US-20260129301-A1 - CAMERA WINCH CONTROL FOR DYNAMIC MONITORING

US20260129301A1US 20260129301 A1US20260129301 A1US 20260129301A1US-20260129301-A1

Abstract

A method for controlling a sensor subsystem, the method including receiving one or more metrics representing one or more characteristics of livestock, including one or more livestock objects, contained in an enclosure and monitored by one or more sensors coupled to a winch subsystem. The method further includes determining a position to move the one or more sensors based on the metrics and determining an instruction that includes information related to a movement of the one or more sensors. The method further includes sending the instruction to the winch subsystem to change the position of the one or more sensors.

Inventors

Barnaby John James
Tatiana Kichkaylo
Peter Kimball
Christopher Thornton

Assignees

TIDALX AI INC.

Dates

Publication Date: 20260507
Application Date: 20250604

Claims (20)

1 - 20 . (canceled)
21 . A computer-implemented method comprising: obtaining one or more metrics representing a group of animals in an enclosure; determining a position to move one or more sensors that monitor the group of one or more animals in the enclosure based on the one or more metrics representing the group of animals in the enclosure; generating an instruction indicating movement of the one or more sensors based on the determined position; and transmitting the generated instruction to a subsystem to move a position of the one or more sensors that monitor the group of the one or more animals in the enclosure.
22 . The method of claim 21 , wherein generating the instruction indicating movement of the one or more sensors based on the determined position comprises: generating an instruction indicating movement of a winch subsystem that positions the one or more sensors, wherein transmitting the generated instruction to the subsystem to move the position of the one or more sensors that monitor the group of the one or more animals in the enclosure comprises: transmitting the instruction indicating movement of the winch subsystem that positions the one or more sensors.
23 . The method of claim 21 , wherein obtaining the one or more metrics representing the group of animals in the enclosure comprises: receiving sensor data from at least one of a camera, IR sensor, or water quality sensor; and generating, using the sensor data, the one or more metrics representing the group of animals in the enclosure.
24 . The method of claim 21 , wherein determining the position to move the one or more sensors comprises: comparing the obtained metrics and one or more predefined threshold values; and determining the position to move the one or more sensors based on the comparison of the obtained metrics and the one or more predefined threshold values.
25 . The method of claim 21 , wherein generating the instruction indicating movement of the one or more sensors based on the determined position comprises: encoding an instruction indicating movement as a set of coordinates indicating one or more positions within the enclosure.
26 . The method of claim 21 , wherein transmitting the generated instruction to the subsystem to move the position of the one or more sensors that monitor the group of the one or more animals in the enclosure comprises: transmitting the generated instruction using a wired or wireless communication interface to a winch subsystem for execution.
27 . The method of claim 21 , comprising: updating a belief matrix representing a likelihood of an animal presence at one or more locations within the enclosure based on the one or more metrics representing the group of animals in the enclosure.
28 . The method of claim 21 , wherein the subsystem is configured to: move the position of the one or more sensors in at least two axes selected from the group consisting of depth, horizontal position, and angular orientation.
29 . The method of claim 21 , wherein the one or more metrics representing the group of animals in the enclosure include at least one of: a number of individual animal object detections, a median distance to the animals, a median depth offset, or a median animal track angle.
30 . One or more non-transitory computer storage media encoded with computer program instructions that when executed by one or more computers cause the one or more computers to perform operations comprising: obtaining one or more metrics representing a group of animals in an enclosure; determining a position to move one or more sensors that monitor the group of one or more animals in the enclosure based on the one or more metrics representing the group of animals in the enclosure; generating an instruction indicating movement of the one or more sensors based on the determined position; and transmitting the generated instruction to a subsystem to move a position of the one or more sensors that monitor the group of the one or more animals in the enclosure.
31 . The media of claim 30 , wherein generating the instruction indicating movement of the one or more sensors based on the determined position comprises: generating an instruction indicating movement of a winch subsystem that positions the one or more sensors, wherein transmitting the generated instruction to the subsystem to move the position of the one or more sensors that monitor the group of the one or more animals in the enclosure comprises: transmitting the instruction indicating movement of the winch subsystem that positions the one or more sensors.
32 . The media of claim 30 , wherein obtaining the one or more metrics representing the group of animals in the enclosure comprises: receiving sensor data from at least one of a camera, IR sensor, or water quality sensor; and generating, using the sensor data, the one or more metrics representing the group of animals in the enclosure.
33 . The media of claim 30 , wherein determining the position to move the one or more sensors comprises: comparing the obtained metrics and one or more predefined threshold values; and determining the position to move the one or more sensors based on the comparison of the obtained metrics and the one or more predefined threshold values.
34 . The media of claim 30 , wherein generating the instruction indicating movement of the one or more sensors based on the determined position comprises: encoding an instruction indicating movement as a set of coordinates indicating one or more positions within the enclosure.
35 . The media of claim 30 , wherein transmitting the generated instruction to the subsystem to move the position of the one or more sensors that monitor the group of the one or more animals in the enclosure comprises: transmitting the generated instruction using a wired or wireless communication interface to a winch subsystem for execution.
36 . The media of claim 30 , wherein the operations comprise: updating a belief matrix representing a likelihood of an animal presence at one or more locations within the enclosure based on the one or more metrics representing the group of animals in the enclosure.
37 . The media of claim 30 , wherein the subsystem is configured to: move the position of the one or more sensors in at least two axes selected from the group consisting of depth, horizontal position, and angular orientation.
38 . The media of claim 30 , wherein the one or more metrics representing the group of animals in the enclosure include at least one of: a number of individual animal object detections, a median distance to the animals, a median depth offset, or a median animal track angle.
39 . A system comprising: one or more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising: obtaining one or more metrics representing a group of animals in an enclosure; determining a position to move one or more sensors that monitor the group of one or more animals in the enclosure based on the one or more metrics representing the group of animals in the enclosure; generating an instruction indicating movement of the one or more sensors based on the determined position; and transmitting the generated instruction to a subsystem to move a position of the one or more sensors that monitor the group of the one or more animals in the enclosure.

Description

CROSS-REFERENCE TO RELATED APPLICATION This patent application is a continuation of U.S. patent application Ser. No. 18/529,983, filed Dec. 5, 2023 which is a continuation of U.S. patent application Ser. No. 17/319,614 filed on May 13, 2021, now U.S. Pat. No. 11,877,062, which is a continuation of U.S. patent application Ser. No. 16/785,252, filed Feb. 7, 2020, now U.S. Pat. No. 11,089,227, the contents of which are incorporated by reference herein in their entirety. FIELD This specification relates to an automated winch controller for aquaculture systems. BACKGROUND Aquaculture involves the farming of aquatic organisms, such as fish, crustaceans, or aquatic plants. In aquaculture, and in contrast to commercial fishing, freshwater and saltwater fish populations are cultivated in controlled environments. For example, the farming of fish can involve raising fish in tanks, fish ponds, or ocean enclosures. A camera system controlled by a human operator can be used to monitor farmed fish as the fish move throughout their enclosure. When camera systems are manually controlled, human factors, such as the attention span or work schedule of the operator, or the comfort of the human operator in extreme weather conditions, can affect the quality of monitoring. SUMMARY The location of livestock, e.g., fish, in an enclosure can change depending on a number of factors, e.g., the presence of food, the temperature of the water, the level of oxygen in the water, or the amount of light. However, biomass monitoring systems that are controlled by human operators can be limited in a number of ways. In one example, an operator may have to sweep a sensor, e.g., a camera, through the enclosure many times to find and confirm a good position at which to monitor the livestock. In other examples, the quality of the sensor data received from human-controlled camera systems can be affected by the operator's attention to the livestock, or by environmental conditions such as the temperature, or the amount of light, precipitation, or surf that may also impact the ability of the operator to operate the sensor. While the term livestock is used to describe the living contents of the enclosure, generally the enclosure can include any type of aquatic cargo such as commercial fish (e.g., salmon, tuna, cod) or plant matter (e.g., seaweed). To enhance the accuracy of biomass metrics, human operators must also take into account many parameters relating to their monitoring, e.g., the number of fish present in the sensor's range, the distance of the fish from the sensor, what parts of the fish are being monitored, such as the heads or the sides of the fish. Human-controlled biomass monitoring systems may therefore be limited by the ability of the operator to track and synthesize the information provided by the various parameters to determine changes in the sensor position that will result in an ideal viewing position of the sensor. Accordingly, disclosed is a biomass monitoring system that does not suffer from the deficiencies of prior systems, and that includes a biomass metric generation subsystem that can receive sensor data from a sensor subsystem that includes one or more sensors and generate biomass metrics related to the livestock. A sensor position subsystem can use the biomass metrics to determine a position for the sensor subsystem. In one general aspect, a method for controlling a sensor subsystem includes receiving one or more metrics representing one or more characteristics of livestock, including one or more livestock objects, contained in an enclosure and monitored by one or more sensors coupled to a winch subsystem. The method further includes determining a position to move the one or more sensors based on the metrics and determining an instruction that includes information related to a movement of the one or more sensors. The method further includes sending the instruction to the winch subsystem to change the position of the one or more sensors. Implementations may include one or more of the following features. For example, the characteristics of the livestock can include being hungry, sick, hurt, or dead. The one or more metrics can include a number of individual livestock object detections, a number of stereo matched livestock tracks, a median distance to the livestock, a median depth offset of the livestock, a median object track duration of the livestock, or a median livestock track angle. In some implementations, the method includes receiving sensor data from the one or more sensors and generating, using the sensor data, the one or more metrics. In some implementations, the method includes receiving, by the winch subsystem, the instructions and changing, by the winch subsystem, the position of the one or more sensors according to the instructions. In some implementations, the method includes determining an approximate number of livestock objects of the livestock and determining that the approximate number of livestock objects is