Hydroponics System and Method
20210127609 ยท 2021-05-06
Assignee
Inventors
Cpc classification
Y02P60/21
GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
A01G2031/006
HUMAN NECESSITIES
A01G31/06
HUMAN NECESSITIES
International classification
A01G31/06
HUMAN NECESSITIES
Abstract
A hydroponics system that uses image processing techniques to automatically manage nutrients is disclosed. The hydroponics system allows small amounts of nutrients to be added to circulated solution on a frequent basis. Images of plants located in a growing area are processed by a computer processor to determine whether the plants are growing. If the plants are growing, the computer processor causes more nutrients to be added to the system than if plants are not growing.
Claims
1. A hydroponics system comprising: a camera; a controller; a main tank; a main tank pump disposed in the main tank and electrically coupled to the controller; a nutrient reservoir; a nutrient reservoir pump disposed in the nutrient reservoir and electrically coupled to the controller; a nutrient supply tube in communication with the main tank and nutrient reservoir pump; and a CPU electrically coupled to the camera and controller and configured to execute a plurality of computer-readable instructions to perform operations comprising: receiving an image of a growing area from the camera; processing the image to calculate an amount of plant growth; based on the calculated amount of plant growth, calculating an amount of nutrients to add to the main tank; based on the calculated amount of nutrients to be added to the main tank, calculating an appropriate pumping time for pumping nutrients into the main tank; and sending instructions to the controller to cause the nutrient reservoir pump to pump nutrients from the nutrient reservoir into the main tank for the calculated pumping time.
2. The hydroponics system of claim 1, wherein processing the image to calculate an amount of plant growth comprises determining a ratio of colors associated with plant growth to colors not associated with plant growth.
3. The hydroponics system of claim 2, wherein determining a ratio of colors comprises using histogram software to sort image pixels into tonal categories that isolate colors relevant to foliage depicted in the image of the growing area received from the camera.
4. A method for managing nutrients in a hydroponics system, comprising: providing a hydroponics system comprising: a CPU; a camera electrically coupled to the CPU; a controller electrically coupled to the CPU; a main tank; a main tank pump disposed in the main tank and electrically coupled to the controller; a nutrient reservoir; a nutrient reservoir pump disposed in the nutrient reservoir and electrically coupled to the controller; a nutrient supply tube in communication with the main tank and nutrient reservoir pump; one or more processors; capturing an image of a growing area using a camera; transmitting the image to a CPU; processing the image to determining an amount of plant growth; based on the amount of plant growth, determining an amount of nutrients to add to a main tank; based on the amount of nutrients to be added to the main tank, calculating a pumping time for pumping nutrients into the main tank; pumping nutrients from a nutrient reservoir into the main tank for the calculated pumping time.
5. The method of claim 4, wherein processing the image to determining an amount of plant growth comprises determining a ratio of colors associated with plant growth to colors not associated with plant growth.
6. The method of claim 5, wherein determining a ratio of colors comprises using histogram software to sort image pixels into tonal categories that isolate colors relevant to foliage depicted in the image of the growing area received from the camera.
Description
BRIEF DESCRIPTION OF DRAWINGS
[0013] For a more complete understanding of the present disclosure and its advantages, reference is now made to the following description taken in conjunction with the accompanying drawings, in which like reference numerals represent like parts:
[0014]
[0015]
[0016]
[0017]
[0018]
[0019]
[0020]
DETAILED DESCRIPTION OF THE INVENTION
[0021] It should be understood at the outset that, although exemplary embodiments are illustrated in the figures and described below, the principles of the present disclosure may be implemented using any number of techniques, whether currently known or not. The present disclosure should in no way be limited to the exemplary implementations and techniques illustrated in the drawings and described below. Additionally, unless otherwise specifically noted, articles depicted in the drawings are not necessarily drawn to scale.
[0022] As shown in
[0023] As shown in
[0024] As shown in
[0025]
[0026] As shown in
[0027] In an exemplary embodiment, CPU 410 is a Raspberry Pi, nutrient reservoir 160 is a glass container, nutrient reservoir pump 210 is a DC 12V pump, controller 230 is an Arduino, main tank 150 is a food-grade, 27-gallon polypropylene container, main tank pump 310 is a DC 12V pump, camera 110 is a Raspberry Pi-compatible, 5-megapixel camera, growing area 120 comprises a plastic tray with drainage and overflow holes, power source 440 is a 12V DC power supply, and nutrients are MaxiGro from General Hydroponics. The CPU 410 may be connected to the camera 110 with a 6-inch ribbon cable. The camera 110 may be housed in a weatherproof container and suspended approximately 36 inches above the growing area by camera pole 112 so the camera can clearly see the growing area 120.
[0028] In some embodiments, the CPU 410 and controller 230 are on a single circuit board. In another embodiment, the nutrient reservoir and nutrient reservoir pump may be replaced by dry nutrient, such as a powder or pellets. In some embodiments, the growing vessels 130 may be felt or woven bags that hold perlite or other inert media for root growth.
[0029] In one embodiment, growing vessels 130 may be positioned on a growing area 120 above the main water tank. In one embodiment, the water tank pump 310 may be positioned inside the main water tank 150 and may be connected to a water supply tube 330 that adds water to the bottom of growing area 120 when the main tank pump is activated. The growing area 120 may also have drain holes and overflow holes that allow water to drain back into the main tank 150.
[0030]
[0031] At step 540, the image is processed to determine the amount or rate of plant growth. Image processing may include determining the ratio of colors that show plant growth (e.g. greens to purples) to colors not associated with plant growth (e.g. brown). In some embodiments, histogram software may sort image pixels into tonal categories that are then used to isolate colors relevant to the amount of foliage in the picture.
[0032] Python modules such as CV2 and Numpi may be used to calculate ratios. In some embodiments, a set of daily images may be used with object recognition software to determine whether individual plants have experienced leaf growth. In some embodiments, periodic histograms may be used to analyze an increase in plant-related colors over time rather than a static ratio.
[0033] At step 550, based on the amount of plant growth determined through image processing, the CPU 410 may determine an amount of nutrients to add to main tank 150. If a liquid nutrient is used, determining the amount of nutrients to add may involve determining a pumping time appropriate for the amount of nutrients to be added. If a dry nutrient is used, determining the amount of nutrients to be added may involve calculating the number of units (e.g. pellets or spoons) of dry nutrients that should be added.
[0034] At step 560, based on the amount of nutrients determined in step 550, the CPU may determine an appropriate pumping time for pumping nutrients into the main tank. The controller 230 may receive instructions from the CPU 410. The transmitted instructions may specify how much nutrient to add using the nutrient reservoir pump 210 (e.g. by specifying a pumping time).
[0035] At step 570, nutrients are pumped from the nutrient reservoir into the main tank for the pumping time determined in step 560. The controller 230 may activate switch 450a connected to the nutrient reservoir pump 210 to pump nutrients from the nutrient reservoir 160 to the main tank 150. The CPU 410 ensures an appropriate pumping time. The controller 230 may turn off the electronic switch 450a to stop pumping nutrients. The controller 230 may cause solution from the main tank 150 to be added to the growing area 120 and circulate among the plant roots in growing vessels 130.
[0036] In an exemplary embodiment, liquid nutrients (e.g. a solution of one-fourth cup MaxiGro to one half gallon of water) are added to the hydroponics systems based on the ratio of plant colors to non-plant colors. No nutrients are added to the water in the main tank when seeds are initially planted. The camera 110 captures images of the growing area 120 on a daily basis while the seeds are germinating. Pumping occurs once a day after the image has been analyzed by the CPU 410. If the ratio of plant colors (e.g. green) to non-plant colors (e.g. brown) is greater than 0.5, nutrients are pumped for 5 seconds. If the ratio of plant colors to non-plant colors is less than or equal to 0.5 but greater than 0, nutrients are pumped for 2 seconds. If the ratio of plant colors to non-plant colors equals 0, nutrients are not pumped. The described rate of image capture, rate of pumping, pumping times, and color ratios are for exemplary purposes only; other rates, times, and ratios may be used. Pumping time periods may vary by type of nutrients, size of reservoir, concentration of nutrients, etc.
[0037] Image processing to determine the amount or rate of plant growth may include techniques involving artificial intelligence. Software approaches for recognizing plant growth or present state may include convolutional neural networks, recurrent neural networks, k-means neural networks, and histograms. These approaches may be implemented with software such as TensorFlow and or Open Computer Vision. These software tools may be employed to learn what successful horticulture looks like or used to match the present state of plants to existing known parameters of plant mass, structure, and color in a defined growing area. Training of neural networks may be accomplished by first labeling images or videos as either successful or unsuccessful and then processing the images and videos to create a model that can be used with real world data.
[0038] The disclosed hydroponics systems may be used to grow various plants, including lettuce, kale, chard, beets, tomatoes, cucumbers, squash, radishes, turnips, bok choy, mizuna, cabbage, collards, papayas, potatoes, sweet potatoes, turmeric, ginger, chives, garlic, beans, strawberries, watermelon, bitter melon, winter melon, rosemary, basil, oregano, marjoram, thyme, celery, broccoli, cauliflower, Hawaiian chili pepper, sweet peppers, habaneros, and most other produce.
[0039] Modifications, additions, or omissions may be made to the systems, apparatuses, and methods described herein without departing from the scope of the disclosure. For example, the components of the systems and apparatuses may be integrated or separated. Moreover, the operations of the systems and apparatuses disclosed herein may be performed by more, fewer, or other components and the methods described may include more, fewer, or other steps. Additionally, steps may be performed in any suitable order. As used in this document, each refers to each member of a set or each member of a subset of a set.