Fish measurement station keeping

Patent metadata

Field	Value
Publication number	US-10534967-B2
Application number	US-201815970131-A
Country	US
Kind code	B2
Filing date	May 3, 2018
Priority date	May 3, 2018
Publication date	Jan 14, 2020
Grant date	Jan 14, 2020

Abstract

A fish monitoring system deployed in a particular area to obtain fish images is described. Neural networks and machine-learning techniques may be implemented to periodically train fish monitoring systems and generate monitoring modes to capture high quality images of fish based on the conditions in the determined area. The camera systems may be configured according to the settings, e.g., positions, viewing angles, specified by the monitoring modes when conditions matching the monitoring modes are detected. Each monitoring mode may be associated with one or more fish activities, such as sleeping, eating, swimming alone, and one or more parameters, such as time, location, and fish type.

First claim

What is claimed is:

1. A system comprising:
one or more computing devices and one or more storage devices that store instructions which, when executed by the one or more computing devices, cause the one or more computing devices to perform operations comprising:
receiving data indicative of (I) one or more conditions at one or more locations in a determined area of an underwater fish pen, and (II) one or more parameters for monitoring one or more objects in the determined area of the underwater fish pen;
determining a monitoring mode, from among multiple monitoring modes, for a camera system in the determined area of the underwater fish pen based on the one or more conditions and the one or more parameters;
configuring the camera system according to the determined monitoring mode to align one or more cameras in the camera system with a target profile of the one or more objects; and
obtaining a set of one or more images in response to configuring the camera system according to the determined monitoring mode, the set of one or more images including images of the one or more objects in the determined area of the underwater fish pen.

2. The system of claim 1 , wherein receiving data indicative of the one or more conditions at the one or more locations in the determined area of the underwater fish pen comprises one or more of:
receiving image data from the one or more cameras;
receiving data from a user indicating a swimming pattern or swimming behavior of the one or more objects; and
receiving environmental data indicating environmental conditions in the determined area from one or more sensors that comprise a light sensor, thermometer, salinity sensor, optical sensor, motion sensor, and current sensor.

3. The system of claim 1 , wherein the one or more conditions comprise a movement of an object, an orientation of an object, a direction of current, a strength of the current, a salinity level, a luminosity, a temperature level, a depth level, a pressure level, an oxygen level, and a topology of the determined area.

4. The system of claim 1 , wherein receiving data indicative of the one or more parameters for monitoring the one or more objects in the determined area of the underwater fish pen comprises one or more of:
obtaining data indicative of an activity or behavior in which the one or more objects are engaged in; and
obtaining data indicative of a type of object of interest.

5. The system of claim 4 , wherein the behavior including one or more of sleeping, eating, swimming alone, swimming in a school, swimming in position, and moving according to a particular movement pattern; and
the one or more objects comprise one or more of:
fish and the type of object is a species of fish or an identification of a particular fish; and
parasites and the type of object is a species of parasite or an identification of a particular parasite.

6. The system of claim 1 , wherein determining the monitoring mode for the camera system in the determined area of the underwater fish pen based on the one or more conditions and the one or more parameters comprises:
determining one or more monitoring modes that map to the one or more conditions, the one or more parameters, and the one or more locations;
determining a score for each of the one or more monitoring modes; and
selecting the monitoring mode having the highest score among the scores for the one or more monitoring modes.

7. The system of claim 1 , wherein configuring the camera system according to the determined monitoring mode to align the one or more cameras in the camera system with the target profile of the one or more objects comprises:
controlling the camera system to position the one or more cameras in the camera system (i) at approximately a perpendicular angle to a body of the one or more objects proximate to the one or more cameras, and (ii) to be approximately horizontal to the body of the one or more objects.

8. The system of claim 7 , wherein:
the one or more objects comprise fish;
controlling the camera system to position the one or more cameras in the camera system to be approximately horizontal to the body of the one or more objects comprises:
controlling the one or more cameras to move upward or downward in the determined area of the underwater fish pen until the one or more cameras are approximately parallel to a fish proximate to the one or more cameras, and a line extending from the one or more cameras to the fish being parallel to a top surface of water in the fish pen; and
controlling the one or more cameras to move laterally such that all key points on at least one side of the body of the fish proximate to the one or more cameras are completely visible in a lens of each of the one or more cameras at the same time; and

the target profile of the fish comprises all the key points on at least one side of the body of the fish, the key points correspond to an eye, nostril, gill plate, operculum, auxiliary bone, pectoral fin, lateral line, dorsal fin, adipose fin, pelvic fin, anal fin, and caudal fin of the fish.

9. The system of claim 1 , wherein configuring the camera system comprises:
activating a first set of cameras in the camera system and deactivating a second set of cameras based on the determined monitoring mode.

10. The system of claim 1 , wherein the operations further comprise:
in response to obtaining the set of one or more images:
determining a quality factor of the one or more images;
determining whether the quality factor satisfies a quality threshold;
in response to the quality factor not satisfying the quality threshold:
receiving additional data that comprises a second set of data indicative of (I) one or more conditions at the one or more locations in the determined area of the underwater fish pen, and (II) one or more parameters for monitoring the one or more objects in the determined area of the underwater fish pen;
reconfiguring the camera system based on the additional data; and
obtaining a second set of one or more images of the one or more objects; and

in response to the quality factor satisfying the quality threshold, obtaining a second set of images of the one or more objects without reconfiguring the camera system.

11. A computer-implemented method comprising:
receiving data indicative of (I) one or more conditions at one or more locations in a determined area of an underwater fish pen, and (II) one or more parameters for monitoring one or more objects in the determined area of the underwater fish pen;
determining, by one or more processors, a monitoring mode, from among multiple monitoring modes, for a camera system in the determined area of the underwater fish pen based on the one or more conditions and the one or more parameters;
configuring, by the one or more processors, the camera system according to the determined monitoring mode to align one or more cameras in the camera system with a target profile of the one or more objects; and
obtaining, by the one or more processors, a set of one or more images in response to configuring the camera system according to the determined monitoring mode, the set of one or more images including images of the one or more objects in the determined area of the underwater fish pen.

12. The computer-implemented method of claim 11 , wherein:
receiving the data indicative of the one or more conditions at the one or more locations in the determined area of the underwater fish pen comprises one or more of:
receiving image data from the one or more cameras;
receiving data from a user indicating a swimming pattern or swimming behavior of the one or more objects; and
receiving environmental data indicating environme

Assignees

• X Dev Llc

Inventors

• Atwater Joel Fraser
• James Barnaby John
• Messana Matthew

Classifications

• H04N23/667

  Camera operation mode switching, e.g. between still and video, sport and normal or high- and low-resolution modes · CPC title

• G06T7/20

  Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51) · CPC title

• A01K61/13

  Prevention or treatment of fish diseases · CPC title

• A01K61/90

  Sorting, grading, counting or marking live aquatic animals, e.g. sex determination · CPC title

• A01K61/60

  Floating cultivation devices, e.g. rafts or floating fish-farms · CPC title