF11, and 98.9%, 97.8% and 100% on Weizmann. Conclusion: Each of the proposed schemes provides high recognition accuracy compared to other state-of-art methods. Especially, the Second Scheme as it gives excellent comparable results to other benchmarked approaches.

scholarly journals Automatic Detection and Counting of Blood Cells in Smear Images Using RetinaNet

Entropy ◽  
2021 ◽  
Vol 23 (11) ◽  
pp. 1522
Author(s):  
Grzegorz Drałus ◽  
Damian Mazur ◽  
Anna Czmil
Keyword(s):  
Blood Cells ◽  
Complete Blood Count ◽  
White Blood Cells ◽  
Relevant Information ◽  
Disease Diagnosis ◽  
Cell Counting ◽  
Additional Advantage ◽  
Manual Counting ◽  
Detection And Counting ◽  
Deep Learning Network

A complete blood count is one of the significant clinical tests that evaluates overall human health and provides relevant information for disease diagnosis. The conventional strategies of blood cell counting include manual counting as well as counting using the hemocytometer and are tedious and time-consuming tasks. This research-based paper proposes an automatic software-based alternative method to count blood cells accurately using the RetinaNet deep learning network, which is used to recognize and classify objects in microscopic images. After training, the network automatically recognizes and counts red blood cells, white blood cells, and platelets. We tested a model trained on smear images and found that the trained model has generalized capabilities. We assessed the quality of detection and cell counting using performance measures, such as accuracy, sensitivity, precision, and F1-score. Moreover, we studied the dependence of the confidence thresholds and the number of learning epochs on the obtained results of recognition and counting. We compared the performance of the proposed approach with those obtained by other authors who dealt with the subject of cell counting and show that object detection and labeling can be an additional advantage in the task of counting objects.

scholarly journals Rice Ear Counting Based on Image Segmentation and Establishment of a Dataset

Plants ◽  
2021 ◽  
Vol 10 (8) ◽  
pp. 1625
Author(s):  
Hongmin Shao ◽  
Rong Tang ◽  
Yujie Lei ◽  
Jiong Mu ◽  
Yan Guan ◽  
...  
Keyword(s):  
Rice Yield ◽  
Absolute Error ◽  
Single Shot ◽  
Manual Counting ◽  
Detection And Counting ◽  
Enhancement Method ◽  
Computer Vision Technology ◽  
The Mean ◽  
Variable Light ◽  
Counting Model

The real-time detection and counting of rice ears in fields is one of the most important methods for estimating rice yield. The traditional manual counting method has many disadvantages: it is time-consuming, inefficient and subjective. Therefore, the use of computer vision technology can improve the accuracy and efficiency of rice ear counting in the field. The contributions of this article are as follows. (1) This paper establishes a dataset containing 3300 rice ear samples, which represent various complex situations, including variable light and complex backgrounds, overlapping rice and overlapping leaves. The collected images were manually labeled, and a data enhancement method was used to increase the sample size. (2) This paper proposes a method that combines the LC-FCN (localization-based counting fully convolutional neural network) model based on transfer learning with the watershed algorithm for the recognition of dense rice images. The results show that the model is superior to traditional machine learning methods and the single-shot multibox detector (SSD) algorithm for target detection. Moreover, it is currently considered an advanced and innovative rice ear counting model. The mean absolute error (MAE) of the model on the 300-size test set is 2.99. The model can be used to calculate the number of rice ears in the field. In addition, it can provide reliable basic data for rice yield estimation and a rice dataset for research.

Sign in / Sign up

Export Citation Format

Share Document