Cattle Identification and Activity Recognition by Surveillance Camera

2020 ◽  
Vol 2020 (12) ◽  
pp. 174-1-174-6
Author(s):  
Haike Guan ◽  
Naoki Motohashi ◽  
Takashi Maki ◽  
Toshifumi Yamaai
Keyword(s):  
Activity Recognition ◽  
Health Condition ◽  
Cattle Farm ◽  
Surveillance Camera ◽  
Brown Cattle ◽  
Similar Appearance ◽  
Cattle Recognition ◽  
Time Image ◽  
Made In ◽  
Activity Times

In cattle farm, it is important to monitor activity of cattle to know their health condition and prevent accidents. Sensors were used by conventional methods to recognize activity of cattle, but attachment of sensors to the animal may cause stress. Camera was used to recognize activity of cattle, but it is difficult to identify cattle because cattle have similar appearance, especially for black or brown cattle. We propose a new method to identify cattle and recognize their activity by surveillance camera. The cattle are recognized at first by CNN deep learning method. Face and body areas of cattle, sitting and standing state are recognized separately at same time. Image samples of day and night were collected for learning model to recognize cattle for 24-hours. Among the recognized cattle, initial ID numbers are set at first frame of the video to identify the animal. Then particle filter object tracking is used to track the cattle. Combing cattle recognition and tracking results, ID numbers of the cattle are kept to the following frames of the video. Cattle activity is recognized by using multi-frame of the video. In areas of face and body of cattle, active or static activities are recognized. Activity times for the areas are outputted as cattle activity recognition results. Cattle identification and activity recognition experiments were made in a cattle farm by wide angle surveillance cameras. Evaluation results demonstrate effectiveness of our proposed method.

scholarly journals Unsupervised Greenhouse Tomato Plant Segmentation Based on Self-Adaptive Iterative Latent Dirichlet Allocation from Surveillance Camera

Agronomy ◽  
2019 ◽  
Vol 9 (2) ◽  
pp. 91 ◽  
Author(s):  
Qifan Cao ◽  
Lihong Xu
Keyword(s):  
Latent Dirichlet Allocation ◽  
Language Model ◽  
Surveillance Camera ◽  
Greenhouse Tomato ◽  
Wavelet Features ◽  
Greenhouse Plant ◽  
Time Image ◽  
Training Sets ◽  
Self Adaptive ◽  
Dirichlet Allocation

It has long been a great concern in deep learning that we lack massive data for high-precision training sets, especially in the agriculture field. Plants in images captured in greenhouses, from a distance or up close, not only have various morphological structures but also can have a busy background, leading to huge challenges in labeling and segmentation. This article proposes an unsupervised statistical algorithm SAI-LDA (self-adaptive iterative latent Dirichlet allocation) to segment greenhouse tomato images from a field surveillance camera automatically, borrowing the language model LDA. Hierarchical wavelet features with an overlapping grid word document design and a modified density-based method quick-shift are adopted, respectively, according to different kinds of images, which are classified by specific proportions between fruits, leaves, and the background. We also utilize the feature correlation between several layers of the image to make further optimization through three rounds of iteration of LDA, with updated documents to achieve finer segmentation. Experiment results show that our method can automatically label the organs of the greenhouse plant under complex circumstances, fast and precisely, overcoming the difficulty of inferior real-time image quality caused by a surveillance camera, and thus obtain large amounts of valuable training sets.

Animal Activity Recognition From Sensor Data Using Ensemble Learning

2022 ◽  
pp. 165-180
Author(s):  
Derya Birant ◽  
Kadircan Yalniz
Keyword(s):  
Random Forest ◽  
Ensemble Learning ◽  
Activity Recognition ◽  
Health Condition ◽  
Sensor Data ◽  
Psychological State ◽  
Gradient Boosting ◽  
Embedded Devices ◽  
Extreme Gradient Boosting ◽  
Animal Activity

Animal activity recognition is an important task to monitor the behavior of animals to know their health condition and psychological state. To provide a solution for this need, this study is aimed to build an internet of things (IoT) system that predicts the activities of animals based on sensor data obtained from embedded devices attached to animals. This chapter especially considers the problem of prediction of goat activity using three types of sensors: accelerometer, gyroscope, and magnetometer. Five possible goat activities are of interest, including stationary, grazing, walking, trotting, and running. The utility of five ensemble learning methods was investigated, including random forest, extremely randomized trees, bagging trees, gradient boosting, and extreme gradient boosting. The results showed that all these methods achieved good performance (>94%) on the datasets. Therefore, this study can be successfully used by professionals such as farmers, vets, and animal behaviorists where animal tracking may be crucial.

Global Health Prediction Based on Vector Projection Algorithm

2014 ◽  
Vol 556-562 ◽  
pp. 4035-4039
Author(s):  
Kai Guo ◽  
Dan Luo ◽  
Yang Wang
Keyword(s):  
Global Health ◽  
Analytical Hierarchy Process ◽  
Policy Making ◽  
Health Condition ◽  
Projection Algorithm ◽  
Tipping Points ◽  
Local Policy ◽  
Vector Projection ◽  
Hierarchy Process ◽  
Made In

This paper develops a model to provide reasonable predictions on Earth’s health condition.Factors that influencethe health condition of each nodeareanalyzed by Analytical Hierarchy Process and Vector Projection Theory is used to calculate shift matriceswhich reflect the interaction between nodes. Also the earth’s overall health condition is shown in this model.The prediction made in the test fits well with the reality.Finally, we analyze sensitivity of our model and find out critical and tipping points in the network. This information can be used for the policy making. We also use an example to show how the local policy influences on the global health condition.

scholarly journals Matching sheep and beef policies to pasture supply on Northland hill country

1995 ◽  
pp. 207-212
Author(s):  
C.R. Page ◽  
R.D. Thomson ◽  
R.W. Webby
Keyword(s):  
Weight Gain ◽  
Beef Cattle ◽  
Cattle Farm ◽  
Pasture Production ◽  
Hill Country ◽  
The Past ◽  
Group Members ◽  
Full Benefit ◽  
Cattle Farms ◽  
Made In

Farm monitoring on sheep and beef cattle farms in Northland has been in operation for the past 8 years. The emphasis has been on monitoring the performance of sheep and beef cattle farms to provide the data to encourage group members to make decisions based on objective measurements. Monitor groups were initially supported by extension and science personnel with more recent groups being operated on a commercial basis. Key biological indices such as animal numbers, weights, weight gain, meat and wool production and pasture production are monitored. Group members are encouraged to use information from the monitor farm to identify opportunities on their own farms for improvement in production and income. Significant gains have been made in production but it can take 3 to 5 years for the full benefit to be realised. Pasture production information has been v,ital to identify changes in feed supply from year to year during the monitoring programme. Farm monitoring in the future is likely to be the basis on which farmers will be able to. meet year-round supply of product based on specifications of weight, date and carcass attributes. Keywords: beef and cattle, farm monitoring, objective measurement, pasture production, sheep

Epilogue

2014 ◽  
Author(s):  
Michael W. O'Hara ◽  
C. Steven Richards
Keyword(s):  
Psychiatric Disorders ◽  
Interdisciplinary Collaboration ◽  
Chronic Health Condition ◽  
Health Condition ◽  
Comorbid Depression ◽  
Chronic Health ◽  
Close Relationship ◽  
Assessment And Treatment ◽  
Big Picture ◽  
Made In

The authors of the chapters in this volume have covered nearly every feature of depression comorbidity with other psychiatric disorders, chronic health conditions, and disturbed close relationships. Treatment implications are addressed both in chapters on individual disorders as well as comprehensively in separate chapters. This volume concludes with the “big picture” provided by Ronald Kessler and his colleagues. Several themes emerge. Depression comorbidity is pervasive. It touches to one degree or another almost every identifiable psychiatric condition, chronic health condition, and disturbed close relationship. There are numerous potential explanations for this pervasive comorbidity that depend in part on the comorbid disorder. Depression comorbidity is associated with greater disease burden, resistance to treatment, increased primary disease morbidity, and mortality relative to cases in which comorbid depression is not present. Although depression comorbidity is common across psychiatric disorders, it is especially common among the anxiety disorders, raising questions as whether these disorders are really distinct. The assessment and treatment of comorbid disorders is complicated and often requires interdisciplinary collaboration. Although great strides have been made in the study of depression comorbidity, there is much left to be learned, so that we will be able to provide the most effective possible care to our patients who suffer from comorbid depression.

scholarly journals Motion Recording for Surveillance Camera

2010 ◽  
Vol 7 (2) ◽  
pp. 1070-1075
Author(s):  
Baghdad Science Journal
Keyword(s):  
Motion Detection ◽  
Vision System ◽  
Sudden Change ◽  
Proof Of Concept ◽  
False Detection ◽  
Surveillance Camera ◽  
Time Motion ◽  
Web Camera ◽  
Made In ◽  
Operational Computer

In this paper we present an operational computer vision system for real-time motion detection and recording that can be used in surveillance system. The system captures a video of a scene and identifies the frames that contains motion and record them in such a way that only the frames that is important to us is recorded and a report is made in the form of a movie is made and can be displayed. All parts that are captured by the camera are recorded to compare both movies. This serves as both a proof-of- concept and a verification of other existing algorithms for motion detection. Motion frames are detected using frame differencing. The results of the experiments with the system indicate the ability to minimize some of the problems false detection and missed detections (like in a sudden change of light in the scene). The software part is written in Matlab language as an M-file and using the Simulink library, the hardware part we used a Pentium 4 computer with a web camera or a laptop integrated camera.

scholarly journals Psychomotor Development of Children from Multiple Pregnancies. A Psychological Evaluation

1972 ◽  
Vol 22 (S1) ◽  
pp. 135-138
Author(s):  
M. Bogdanowicz
Keyword(s):  
Multiple Pregnancy ◽  
Health Condition ◽  
Individual Development ◽  
Psychomotor Development ◽  
Multiple Pregnancies ◽  
The Central Nervous System ◽  
The One ◽  
The Individual ◽  
Mz Twins ◽  
Made In

Psychological examinations were made in 56 children from quintuplet, quadruplet, and triplet pregnancies. The psychomotor development of these children from multiple pregnancies did not, as a rule, differ much from the one of singletons, although the multiple pregnancy was more inclined to cause lesions of the central nervous system. Out of the 56 children examined, 25 were found to develop properly.It is necessary to examine the development of each child separately, taking into consideration its health condition in the neonatal period and its specific environment which effect the individual development and may be the cause of disturbances, as well as of mental differences not only in children from the same pregnancy but even in MZ twins.

scholarly journals Introducing VTT-ConIot: A Realistic Dataset for Activity Recognition of Construction Workers Using IMU Devices

2021 ◽  
Vol 14 (1) ◽  
pp. 220
Author(s):  
Satu-Marja Mäkelä ◽  
Arttu Lämsä ◽  
Janne S. Keränen ◽  
Jussi Liikka ◽  
Jussi Ronkainen ◽  
...  
Keyword(s):  
Activity Recognition ◽  
Human Activity ◽  
Occupational Safety ◽  
Inertial Sensors ◽  
Wearable Sensors ◽  
Well Being ◽  
Work Conditions ◽  
Human Activity Recognition ◽  
Wearable Sensor ◽  
Made In

Sustainable work aims at improving working conditions to allow workers to effectively extend their working life. In this context, occupational safety and well-being are major concerns, especially in labor-intensive fields, such as construction-related work. Internet of Things and wearable sensors provide for unobtrusive technology that could enhance safety using human activity recognition techniques, and has the potential of improving work conditions and health. However, the research community lacks commonly used standard datasets that provide for realistic and variating activities from multiple users. In this article, our contributions are threefold. First, we present VTT-ConIoT, a new publicly available dataset for the evaluation of HAR from inertial sensors in professional construction settings. The dataset, which contains data from 13 users and 16 different activities, is collected from three different wearable sensor locations.Second, we provide a benchmark baseline for human activity recognition that shows a classification accuracy of up to 89% for a six class setup and up to 78% for a sixteen class more granular one. Finally, we show an analysis of the representativity and usefulness of the dataset by comparing it with data collected in a pilot study made in a real construction environment with real workers.

Sign in / Sign up

Export Citation Format

Share Document