Automatic monitoring of activity intensity in a chicken flock using a computer vision-based background image subtraction technique: An experimental infection study with fowl adenovirus
This study assessed the applicability of a background image subtraction technique for automatic monitoring of activity intensity in a chicken flock. Initially, to determine the appropriate camera shooting direction and time of day for activity analysis, two cages housing five and seven chickens were...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375525000553 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823864274848579584 |
|---|---|
| author | Hiroshi Iseki Eri Furukawa Tomoya Shimasaki Shogo Higaki |
| author_facet | Hiroshi Iseki Eri Furukawa Tomoya Shimasaki Shogo Higaki |
| author_sort | Hiroshi Iseki |
| collection | DOAJ |
| description | This study assessed the applicability of a background image subtraction technique for automatic monitoring of activity intensity in a chicken flock. Initially, to determine the appropriate camera shooting direction and time of day for activity analysis, two cages housing five and seven chickens were simultaneously video recorded from top and side perspectives. The foreground (moving object: chicken) was extracted from the videos using background subtraction, and moving pixels were counted in 5-frame-per-second sequences. Analysis of hourly averaged moving pixel ratios (total pixels of the moving object / total pixels of the region of interest) showed that the daytime top-view video was suitable. Subsequently, an experimental infection study using fowl adenovirus was performed, with four cages per infected and non-infected group, and six chickens per cage. Daytime top-view videos from –8 to 8 days post-inoculation (dpi) were analyzed and a daily activity index (average moving pixel ratio during daytime / average moving pixel ratio during daytime from –8 to –5 dpi) was calculated. Correlation analysis between the activity index and visual clinical score revealed a strong positive correlation (Pearson's correlation coefficient = 0.663). This finding indicates the potential of this method for automatic monitoring of activity intensity in a chicken flock. |
| format | Article |
| id | doaj-art-c51456de32ee4e4d992cc8879192ac2d |
| institution | Kabale University |
| issn | 2772-3755 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj-art-c51456de32ee4e4d992cc8879192ac2d2025-02-09T05:01:41ZengElsevierSmart Agricultural Technology2772-37552025-03-0110100821Automatic monitoring of activity intensity in a chicken flock using a computer vision-based background image subtraction technique: An experimental infection study with fowl adenovirusHiroshi Iseki0Eri Furukawa1Tomoya Shimasaki2Shogo Higaki3National Institute of Animal Health, National Agriculture and Food Research Organization, Tsukuba, Ibaraki 305-0856, JapanNational Institute of Animal Health, National Agriculture and Food Research Organization, Tsukuba, Ibaraki 305-0856, JapanInstitute of Livestock and Grassland Science, National Agriculture and Food Research Organization, Tsukuba, Ibaraki 305-0901, JapanNational Institute of Animal Health, National Agriculture and Food Research Organization, Tsukuba, Ibaraki 305-0856, Japan; Department of Animal and Dairy Sciences, University of Wisconsin, Madison, WI 53706, USA; Corresponding author: National Institute of Animal Health, National Agriculture and Food Research Organization, Tsukuba, Ibaraki 305-0856, Japan.This study assessed the applicability of a background image subtraction technique for automatic monitoring of activity intensity in a chicken flock. Initially, to determine the appropriate camera shooting direction and time of day for activity analysis, two cages housing five and seven chickens were simultaneously video recorded from top and side perspectives. The foreground (moving object: chicken) was extracted from the videos using background subtraction, and moving pixels were counted in 5-frame-per-second sequences. Analysis of hourly averaged moving pixel ratios (total pixels of the moving object / total pixels of the region of interest) showed that the daytime top-view video was suitable. Subsequently, an experimental infection study using fowl adenovirus was performed, with four cages per infected and non-infected group, and six chickens per cage. Daytime top-view videos from –8 to 8 days post-inoculation (dpi) were analyzed and a daily activity index (average moving pixel ratio during daytime / average moving pixel ratio during daytime from –8 to –5 dpi) was calculated. Correlation analysis between the activity index and visual clinical score revealed a strong positive correlation (Pearson's correlation coefficient = 0.663). This finding indicates the potential of this method for automatic monitoring of activity intensity in a chicken flock.http://www.sciencedirect.com/science/article/pii/S2772375525000553ActivityChickenComputer visionFlockInfectious disease;Precision livestock farming |
| spellingShingle | Hiroshi Iseki Eri Furukawa Tomoya Shimasaki Shogo Higaki Automatic monitoring of activity intensity in a chicken flock using a computer vision-based background image subtraction technique: An experimental infection study with fowl adenovirus Smart Agricultural Technology Activity Chicken Computer vision Flock Infectious disease;Precision livestock farming |
| title | Automatic monitoring of activity intensity in a chicken flock using a computer vision-based background image subtraction technique: An experimental infection study with fowl adenovirus |
| title_full | Automatic monitoring of activity intensity in a chicken flock using a computer vision-based background image subtraction technique: An experimental infection study with fowl adenovirus |
| title_fullStr | Automatic monitoring of activity intensity in a chicken flock using a computer vision-based background image subtraction technique: An experimental infection study with fowl adenovirus |
| title_full_unstemmed | Automatic monitoring of activity intensity in a chicken flock using a computer vision-based background image subtraction technique: An experimental infection study with fowl adenovirus |
| title_short | Automatic monitoring of activity intensity in a chicken flock using a computer vision-based background image subtraction technique: An experimental infection study with fowl adenovirus |
| title_sort | automatic monitoring of activity intensity in a chicken flock using a computer vision based background image subtraction technique an experimental infection study with fowl adenovirus |
| topic | Activity Chicken Computer vision Flock Infectious disease;Precision livestock farming |
| url | http://www.sciencedirect.com/science/article/pii/S2772375525000553 |
| work_keys_str_mv | AT hiroshiiseki automaticmonitoringofactivityintensityinachickenflockusingacomputervisionbasedbackgroundimagesubtractiontechniqueanexperimentalinfectionstudywithfowladenovirus AT erifurukawa automaticmonitoringofactivityintensityinachickenflockusingacomputervisionbasedbackgroundimagesubtractiontechniqueanexperimentalinfectionstudywithfowladenovirus AT tomoyashimasaki automaticmonitoringofactivityintensityinachickenflockusingacomputervisionbasedbackgroundimagesubtractiontechniqueanexperimentalinfectionstudywithfowladenovirus AT shogohigaki automaticmonitoringofactivityintensityinachickenflockusingacomputervisionbasedbackgroundimagesubtractiontechniqueanexperimentalinfectionstudywithfowladenovirus |