System for external fish parasite monitoring in aquaculture
A system for external fish parasite monitoring in aquaculture, the system comprising: —a camera ( 52 ) suitable to be submerged in a sea pen suitable for containing fish, the camera being arranged for capturing images of the fish; and —an electronic image processing system ( 86 ) configured for identifying external fish parasites on the fish by analyzing the captured images, characterized by a camera and lighting rig ( 10 ) having a vertical support member ( 14 ), an upper boom ( 16 ) articulated to a top end of the support member ( 14 ) and carrying an upper lighting array ( 22 ), a lower boom ( 18 ) articulated to a lower end of the support member ( 14 ) and carrying a lower lighting array ( 24 ), and a housing ( 20 ) attached to the support member and carrying the camera ( 52 ), wherein the upper and lower lighting arrays ( 22, 44 ) are configured to illuminate, from above and from below, a target region inside a field of view of the camera ( 52 ).
1. A system for external fish parasites monitoring in aquaculture, the system comprising:
a camera ( 52 ) suitable to be submerged in a sea pen ( 40 ) suitable for containing fish ( 72 , 74 ), the camera being arranged for capturing images of the fish; and
an electronic image processing system ( 86 ) configured for identifying external fish parasites on the fish by analyzing the captured images,
characterized by a camera and lighting rig ( 10 ) having a vertical support member ( 14 ), an upper boom ( 16 ) articulated to a top end of the support member ( 14 ) and carrying an upper lighting array ( 22 ), a lower boom ( 18 ) articulated to a lower end of the support member ( 14 ) and carrying a lower lighting array ( 24 ), and a housing ( 20 ) attached to the support member and carrying the camera ( 52 ), wherein the upper and lower lighting arrays ( 22 , 44 ) are configured to illuminate, from above and from below, a target region inside a field of view of the camera ( 52 ).
2. The system according to claim 1 , wherein the target region that is illuminated by both the upper and the lower lighting array is dimensioned so as to accommodate an entire silhouette of a fish.
3. The system according to claim 1 , wherein the upper lighting array ( 22 ) is configured to emit light with an intensity and/or spectral composition different from that of the light emitted by the lower lighting array ( 24 ).
4. The system according to claim 3 , wherein the upper lighting array ( 22 ) comprises a flash tube unit, and the lower lighting array ( 24 ) comprises an LED lighting unit.
5. The system according to claim 1 , comprising a posture sensing unit ( 56 ) adapted to detect a posture of the camera and lighting rig ( 10 ) relative to the sea pen ( 40 ).
6. The system according to claim 1 , comprising:
a ranging detector ( 54 ) mounted on the housing ( 20 ) and configured for detecting the presence of fish and measuring a distance from the detector to the; and
an electronic control system ( 12 ) arranged to control a focus of the camera ( 52 ) on the basis of the measured distance and to trigger the camera ( 52 ) when a fish has been detected within a predetermined distance range.
7. The system according to claim 6 , wherein the electronic control system ( 12 ) is configured to control the camera ( 52 ) so as to capture a sequence of images in an extended time interval in which the ranging detector ( 54 ) continuously detects the fish within the predetermined distance range.
8. The system according to claim 6 , wherein the ranging detector ( 54 ) comprises a light-based time-of-flight ranging and detection unit having:
LED emit optics ( 58 ) for emitting light; and
receive optics ( 60 ) adapted to receive reflected light and to measure a time of flight the received light.
9. The system according to claim 8 , wherein the emit optics ( 58 ) is configured to emit light in the form of a fan spread over an extended angular range in vertical direction and collimated in horizontal direction.
10. The system according to claim 9 , wherein the receive optics ( 60 ) includes a plurality of detector elements having adjacent fields of view ( 66 ) which collectively form a vertically oriented acceptance fan ( 68 ), the ranging detector being adapted to measure bearing angles (□) under which reflected light is detected by the individual detector elements.
11. The system according to claim 1 , wherein the electronic image processing system ( 78 ) comprises a fish detector ( 84 ) configured to recognize a silhouette of a fish in the captured image, and an external fish parasite detector ( 86 ) configured to detect external fish parasites in a specified region ( 90 - 100 ) within the silhouette of the fish ( 72 ).
12. The system according to claim 11 , wherein the electronic image processing system ( 78 ) comprises at least one neural network constituting the fish detector ( 84 ) and/or the external fish parasite detector ( 86 ).
13. A method for external fish parasites monitoring in aquaculture, characterized by using the system according claim 1 .
14. The method according to claim 13 , wherein the image processing system ( 78 ) is used for detecting fish ( 72 , 74 ) in an image captured by the camera ( 52 ) and for detecting external fish parasites within a silhouette of the detected fish.
15. The method according to claim 14 , wherein the ranging detector ( 54 ) is used for measuring a bearing angle of a detected fish ( 72 ), and the measured bearing angle is used in the machine vision system ( 78 ) for searching for the silhouette of the fish in the captured image.
16. The method according to claim 13 , wherein the target region bounded by a field of view of the camera ( 52 ) and by said predetermined distance range is illuminated from above and below with light of different intensities and/or spectral compositions.
17. The method according to claim 16 , wherein a step of detecting the presence of external fish parasites at a given location on the fish includes distinguishing whether said given location is in a top side region ( 90 ) or a bottom side region ( 92 ) of the fish.
18. The method according to claim 13 , comprising:
distinguishing between at least two different classes of external fish parasites which differ in the difficulty of recognizing the external fish parasites;
calculating quality metrics for each captured image, the quality metrics permitting to identify the classes of external fish parasites for which the quality of the image is sufficient for external fish parasites detection; and
establishing separate detection rates for each class of external fish parasites, each detection rate being based only on images the quality of which, as described by the quality metrics, was sufficient for detecting external fish parasites of that class.
19. A method for external fish parasites monitoring in aquaculture, characterized by using the system according to claim 6 .
20. The method according to claim 14 , comprising:
distinguishing between at least two different classes of external fish parasites which differ in the difficulty of recognizing the external fish parasites;
calculating quality metrics for each captured image, the quality metrics permitting to identify the classes of external fish parasites for which the quality of the image is sufficient for external fish parasites detection; and
establishing separate detection rates for each class of external fish parasites, each detection rate being based only on images the quality of which, as described by the quality metrics, was sufficient for detecting external fish parasites of that class.