High-intensity lighting system and method for using same

Abstract

Described herein is a high-brightness lighting system that includes an illumination array of lights, such as light emitting diodes, configured to illuminate a surface. The illumination array is configured to illuminate the surface with illumination comparable to or multiple times brighter than ambient illumination, such as sunlight. Also described herein is a method of using the high-brightness lighting system to illuminate a surface for applications including imaging, object detection, and object localization. The systems and methods described herein can be applied to a range of industries, including agriculture, farming, construction, and autonomous vehicles.

Description

[Background technology]

[0001] cross reference This application claims the benefit of U.S. Provisional Patent Application No. 63 / 274,686, entitled "HIGH INTENSITY ILLUMINATION SYSTEMS AND METHODS OF USE THEREOF," filed November 2, 2021, which application is incorporated by reference herein in its entirety for all purposes.

[0002] The accuracy of automatic object detection in images is highly dependent on the quality of the images. Furthermore, training systems for automatic object detection in images collected under inconsistent imaging conditions require large amounts of training data to account for the variations in imaging conditions. There is a need for a system that generates consistent imaging conditions for automatic object detection in a variety of irregular environments. Summary of the Invention [Means for solving the problem]

[0003] In various aspects, the present disclosure provides an object targeting system comprising: an illumination array comprising a plurality of light emitters configured to emit light and illuminate an area of ​​interest at an illuminance greater than ambient lighting, the area of ​​interest defining an area on a surface; a detection system comprising a camera configured to image the area of ​​interest, the area of ​​interest including an object to be targeted; an object location module configured to determine an object position based on an image of the object collected by the camera; and an instrument configured to target the object at the object position.

[0004] In some embodiments, when the lighting array is activated, the illumination within the region of interest is consistent over a depth of field range of 8 cm or more. In some embodiments, when the lighting array is activated, the illumination within the region of interest is consistent over the region of interest. In some embodiments, when the lighting array is activated, the illumination within the region of interest is consistent over a depth of field range of at least 0.1 m. 2In some embodiments, the ambient lighting comprises sunlight. In some embodiments, the lighting array has a lumens / m2 of 120,000 or more, 240,000,000 or more, or 360,000 or more. 2 (lux). In some embodiments, the lighting array is configured to generate an illuminance of at least 200,000 lux and at most 700,000 lux.

[0005] In some aspects, when the lighting array is activated, the illuminance in the area of ​​interest changes by no more than 50% from day to night. In some aspects, when the lighting array is activated, the illuminance in the area of ​​interest changes by no more than 20% from day to night. In some aspects, when the lighting array is activated, the illuminance in the area of ​​interest changes by no more than 50% across the area of ​​interest. In some aspects, when the lighting array is activated, the illuminance in the area of ​​interest changes by no more than 20% across the area of ​​interest.

[0006] In some embodiments, the multiple light emitters are arranged in a line, a circle, an ellipse, an irregular pattern, or a combination thereof. In some embodiments, the camera has an exposure time of 1.5 ms or less. In some embodiments, the camera has a resolution of 100 pixels per inch or greater.

[0007] In some embodiments, the object targeting system is coupled to the vehicle, and the vehicle is configured to move relative to the surface. In some embodiments, the detection system is coupled to the vehicle such that the area of ​​interest imaged by the detection system is below the vehicle. In some embodiments, the lighting array is coupled to the vehicle such that the area of ​​interest illuminated by the lighting array is below the vehicle. In some embodiments, the vehicle can move at a speed of 2 km / hour or more relative to the surface, or 1.2 miles / hour or more. In some embodiments, the vehicle can move at a speed of 2 km / hour or more and 8 km / hour or less, or 1.2 miles / hour or more and 5.0 miles / hour or less, relative to the surface.

[0008] In some aspects, the object targeting system further comprises a computer and a strobe circuit module, the computer configured to control the strobe circuit module, the strobe circuit module configured to activate and deactivate the lighting array and synchronize the camera exposure time with the activation state of the lighting array, hi some aspects, the strobe circuit module configured to activate the lighting array when the camera exposure time begins and deactivate the lighting array when the camera exposure time ends.

[0009] In some embodiments, the surface is ground. In some embodiments, the surface is agricultural land. In some embodiments, the object is a plant. In some embodiments, the object is a weed. In some embodiments, the surface is a building site. In some embodiments, the instrument is a laser. In some embodiments, the laser is configured to burn the object. In some embodiments, the instrument is a sprayer. In some embodiments, the sprayer is configured to spray the object. In some embodiments, the instrument is a grabber. In some embodiments, the grabber is configured to move the object. In some embodiments, the light emitter is a light emitting diode (LED).

[0010] In various aspects, the present disclosure provides a method for targeting an object, the method including: (a) activating a lighting array comprising a plurality of light emitters that emit light and illuminate a region of interest defining an area on a surface at an illuminance greater than ambient illumination; (b) collecting an image of the region of interest with a camera for an exposure time corresponding to a time from starting image collection to stopping image collection; (c) terminating image collection; (d) stopping the lighting array; (e) determining a location of the object based on the image; and (f) targeting an instrument at the location of the object.

[0011] In some embodiments, the method provides for a lumens / m2 output of 120,000 or more, 240,000 or more, or 360,000 or more. 2(lux). In some embodiments, the method includes illuminating the area of ​​interest with an illuminance of at least 200,000 lux and no more than 700,000 lux. In some embodiments, the method includes illuminating the area of ​​interest with an illuminance that varies from day to night by no more than 50% or no more than 20%. In some embodiments, the method includes illuminating the area of ​​interest with an illuminance that varies over the area of ​​interest by no more than 50% or no more than 20%. In some embodiments, the method includes the ambient illumination includes sunlight.

[0012] In some aspects, the method further includes repeating steps (a)-(c) with a period corresponding to the camera frame rate. In some aspects, the exposure time is no more than 7% or no more than 15% of the camera frame rate. In some aspects, the exposure time is no more than 2% or no more than 15% of the camera frame rate. In some aspects, the lighting array and camera are coupled to the vehicle such that the region of interest illuminated by the lighting array is located beneath the vehicle.

[0013] In some embodiments, the instrument is coupled to a vehicle. In some embodiments, the vehicle is moving relative to the surface. In some embodiments, the vehicle is moving relative to the surface at a speed of at least 2 km / hr and at most 8 km / hr, or at least 1.2 mph and at most 5.0 mph.

[0014] In some embodiments, the exposure time is 1.5 ms or less. In some embodiments, the exposure time is 500 μs or less. In some embodiments, the image resolution is 100 pixels per inch or greater.

[0015] In some aspects, the method includes performing step (a) and initiating step (b) within 0.1 ms or 10 μs of each other, where step (a) is performed before step (b) is initiated, or where step (b) is initiated before step (a) is performed. In some aspects, the method includes activating the lighting array within 0.1 ms or 10 μs of starting to collect images. In some aspects, the method includes activating the lighting array before starting to collect images. In some aspects, the method includes activating the lighting array after starting to collect images. In some aspects, the method includes performing step (a) simultaneously with the initiation of step (b). In some aspects, the method includes activating the lighting array and starting to collect images simultaneously.

[0016] In some aspects, the method includes performing steps (c) and (d) within 0.1 ms or 10 μs of each other, where step (c) is performed before step (d), or step (d) is performed before step (c). In some aspects, the method includes stopping the illumination array within 0.1 ms or 10 μs of finishing collecting images. In some aspects, the method includes stopping the illumination array before finishing collecting images. In some aspects, the method includes stopping the illumination array after finishing collecting images. In some aspects, the method includes performing steps (c) and (d) simultaneously. In some aspects, the method includes stopping the illumination array and finishing collecting images simultaneously.

[0017] In some aspects, targeting the object with the instrument comprises burning the object with a laser. In some aspects, targeting the object with the instrument comprises spraying the object with a sprayer. In some aspects, targeting the object with the instrument comprises moving the object with a grabber. In some aspects, the object is a weed.

[0018] In various aspects, the present disclosure provides a system for illuminating a region of interest on a surface, the system comprising an illumination array comprising a plurality of light emitters configured to emit light toward the region of interest, the illumination array configured to illuminate the region of interest with an illuminance greater than ambient illumination, the region of interest defining an area on the surface, and the high brightness illumination system providing consistent illumination within a depth of field range of at least 8 cm.

[0019] In some embodiments, the plurality of light emitters has a light output of 120,000 lumens / m 2 (lux) or greater. In some embodiments, the plurality of light emitters generates an illuminance of 240,000 lux or greater. In some embodiments, the plurality of light emitters generates an illuminance of 360,000 lux or greater. In some embodiments, the plurality of light emitters generates an illuminance of 200,000 lux or greater and 700,000 lux or less. In some embodiments, the ambient lighting comprises sunlight.

[0020] In some embodiments, the surface is a ground surface. In some embodiments, the surface is an agricultural field. In some embodiments, the surface is a building site.

[0021] In some embodiments, the illumination is at least 0.1 m 2 In some embodiments, the illumination of the plurality of light emitters is consistent over an area of ​​the surface. In some embodiments, the plurality of light emitters are arranged in a line, a circle, an ellipse, an irregular pattern, or a combination thereof. In some embodiments, the arrangement of the plurality of light emitters produces uniform illumination of the surface. In some embodiments, one or more light emitters of the plurality of light emitters are angled relative to other light emitters of the plurality of light emitters. In some embodiments, the plurality of light emitters include light emitting diodes (LEDs).

[0022] In some embodiments, the illumination at the surface varies by no more than 50% from day to night. In some embodiments, the illumination at the surface varies by no more than 20% from day to night. In some embodiments, the illumination at the surface varies by no more than 50% across the region of interest. In some embodiments, the illumination at the surface varies by no more than 20% across the region of interest.

[0023] In some embodiments, the system further comprises a camera configured to image the region of interest. In some embodiments, the camera images the region of interest with an exposure time of 1.5 ms or less. In some embodiments, the camera images the region of interest with a resolution of 100 pixels per inch or greater.

[0024] In various aspects, the present disclosure provides a system for controlling a lighting array, the system comprising a computer, a strobe circuit module, a lighting array having a plurality of light emitters, and a camera, the computer configured to control the strobe circuit module, the strobe circuit module configured to turn the light emitters on and off and to synchronize an exposure time of the camera with the on / off states of the plurality of light emitters.

[0025] In some aspects, the system further comprises a capacitor, the capacitor configured to charge while the plurality of light emitters are in an off state. In some aspects, the plurality of light emitters are configured to be turned on by discharging the capacitor. In some aspects, the system further comprises a heat sink configured to dissipate heat from the plurality of light emitters. In some aspects, the strobe circuit module is configured to operate the plurality of light emitters at a duty cycle of 15% or less. In some aspects, the strobe circuit module is configured to operate the plurality of light emitters at a duty cycle of 7% or less. In some aspects, the strobe circuit module is configured to operate the plurality of light emitters at a duty cycle of 2% or more and 15% or less. In some aspects, the strobe circuit module is configured to expose the camera while the plurality of light emitters are on. In some aspects, the strobe circuit module is configured to provide a voltage at least twice the recommended voltage at which the plurality of light emitters are designed to operate.

[0026] In some embodiments, the lighting array has a light output of 120,000 lumens / m 2(lux). In some aspects, the lighting array is configured to generate an illuminance of at least 240,000 lux. In some aspects, the lighting array is configured to generate an illuminance of at least 360,000 lux. In some aspects, the lighting array is configured to generate an illuminance of between 200,000 lux and 700,000 lux.

[0027] In some embodiments, the camera is configured to operate with an exposure time of up to 1.5 ms. In some embodiments, the camera is configured to operate with an exposure time of up to 500 μs.

[0028] In various aspects, the present disclosure provides a method of illuminating an area of ​​interest on a surface, the method comprising emitting light from a high brightness illumination system comprising an illumination array having a plurality of light emitters for emitting light, directing the light towards an area of ​​interest defining an area on the surface, and illuminating at least 120,000 lumens / m consistently across the area of ​​interest within a depth of field range of at least 8 cm or at least 3.1 inches. 2 and illuminating the area of ​​interest with an illuminance of at least one luminance (lux).

[0029] In some embodiments, the method comprises: 2 In some embodiments, the method includes illuminating the area of ​​interest with an illuminance that varies by no more than 50% from day to night. In some embodiments, the method includes illuminating the area of ​​interest with an illuminance that varies by no more than 20% from day to night. In some embodiments, the method includes illuminating the area of ​​interest with an illuminance that varies by no more than 50% across the area of ​​interest. In some embodiments, the method includes illuminating the area of ​​interest with an illuminance that varies by no more than 20% across the area of ​​interest.

[0030] In some embodiments, the method further includes turning the plurality of light emitters on and off in an on / off cycle. In some embodiments, the method includes turning the plurality of light emitters on for no more than 15% of the on / off cycle. In some embodiments, the method includes turning the plurality of light emitters on for no more than 7% of the on / off cycle. In some embodiments, the method includes turning the plurality of light emitters on for at least 2% and no more than 15% of the on / off cycle.

[0031] In some embodiments, the method further includes imaging the region of interest with a camera to collect an image. In some embodiments, the exposure time of the camera is synchronized with the on state of the light emitters. In some embodiments, the multiple light emitters are on during the camera exposure. In some embodiments, the exposure time of the camera is 1.5 ms or less. In some embodiments, the exposure time of the camera is 500 μs or less. In some embodiments, the image collected by the camera comprises a resolution of at least 100 pixels per inch. In some embodiments, the image has reduced motion blur compared to an image without illuminating the region of interest with the lighting array.

[0032] In some embodiments, the method further includes identifying and / or locating an object within the image, hi some embodiments, the object is located on, above, or below the surface.

[0033] In some embodiments, the high intensity lighting system is coupled to a vehicle. In some embodiments, the method further includes moving the vehicle relative to the surface. In some embodiments, the vehicle is moving relative to the surface at a speed of 2 km / hr or more and 8 km / hr or less, or 1.2 mph or more and 5.0 mph or less. In some embodiments, the vehicle is moving relative to the surface at a speed of 2 km / hr or more or 1.2 mph or more.

[0034] Incorporation by Reference All publications, patents, and patent applications mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent, or patent application was specifically and individually indicated to be incorporated by reference.

[0035] The novel features of the invention are set forth with particularity in the appended claims. A better understanding of the features and advantages of the present invention will be obtained by reference to the following detailed description that sets forth illustrative embodiments, in which the principles of the invention are utilized, and the accompanying drawings of which: [Brief description of the drawings]

[0036] [Figure 1A] FIG. 1 illustrates a front view of an autonomous weeding vehicle, a detection system, and a lighting array, according to one or more embodiments of the present disclosure. [Figure 1B] 1 illustrates an isometric view of an autonomous weeding vehicle, a detection system, and a lighting array, according to one or more embodiments herein. [Figure 1C] FIG. 1 illustrates a top view of a surface beneath an autonomous weeding vehicle showing the coverage area of ​​a lighting array in accordance with one or more embodiments herein. [Diagram 2] 1 illustrates an example image of a region of interest illuminated using a high brightness illumination system, in accordance with one or more embodiments herein. [Diagram 3] 1 shows an image of a region of interest collected without high intensity illumination. [Figure 4A] 1 shows an example image of an area of ​​interest illuminated at 600,000 lux collected with an exposure time of 0.3 ms while moving at a speed of 2 miles per hour, according to one or more embodiments herein. [Figure 4B] 1 shows simulated motion blur when imaging a region of interest illuminated at 120,000 lux while moving at a speed of 2 mph. [Figure 4C] 1 shows simulated motion blur when imaging a region of interest illuminated at 60,000 lux while moving at a speed of 2 mph. [Figure 5A]1A and 1B illustrate schematic diagrams of a bottom view of a lighting array for a high brightness lighting system, in accordance with one or more embodiments of the present disclosure. [Figure 5B] 1A and 1B illustrate schematic diagrams of an isometric bottom view of a lighting array for a high-brightness lighting system according to one or more embodiments of the present disclosure. [Figure 6A] 1A and 1B illustrate schematic diagrams of a bottom view of a lighting array for a high brightness lighting system, in accordance with one or more embodiments of the present disclosure. [Figure 6B] FIG. 1 illustrates a schematic bottom view of a vehicle with multiple lighting arrays for a high-brightness lighting system configured on an autonomous weed-cutting vehicle, in accordance with one or more embodiments herein. [Figure 7] 1 illustrates a schematic diagram of a system for synchronizing a high-brightness illumination system and a detection system, in accordance with one or more embodiments of the present disclosure. [Figure 8] 1A and 1B illustrate schematic diagrams of a surface illuminated with high intensity lighting, in accordance with one or more embodiments of the present disclosure. [Figure 9] 1 illustrates a schematic of an electrical configuration for powering a high brightness lighting system, according to one or more embodiments of the present disclosure. [Figure 10] 1 illustrates a system for identifying, locating, targeting, and manipulating objects according to one or more embodiments herein. [Figure 11A] 1 illustrates an isometric view of a portion of a detection system with a laser path and a visible light path shown, according to one or more embodiments herein. [Figure 11B] 1 illustrates a top view of a portion of a detection system with a laser path and a visible light path shown, according to one or more embodiments herein. [Figure 12] 1 illustrates a schematic diagram of a method for targeting an object using a high brightness illumination system, according to one or more embodiments herein. [Figure 13A] FIG. 1 is a block diagram illustrating a computing device in accordance with an exemplary embodiment. [Figure 13B] FIG. 1 is a block diagram illustrating a computing device in accordance with an exemplary embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0037] Various exemplary embodiments of the present disclosure are described in detail below. Although specific embodiments are described, it is understood that this description is for illustrative purposes only. Those skilled in the relevant art will recognize that other components and configurations may be used without departing from the spirit and scope of the present disclosure. Therefore, the following description and drawings are illustrative and should not be construed as limiting. Many specific details are described in order to provide a thorough understanding of the present disclosure. However, in certain instances, well-known or conventional details are not described in order to avoid obscuring the description. References to an embodiment or an embodiment in the present disclosure may refer to the same embodiment or any embodiment, and such references refer to at least one of the exemplary embodiments.

[0038] Reference to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with that embodiment is included in at least one embodiment of the present disclosure. The phrase "in one embodiment" appears in various places in this specification not all necessarily referring to the same embodiment, nor are separate or alternative exemplary embodiments mutually exclusive with other exemplary embodiments. Furthermore, various features are described that may be exhibited by some exemplary embodiments and not by other embodiments. Any feature of one example may be combined with or used in conjunction with any other feature of any other example.

[0039] The terms used herein generally have their ordinary meaning in the art, within the context of this disclosure and within the specific context in which each term is used. Alternative terms and synonyms may be used for any one or more of the terms discussed herein, and no special significance should be placed on whether the term is detailed or discussed herein. In some cases, synonyms for a particular term are provided. The description of one or more synonyms does not exclude the use of other synonyms. The use of examples anywhere in this specification, including examples of any term discussed herein, is merely illustrative and is not intended to further limit the scope and meaning of the disclosure or any exemplary term. Similarly, the present disclosure is not limited to the various exemplary embodiments provided herein.

[0040] Although not intended to limit the scope of the present disclosure, examples of instruments, devices, methods and their related results according to exemplary embodiments of the present disclosure are given below. Please note that titles or subtitles may be used in the examples for the convenience of the reader, but do not limit the scope of the present disclosure in any way. Unless otherwise defined, technical and scientific terms used herein have the meanings commonly understood by those skilled in the art to which the present disclosure belongs. In case of conflict, the present document, including definitions, will prevail.

[0041] Additional features and advantages of the present disclosure will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by the practice of the principles disclosed herein. The features and advantages of the present disclosure may be realized and obtained by means of the instruments and combinations particularly pointed out in the appended claims. These and other features of the present disclosure will become more fully apparent from the following description and the appended claims, or may be learned by the practice of the principles as described herein.

[0042] For clarity of explanation, in some cases, the technology may be presented as including individual functional blocks that represent devices, device components, steps or routines in a method implemented in software, or a combination of hardware and software.

[0043] In the figures, some structural or method features may be shown in a particular arrangement and / or order. However, it should be understood that such a particular arrangement and / or order may not be required. Rather, in some embodiments, such features may be arranged in a different manner and / or order than that shown in the exemplary figures. Furthermore, the inclusion of a structural or method feature in a particular figure does not imply that such feature is required in all embodiments, and that in some embodiments it may not be included or may be combined with other features.

[0044] While the concepts of the present disclosure are susceptible to various modifications and alternative forms, specific embodiments thereof have been shown by way of example in the drawings and are herein described in detail, It is to be understood, however, that there is no intention to limit the concepts of the present disclosure to the particular forms disclosed, but on the contrary, the intention is to cover all modifications, equivalents, and alternatives consistent with the scope of the disclosure and the appended claims.

[0045] High brightness lighting system and method The present disclosure provides systems and methods for generating consistent high-intensity illumination across an area of ​​interest on a surface. Such systems and methods may enable the collection of high-quality, high-resolution, and / or short-exposure images of an area of ​​interest, independent of ambient light (e.g., sunlight in an outdoor environment). The collection of consistent high-quality, high-resolution, and / or short-exposure images may be beneficial for many applications, including automated object detection, which relies on image quality and consistency to recognize objects in the images. Automated object detection often uses machine learning software trained on a training image set that includes known objects. In this case, the accuracy of object detection in the images relies on the consistency between the training data and the images, as well as a high level of image clarity and definition. For images collected under highly variable conditions, a large amount of training data may be required to account for these variable conditions. For blurry or low-quality images (e.g., low resolution, overexposed, or underexposed), even a large amount of training may not be able to account for the variability of the images, as object features may not be discernible. Collecting images under consistent high-intensity illumination, such as by use of the systems and methods described herein, significantly reduces the amount of training data required to train object recognition software. In some embodiments, an automated object detection system trained using training images collected under illumination of a high-intensity illumination system may require 10-100 times fewer images to train the system than an automated object detection system trained using training images collected without high-intensity illumination. For example, an automated object detection system trained using training images collected under illumination of a high-intensity illumination system may require about 25-250, about 50-500, or about 75-750 training images, while an automated object detection system trained using training images collected without high-intensity illumination may require about 250-2500, about 500-5000, or about 750-7500 training images. Furthermore, imaging of an area of ​​interest illuminated with high-intensity illumination may be performed with higher resolution and / or shorter exposure times than imaging performed under ambient or low-intensity illumination conditions, since both increasing resolution and decreasing exposure times reduce the amount of light received per pixel.

[0046] Described herein is a high-intensity lighting system for illuminating an area of ​​interest on a surface. Such high-intensity lighting can facilitate imaging of the surface by providing bright, uniform illumination of the area of ​​interest. A high-intensity lighting system with an illumination array may be configured to illuminate the surface with uniform illumination across the area of ​​interest such that a collected image of the area of ​​interest is not overexposed or underexposed in parts of the image due to shadows or irregular illumination. The surface may be an uneven surface such as a soil surface. An example of an image collected without the use of a high-intensity lighting system and having an overexposed area due to glare from the sun is shown in FIG. 3. The image provided in FIG. 3 includes clipped areas where the light level of the area is either below the detection threshold of the camera (underexposed) or saturates the camera (overexposed). The overexposed areas are indicated by shaded arrows. An example of an image of an area of ​​interest 162 including an object 161 illuminated with a high-intensity lighting system as described herein is shown in FIG. 2.

[0047] The high-intensity lighting system of the present disclosure can provide bright, uniform illumination of an area of ​​interest (e.g., an area on a surface under a vehicle) despite changing ambient lighting conditions. The high-intensity lighting system can illuminate the area of ​​interest with an intensity several times brighter than the ambient lighting (e.g., sunlight), thereby preventing the ambient lighting from causing uneven illumination across the area of ​​interest. For example, the high-intensity lighting system can uniformly illuminate the area of ​​interest throughout the day, where the angle and intensity of the sunlight varies. The high-intensity lighting system can provide uniform illumination across the area of ​​interest without the use of a shade shroud or skirt that blocks ambient light from reaching the area of ​​interest.

[0048] A high-intensity lighting system may uniformly illuminate an area of ​​interest (e.g., an area on a surface under a vehicle) such that a collected image of the area of ​​interest (e.g., an image collected by a camera) is not overexposed or underexposed, also referred to as "clipped." In some embodiments, the light levels across the area of ​​interest may be within the dynamic range of the camera used to collect the image of the area of ​​interest. In contrast, a collected image of an area not illuminated with a high-intensity lighting system may include areas that are overexposed (e.g., saturating the camera used to collect the image), underexposed (e.g., below the detection threshold of the camera used to collect the image), or both. For example, a collected image of an area not illuminated with a high-intensity lighting system may be clipped.

[0049] A high-intensity illumination system can facilitate collection of a color image of an area illuminated by the high-intensity illumination system. The color image may be collected using two or more color channels, such as an RGB image collected using red, blue, and green color channels. The area of ​​interest illuminated by the high-intensity illumination system may be illuminated such that the luminance collected in each color channel (e.g., each of the red, green, and blue channels) is within the dynamic range of the image sensor, such that none of the channels are clipped (e.g., overexposed or underexposed). In some embodiments, the luminance collected in each color channel (e.g., each of the red, green, and blue channels) may be within a standard deviation of each other. For example, the average luminance of the red channel may be within a standard deviation of the average luminance of each of the green and blue channels, the average luminance of the blue channel may be within a standard deviation of the average luminance of each of the green and red channels, the average luminance of the green channel may be within a standard deviation of the average luminance of each of the red and blue channels, or a combination thereof.

[0050] Also described herein are methods for illuminating a surface with a high-intensity illumination system and imaging the illuminated surface with high resolution (e.g., at least 100 pixels / inch or at least 200 pixels / inch) and / or short exposure times (e.g., 1.5 ms or less or 300 μs or less). These methods may be used to illuminate and image a surface (e.g., a soil surface) and identify and / or locate objects (e.g., plants or weeds) in the image. In some embodiments, high-intensity illumination systems may be integrated into a vehicle (e.g., an autonomous vehicle) to illuminate areas under, in front of, behind, or around the vehicle. In some embodiments, the high-intensity illumination methods described herein may be used to facilitate identification and / or location of objects in agricultural, farming, or construction environments.

[0051] The high brightness illumination system of the present disclosure may include a plurality of light emitters, such as light emitting diodes (LEDs), arranged in an illumination array. The light emitters may be configured to emit light toward a surface and illuminate an area of ​​the surface (e.g., an area of ​​interest on the surface). The light emitters may provide uniform illumination across the area over a depth of field range of at least 5 cm, at least 8 cm, at least 12 cm, or at least 12.7 cm. The illumination may be at least 0.1 m. 2 , at least 0.15m 2 , at least 0.2m 2 , or at least 0.25 m 2 In some embodiments, the brightness of the illumination may vary by no more than 5%, no more than 10%, no more than 20%, no more than 30%, no more than 40%, or no more than 50% over the area of ​​the surface.

[0052] The high-intensity lighting system may be configured to illuminate the surface with an illuminance comparable to or brighter than ambient lighting conditions (e.g., the sun, indoor lighting, or outdoor lighting). The illuminance may be two, three, four, or five times brighter than ambient lighting conditions. For example, under daylight conditions where most ambient light is sunlight, the high-intensity lighting may provide consistent illumination of an area of ​​the surface (e.g., the ground) even as the sun changes position relative to the surface throughout the day. In some embodiments, the high-intensity lighting system may illuminate an area of ​​the surface with illumination comparable to that provided by the sun on a sunny day. In some embodiments, the high-intensity lighting system may illuminate an area of ​​the surface with illumination that is two, three, four, five, six, eight, or ten times brighter than that provided by the sun on a sunny day. In some embodiments, the high-intensity lighting system may provide at least 120,000 lumens / m 2 (lux), at least 240,000 lux, at least 360,000 lux, at least 600,000 lux, 800,000 lux, 1000,000 lux, or 1200,000 lux. In some embodiments, the high brightness lighting system can illuminate an area of ​​the surface with an illuminance of 200,000 lux to 700,000 lux, 240,000 lux to 800,000 lux, 300,000 lux to 1,000,000 lux, or 400,000 lux to 1,200,000 lux.

[0053] High intensity lighting that is comparable to or brighter than ambient lighting conditions can enable imaging at all times of the day and night without variation due to the presence or angle of sunlight. For example, a high intensity lighting system can provide uniform illumination without glare or shadows over an area of ​​a surface, even when the sun hits the surface at a low angle. For example, illumination can vary by 20% or less, 30% or less, 40% or less, or 50% or less from day to night.

[0054] In some embodiments, the high-intensity lighting system may be located on or part of an apparatus such as a vehicle. An example of a vehicle 100 with a high-intensity lighting system including a lighting array 150 is shown in FIG. 1A, FIG. 1B, and FIG. 1C. The lighting array may include one or more light emitters 151, such as light-emitting diodes (LEDs), configured to emit light 152 toward a surface 160. As shown in FIG. 1A, FIG. 1B, and FIG. 1C, the lighting array 150 may be located on the underside of the vehicle 100 such that the light 152 emitted from the lighting array illuminates an area of ​​interest 162 on the surface below the vehicle. The vehicle may be capable of moving along the surface 160 using one or more wheels 110. The area of ​​interest 162 may include an object 161 to be targeted by the detection system 101. The surface may be a ground surface, for example, in an agricultural or construction environment. For example, the agricultural land may be a crop field or a greenhouse. In some embodiments, the vehicle may further include a detection system 101 comprising a camera for imaging an area of ​​the surface illuminated by the high-intensity lighting system. For example, an autonomous vehicle configured to image, detect, identify, locate, and / or remove weeds within a crop field may be equipped with a high intensity lighting system for imaging, detecting, identifying, and / or locating the weeds.

[0055] Lighting Array The high brightness lighting systems described herein may include one or more lighting arrays including an array of light emitters configured to uniformly illuminate a surface. Examples of lighting arrays 150 including one or more light emitters 151, such as LEDs, are shown in Figures 5A, 5B, 6A, and 6B. Figure 6B further illustrates multiple lighting arrays 150 arranged on a vehicle 100. Figure 5A illustrates a bottom view of the lighting array 150, and Figure 1B illustrates an isometric bottom view of the lighting array as viewed, for example, from the underside of the vehicle 100. Figure 6A illustrates a bottom view of different LED configurations of the lighting array 150. Figure 6B illustrates a bottom view of a vehicle 100 with multiple lighting arrays 150 illuminating a surface below the vehicle. The lighting array may further include a heat sink 155 to dissipate heat generated by operating the light emitters 151 and power levels higher than the manufacturer's recommended voltage or higher than the safety rated voltage. In some embodiments, the light emitters 151 of the illumination array 150 may be arranged to define a closed region, such as a rectangular region, as shown in FIGS. 5A and 6A. In some embodiments, the light emitters 151 of the illumination array 150 may be arranged to define other closed regions, such as circular, elliptical, polygonal, or other shaped regions. The light emitters 151 of the illumination array 150 may be arranged to provide uniform illumination over a region of interest (e.g., a region imaged by a camera, such as region 162 in FIG. 1C), such that the sum of the illumination from the multiple light emitters 151 of the illumination array 150 is uniform over the region of interest, as shown in FIG. 8. The light emitters 151 of the illumination array 150 may be surrounded by or disposed near a reflector 157 such that the portion of the light 152 emitted by the light emitters that does not reach the surface is reflected toward the surface 160. In some embodiments, the reflector 157 may be configured to increase the amount of light 152 from the emitter 151 that reaches the surface 160, to spread the light 152 across the surface 160 so that the light illuminates the surface more evenly, or a combination thereof. The reflector 157 may have a variety of shapes, including parabolic, hemispherical, elliptical, conical, cylindrical, curved, or segments or combinations thereof.

[0056] The multiple light emitters 151 of the lighting array may be arranged to generate uniform illumination 165 across an area of ​​the surface 160 (e.g., area 162 in FIG. 1C ). For example, a first light emitter 151(a) may emit a first light 152(a) to illuminate the surface 160 with a first illumination 165(a), and a second light emitter 151(b) may emit a second light 152(b) to illuminate the surface 160 with a second illumination 165(b), such that the overall illumination 165 is uniform across the area of ​​the surface 160. In some embodiments, the arrangement of the light emitters 151 may be determined using computer modeling or empirical testing. A computer simulation to determine the placement of the light emitters can identify a placement of light emitters that produces uniform illumination across the region of interest while considering parameters including geometric constraints on the placement of light emitters with respect to the illumination array 150, the distribution of light from the light emitters, the presence and / or type of reflectors, the distance of the illumination array from the surface, the size and / or shape of the region of interest, and combinations thereof. In some embodiments, parameters that can be varied include the position, number, and / or angle of the light emitters, the presence and / or type of reflectors, the brightness of the light emitters, or combinations thereof. The illumination can be the sum of the illumination from the individual light emitters, as shown in FIG. 8. In some embodiments, the computer simulation can place the light emitters 151 to minimize brightness variations across the region of interest of the surface 160. In some embodiments, the light emitter configuration can include linear, circular, rectangular, or irregular placement of light emitters, or combinations thereof. In some embodiments, the placement of the light emitters can be constrained by the size or shape of the device (e.g., vehicle) on which the array is placed. In some embodiments, the placement of the light emitters can be constrained by the location of additional components of the device such that the light emitters do not interfere with the additional components.

[0057] Control System The high brightness lighting system described herein may be controlled by a control system. The control system may control power to the light emitters (e.g., LEDs) of the lighting array and synchronize the on / off state of the LEDs to the camera shutter or exposure. An example of a control system 700 is shown in FIG. 7. The control system 700 may include a computer 701 configured to control a strobe circuit system 710 including a strobe control printed circuit board (PCB) 702. The strobe PCB may provide a strobe signal (e.g., a pulsed voltage) to the lighting array 703 (e.g., an LED array). The strobe control PCB 702 may further provide a camera trigger signal to one or more cameras 704. The one or more cameras may be part of the detection system 101. Optionally, the control system may further include a strobe driver PCB 705 including one or more capacitors 706 connected to the strobe control PCB 702 and the lighting array 703. The PCB capacitor 706 can store charge while the light emitters of the lighting array 150 are in an off state and can be discharged to turn the light emitters on. Because providing high wattage power pulses to the light emitters of the lighting array 150 to turn them on and off can overtax the power generation system, the inclusion of the capacitor 706 can allow for pulsed power while providing a more uniform load to the power generation system. For example, the capacitor 706 can provide pulsed power to the light emitters of the lighting array 150 while the power generation provides sustained power by charging a capacitor during the time the light emitters are off and discharging the capacitor to turn the light emitters on. The inclusion of a strobe driver PCB can reduce the peak power output of the power generation system compared to a system that does not include a strobe driver PCB.

[0058] An exemplary circuit configuration for controlling the lighting array 150 is shown in Figure 9. A power supply unit (PSU) 720 may provide power to a strobe driver PCB 705. A strobe signal 702 may control the charging and discharging of a capacitor in the strobe driver PCB 705, which may provide power to the light emitters 151 when discharging. Individual lighting modules 750 may be chained together to form the lighting array 150.

[0059] A control system, such as the control system 700 shown in FIG. 7, may be configured to provide a voltage to a lighting array sufficient to power the light emitters of the lighting array to illuminate a surface with an illuminance comparable to or brighter than sunlight (e.g., an illuminance of at least 120,000 lux, at least 240,000 lux, at least 400,000 lux, or at least 600,000 lux). The voltage provided to the light emitters by the strobe PCB may be higher than the manufacturer's recommended voltage or may be higher than the safety rated voltage of the light emitters. In some embodiments, the voltage provided to the light emitters may be at least 1.2 times, at least 1.5 times, or at least 2 times the voltage at which the light emitters are designed to operate.

[0060] To compensate for the high voltage, the light emitters may be operated at a low duty cycle. Operating at a low duty cycle can reduce overheating caused by high voltage and / or extend the life of the light emitters that may otherwise be shortened by high voltage. In some embodiments, the light emitters may be operated at a duty cycle of 20% or less, 15% or less, 10% or less, 7% or less, or between 2% and 15%. For example, a lighting array receiving twice the recommended voltage may be operated at a duty cycle of 10% or less. In some embodiments, the lighting array may further comprise a heat sink to dissipate excess heat and extend the life of the light emitters.

[0061] The duty cycle of the lighting array may be synchronized with the frame rate, shutter trigger, or exposure time of the camera. The camera may be configured to image the area illuminated by the lighting array. The strobe PCB may synchronize the lighting array with the camera such that the lighting array is on while the camera is collecting images (e.g., while the camera shutter is open or while the camera is exposing the sensor chip). The camera may be operated at a fast frame rate (e.g., exposure time of 1.5 ms or less or 300 μs or less). The strobe PCB may cycle the lighting array on and off to create a strobe effect synchronized with the camera frame rate and / or exposure time.

[0062] Object targeting system and method The high-intensity lighting system of the present disclosure may be part of an object targeting system, such as a weeding system. A weeding system including a high-intensity lighting system may be configured to autonomously locate, target, and weed in an agricultural environment (e.g., a crop field or a greenhouse). In some embodiments, the high-intensity lighting system may improve the accuracy of the weeding system, increase the speed of weed detection by the weeding system, increase the speed at which the weeding system can move, or a combination thereof. A weeding system including a high-intensity lighting system of the present disclosure may be able to detect weeds in images collected with higher resolution and / or shorter exposure times than a weeding system that does not include a high-intensity lighting system (e.g., a weeding system operating under ambient lighting conditions).

[0063] In some embodiments, a detection system of the present disclosure, including a prediction system and a targeting system, can be configured to identify and target objects using a point-to-point targeting method. The prediction system can include a prediction sensor configured to image a region of interest, and the targeting system can include a targeting sensor configured to image a portion of the region of interest. The imaging can include collecting a representation (e.g., an image) of the region of interest or a portion of the region of interest.

[0064] FIG. 10 illustrates a schematic of a detection system 101 that may be used with a high-intensity illumination system to locate and precisely target an object of interest 161. In some embodiments, the detection system may comprise an optical configuration as illustrated in FIG. 11A and FIG. 11B as described herein. As illustrated in FIG. 10, the detection system 101 may be a multi-camera system including a prediction module 1010 and a targeting module 1050. The detection system 101 may use a first sensor, such as a prediction sensor 1020, to image an area of ​​interest, such as a predicted area of ​​interest 1091. The predicted area of ​​interest 1091 may be an area of ​​a surface 160, such as the ground, a floor, or a farm field. The image may be a visible light image, an infrared image, an ultraviolet image, a light detection and ranging (LIDAR) image, an x-ray image, or any other electromagnetic image. The predictive sensor 1020 may be a camera, such as a charge-coupled device (CCD) camera or a complementary metal-oxide semiconductor (CMOS) camera, a LIDAR detector, an infrared sensor, an ultraviolet sensor, an x-ray detector, or any other sensor capable of detecting electromagnetic waves.

[0065] The object identification module 1030 can receive images from the predictive sensor 1020. The predictive module 1010 can use the object identification module 1030 to determine the presence or absence of an object of interest 161 in an image of a region of interest, such as predicted region of interest 1091, collected by the predictive sensor 1020. The object identification module 1030 can identify an object of interest in an image and can distinguish the object of interest from other objects in the image. In some embodiments, the object identification module 1030 includes a discriminative machine learning model trained to identify the object of interest based on features extracted from the labeled image used to train the discriminative machine learning model. The machine learning model can be a deep learning model, such as a deep learning neural network. In some embodiments, the object identification module 1030 can implement heuristic models, thresholding, or classical detection algorithms to identify the object. In some embodiments, the object identification module uses spectroscopic data to identify the object.

[0066] The object identification module may be configured to identify plants and distinguish between different plants, such as crops and weeds, for example using a machine learning model. In some embodiments, the machine learning model may be a deep learning model, such as a deep learning neural network. In some embodiments, the object identification module may utilize a discriminative machine learning model, such as a convolutional neural network. The discriminative machine learning model may be trained with many images of surfaces with and without objects of interest. For example, the machine learning model may be trained with images of fields with weeds and images of fields without weeds. Once trained, the machine learning model may be configured to identify regions in the image that contain the objects of interest. The regions may be defined by polygons, e.g., rectangles. In some embodiments, the regions are bounding boxes. In some embodiments, the regions are polygonal masks that cover the identified regions. In some embodiments, the discriminative machine learning model may be trained to determine the location of the object of interest, e.g., pixel locations in a predicted image.

[0067] The location of the identified object may be communicated to the object location module 1040. The object location module 1040 may transmit the location of the object 161 to the target module 1050. In some embodiments, the detection system may not include a prediction module 1010, and the location of the object 161 may be determined directly from images collected by the target sensor. In some embodiments, the target module 1050 is one of multiple target modules, and the target module 1050 may be selected based on the availability of the target module or the proximity of the target module to the object location.

[0068] The target control module 1055 of the target module 1050 can control the position, orientation, or direction of the target sensor 1060. In some embodiments, the target control module 1055 can control the position, orientation, or direction of the target sensor 1060 by moving an actuator that adjusts the position or orientation of the target sensor 1060. In some embodiments, the target control module 1055 can control the position, orientation, or direction of the target sensor 1060 by moving an actuator that adjusts the position or orientation of a reflective surface that directs electromagnetic waves to or from the target sensor 1060.

[0069] The target sensor 1060 may have its position, orientation, or direction adjusted by the target control module 1055 to face toward the object location and may collect additional images of the region of interest, such as the target region of interest 1093, including the object of interest 161. The target region of interest 1093 may cover a portion of the predicted region of interest 1091 imaged by the predictive sensor 1020. The additional images may be used to confirm or update the location of the object of interest 161. Optionally, the target control module 1055 may adjust the position, orientation, or direction of the instrument 1080 based on the location of the object 161 in the additional images collected by the target sensor. In some embodiments, the target control module 1055 may adjust the position, orientation, or direction of the instrument 1080 by moving an actuator that adjusts the position or orientation of the instrument 1080. In some embodiments, the target module may activate or deactivate selected instruments in the array of instruments so that the object is selectively targeted.

[0070] The instrument 1080 can perform an action on the object 161 by directing the instrument toward the object location. For example, the instrument 1080 can be a laser that emits laser light toward the object 161. In another example, the instrument 1080 can be a gripping tool that grips the object 161. In another example, the instrument 1080 can be a spraying tool that sprays a fluid on the object 161. In some embodiments, the instrument 1080 can be a planting tool that plants a plant at the identified location. In some embodiments, the instrument 1080 can be a harvesting tool that harvests the object 161. In some embodiments, the instrument 1080 can be a pollination tool that pollinates the object 161. In some embodiments, directing the instrument toward the object location can include activating or deactivating a selected instrument in an array of instruments such that the object is selectively targeted.

[0071] The detection system of the object targeting system, including the high-intensity illumination system, may be configured to locate and target an object of interest. In some embodiments, the detection system may be used to target an object of interest identified in an image or representation collected by a sensor, such as a camera. The location of the object may be determined based on the image, and the object may be targeted at the determined location. Targeting the object may include precisely locating the object using a targeting sensor and targeting the object with an instrument. For example, the detection system may include a laser optical system that directs laser illumination toward the target object at a location determined by the object detection system.

[0072] The object detection system may be configured to direct a beam, e.g., a light beam, to a target location on the surface, such as the location of the object of interest. An exemplary object targeting system including a detection system is described with reference to Figures 11A and 11B. In the illustrated embodiment, the instrument is a laser. However, other instruments are within the scope of the present disclosure, including, but not limited to, a gripping instrument, a spraying instrument, a planting instrument, a harvesting instrument, a pollinating instrument, a marking instrument, a spraying instrument, or a depositing instrument. In some embodiments, the instrument may include an array of instruments that can be selectively activated or deactivated to target the location of the object of interest. For example, the instrument may include an array of sprayers, where each sprayer of the array is activated or deactivated depending on the location of the object of interest, such that the location of the object of interest is selectively sprayed.

[0073] 11A shows an isometric view of an embodiment of a detection system 101 disclosed herein. An emitter 1101, such as a laser, is configured to direct a beam along an optical path, e.g., laser path 1102. In some embodiments, the beam comprises electromagnetic radiation, e.g., light, radio waves, microwaves, or x-rays. In some embodiments, the light is visible light, infrared light, or ultraviolet light. The beam may be coherent. In one embodiment, the emitter is a laser, such as an infrared laser.

[0074] One or more optical elements may be disposed in the path of the beam. The optical elements may include one or more of a beam combiner 1103, a first reflective element 1105, and a second reflective element 1106. These elements may be arranged in the following order in the direction of the beam path: beam combiner 1103, then first reflective element 1105, then second reflective element 1106.

[0075] In another example, the first reflective element 1105 or the second reflective element 1106, or both, may be arranged in the beam path direction before the beam combiner 1103. In another example, the optical elements may be arranged in the beam path direction in the order of the beam combiner 1103 and then the first reflective element 1105. In another example, the first reflective element 1105 or the second reflective element 1106, or both, may be arranged in the beam path direction before the beam combiner 1103. Any number of additional reflective elements may be arranged in the beam path. The beam may pass through a laser escape window 1107. The laser escape window 1107 may be transparent and may protect other optical elements from dust.

[0076] The beam combiner 1103 may be referred to as a beam combining element. In some embodiments, the beam combiner 1103 may be a zinc selenide (ZnSe), zinc sulfide (ZnS), or germanium (Ge) beam combiner. For example, the beam combiner 1103 may be configured to transmit infrared light and reflect visible light. In some embodiments, the beam combiner 1103 may be dichroic. In some embodiments, the beam combiner 1103 may be configured to pass electromagnetic radiation having a wavelength longer than a cutoff wavelength and reflect electromagnetic radiation having a wavelength shorter than a cutoff wavelength. In some embodiments, the beam combiner may be configured to pass electromagnetic radiation having a wavelength shorter than a cutoff wavelength and reflect electromagnetic radiation having a wavelength longer than a cutoff wavelength. In some embodiments, the beam combiner may be a polarizing beam splitter, a long pass filter, a short pass filter, or a band pass filter.

[0077] The optical control system of the present disclosure may further include a lens disposed in the optical path. In some embodiments, the lens may be a focusing lens disposed to focus the beam, the scattered light, or both. For example, a focusing lens may be disposed in the visible optical path to focus the scattered light to the target camera. In some embodiments, the lens may be a defocusing lens disposed to defocus the beam, the scattered light, or both. In some embodiments, the lens may be a collimating lens disposed to collimate the beam, the scattered light, or both. In some embodiments, more than one lens may be disposed in the optical path. For example, two lenses may be disposed in series in the optical path to expand or narrow the beam.

[0078] The position and orientation of one or both of the first reflective element 1105 and the second reflective element 1106 may be controlled by an actuator. In some embodiments, the actuator may be a motor, a solenoid, a galvanometer, or a servo. For example, the position of the first reflective element 1105 may be controlled by a first actuator, and the position and orientation of the second reflective element 1106 may be controlled by a second actuator. In some embodiments, a single reflective element may be controlled by multiple actuators. For example, the first reflective element 1105 may be controlled by a first actuator along a first axis and a second actuator along a second axis. In some embodiments, a single actuator may control the reflective elements along multiple axes.

[0079] The actuator can change the angle of incidence of the beam hitting the reflective element by changing the position of the reflective element by rotating the reflective element. Changing the angle of incidence can result in a translation of the position where the beam hits the surface. In some embodiments, the angle of incidence can be adjusted to maintain the position where the beam hits the surface while the optical system is moving relative to the surface. The actuator can be servo controlled, piezoelectric actuated, piezo inertial actuated, stepper motor controlled, galvanometer driven, linear actuator controlled, or any combination thereof. The reflective element can be a mirror, e.g., a dichroic or dielectric mirror, a prism, a beam splitter, or any combination thereof. In some embodiments, the reflective element can be any element capable of deflecting a beam.

[0080] 11B shows a top view of an embodiment of the detection system 101 shown in FIG. 11A. As seen in FIG. 11A, the camera 1104 may be positioned to capture light, e.g., visible light, traveling in a direction opposite to the beam path, e.g., laser path 1102, along a visible light path 1152. The light may be scattered by a surface, e.g., a surface having an object of interest, or an object, e.g., an object of interest, and may travel along the visible light path 1152 toward the target camera 1104. In some embodiments, the camera 1104 is positioned to capture light reflected from the beam combiner 1103. In other embodiments, the camera 1104 is positioned to capture light transmitted through the beam combiner 1103. Upon capturing such light, the camera 1104 may be configured to image an area of ​​interest on the surface. The camera 1104 may be coupled to the beam combiner 1103, or the camera 1104 may be coupled to a support structure that supports the beam combiner 1103. In one embodiment, the target camera 1104 does not move relative to the beam combiner 1103 such that the camera 1104 maintains a fixed position relative to the beam combiner 1103 .

[0081] The high intensity lighting system described herein or the object targeting system described herein may be part of an autonomous weeding system for targeting and removing weeds. For example, the autonomous weeding system may be used to target weeds of interest identified and / or located in an image or representation collected by a sensor, such as a sensor. Targeting the weeds may include precisely locating the weeds using a sensor, targeting the weeds with a laser, and removing the weeds by burning the weeds with a laser light, such as infrared light. The high intensity lighting system may improve the accuracy of weed targeting by enabling shorter camera frame rates, shorter image exposure times, higher resolution imaging, or a combination thereof.

[0082] A method 1200 of targeting an object using a high-intensity lighting system of the present disclosure is shown in FIG. 12. Such a method may be implemented using a lighting array as described herein, such as the lighting array 150 shown in FIG. 5A, FIG. 5B, FIG. 6A, or FIG. 6B. The object may be detected using a detection system described herein, such as the detection system 101 shown in FIG. 10. In some embodiments, both the lighting array and the object detection system may be coupled to a vehicle, such as an autonomous weeding vehicle, as shown in FIG. 1A, FIG. 1B, and FIG. 1C, to detect an object 161 (e.g., a weed) located on a surface 160 (e.g., a ground). At step 1210 of the method 1200, the lighting array may be activated. Upon activation, the lighting array may illuminate an area of ​​interest on the surface with high-intensity lighting. At step 1220, the detection system may begin collecting images of the area of ​​interest illuminated by the lighting array. The initiation of image collection and the activation of the lighting array may occur substantially simultaneously. In some embodiments, activation of the illumination array and the start of image collection may occur within about 0.1 μs, about 1 μs, about 10 μs, or about 0.1 ms of each other. In some embodiments, activation of the illumination array may occur before starting image collection. Activation of the illumination array may occur within about 0.1 μs, about 1 μs, about 10 μs, or about 0.1 ms before starting image collection. In some embodiments, the start of image collection may occur before activation of the illumination array. The start of image collection may occur within about 0.1 μs, about 1 μs, about 10 μs, or about 0.1 ms before activation of the illumination array.

[0083] An image of the region of interest may be collected in step 1230 to generate an image of the region of interest. The image collection may correspond to a period between the start of image collection and the end of image collection, which may be referred to as the exposure time of the image. In step 1240, the detection system may end image collection of the region of interest, and in step 1250, the illumination array may be stopped. The end of image collection and the stopping of the illumination array may occur substantially simultaneously. In some embodiments, the stopping of the illumination array and the end of image collection may occur within about 0.1 μs, about 1 μs, about 10 μs, or about 0.1 ms of each other. In some embodiments, the stopping of the illumination array may occur before the end of image collection. The stopping of the illumination array may occur within about 0.1 μs, about 1 μs, about 10 μs, or about 0.1 ms before the end of image collection. In some embodiments, the end of image collection may occur before the stopping of the illumination array. The end of image collection may occur within about 0.1 μs, about 1 μs, about 10 μs, or about 0.1 ms before the illumination array is turned off.

[0084] The steps of activating the lighting array (step 1210), starting image collection (step 1220), collecting images (step 1230), terminating image collection (step 1240), and stopping the lighting array (step 1250) can be repeated to collect a series of images (e.g., a video). The steps may be repeated at a rate that corresponds to a frame rate, also referred to as the camera frame rate or video frame rate. In some embodiments, the frame rate may be measured as the time between the start of collection of successive image frames, i.e., the time between the start of collection of a first image frame and the start of collection of a second subsequent image frame.

[0085] In step 1260, an object, such as object 161 of FIG. 1C, may be located in the image collected in step 1230 or in a series of images collected by repeating steps 1210, 1220, 1230, 1240, and 1250. The use of a high intensity lighting system may improve the accuracy of the object location in the image, for example, by improving image quality by providing more uniform illumination over the region of interest captured in the image, allowing faster frame rates, allowing shorter frame times, allowing higher image resolution, or a combination thereof. The object may be targeted with an instrument in step 1270 based on the location determined in step 1260. For example, the object may be a weed targeted with a laser instrument to burn the weed. In another example, the object may be a plant (e.g., a crop or a weed) that is sprayed with a spray instrument. In another example, the object may be moved with a gripping instrument. In some embodiments, the instrument may include an array of instruments, and targeting the object may include selectively activating or deactivating individual instruments in the array to target the object of interest. For example, the instrument may include an array of sprayers, and each sprayer in the array is activated or deactivated depending on the location of the object of interest such that the location of the object of interest is selectively sprayed.

[0086] FIG. 13A illustrates a system bus architecture of a computing system 400, according to an exemplary embodiment. The system 400 may represent at least a portion of the detection system 101 or the control system 700. For example, the system 400 may represent at least a portion of the computer 701 of the control system 700. One or more components of the system 400 may electronically communicate with each other using a bus 405. The system 400 includes a processing unit (CPU or processor) 410 and a system bus 405 that couples various system components to the processor 410, including a system memory 415, such as a read-only memory (ROM) 420 and a random access memory (RAM) 425. The system 400 may include a cache of high-speed memory directly connected to the processor 410, in close proximity to it, or integrated as part of the processor 410. The system 400 may copy data from the memory 415 and / or the storage device 430 to the cache 412 for quick access by the processor 410. In this way, the cache 412 can provide a performance boost to avoid delays of the processor 410 while waiting for data. These and other modules may control or be configured to control the processor 410 to perform various actions. Other system memory 415 may be available as well. The memory 415 may include multiple different types of memory with different performance characteristics. The processor 410 may include any general-purpose processor as well as hardware or software modules such as service 1 432, service 2 434, and service 3 436 stored in storage 430 configured to control the processor 410, as well as special-purpose processors where software instructions are incorporated into the actual processor design. The processor 410 may essentially be a fully self-contained computing system including multiple cores or processors, buses, memory controllers, caches, etc. Multi-core processors may be symmetrical or asymmetrical.

[0087] To allow user interaction with the computing system 400, the input device 445 may represent any number of input mechanisms, such as a microphone for audio, a touch screen for gesture or graphical input, a keyboard, a mouse, motion input, voice, etc. The output device 435 may also be one or more of several output mechanisms known to those skilled in the art. In some cases, a multimodal system may allow a user to provide multiple types of input to communicate with the computing system 400. The communication interface 440 may generally manage and manage user input and system output. There is no restriction to operation with any particular hardware arrangement, so the basic features herein may be easily substituted for improved hardware or firmware arrangements as they are developed.

[0088] The storage device 430 may be a non-volatile memory, such as a magnetic cassette, a flash memory card, a solid-state memory device, a digital versatile disk, a cartridge, a random access memory (RAM) 425, a read-only memory (ROM) 420, and hybrids thereof, and may be a hard disk or other type of computer-readable medium capable of storing data accessible by a computer.

[0089] The storage device 430 may include services 432, 434, and 436 that control the processor 410. Other hardware or software modules are also contemplated. The storage device 430 may be connected to the system bus 405. In one aspect, a hardware module that performs a particular function may include software components stored in a computer readable medium in connection with the necessary hardware components, such as the processor 410, the bus 405, the output device 435 (e.g., a display), etc., to perform that function.

[0090] FIG. 13B illustrates a computer system 450 having a chipset architecture that may represent at least a portion of the detection system 140 or the control system 700. For example, the system 400 may represent at least a portion of the computer 701 of the control system 700. The computer system 450 may be an example of computer hardware, software, and firmware that may be used to implement the disclosed techniques. The system 450 may include a processor 455 that represents any number of physically and / or logically distinct resources capable of executing software, firmware, and hardware configured to perform the identified calculations. The processor 455 may communicate with a chipset 460 that may control input to and output from the processor 455. In this example, the chipset 460 may output information to an output 465, such as a display, and may read and write information to a storage device 470, which may include, for example, magnetic and solid-state media. The chipset 460 may also read data from and write data to a storage device 475 (e.g., RAM). A bridge 480 for interfacing with various user interface components 485 may be provided for interfacing with chipset 460. Such user interface components 485 may include a keyboard, a microphone, touch detection and processing circuitry, a pointing device such as a mouse, etc. In general, input to system 450 may come from any of a variety of machine-generated and / or human-generated sources.

[0091] Chipset 460 may also interface with one or more communication interfaces 490, which may have different physical interfaces. Such communication interfaces may include interfaces for wired and wireless local area networks, broadband wireless networks, and personal area networks. Some applications of the methods for generating, displaying, and using GUIs disclosed herein may include receiving an ordered data set via a physical interface, or a data set generated by the machine itself by processor 455 analyzing data stored in storage 470 or storage 475. Additionally, the machine may receive inputs from a user via user interface components 485 and perform appropriate functions, such as browsing functions, by interpreting these inputs with processor 455.

[0092] Of course, the exemplary systems 400 and 450 may have more than one processor 410, or may be part of a group or cluster of computing devices networked together to provide greater processing power.

[0093] In the foregoing description, aspects of the present application have been described with reference to specific embodiments thereof, but those skilled in the art will recognize that the present application is not limited thereto. Thus, while exemplary embodiments of the present application have been described in detail herein, it should be understood that the inventive concepts may be embodied and used in various other ways, and that the appended claims are intended to be construed to include such variations, except as limited by the prior art. Various features and aspects of the above-described applications may be used individually or together. Moreover, the embodiments may be utilized in any number of environments and applications beyond those described herein without departing from the broader spirit and scope of the present specification. Thus, the present specification and drawings should be regarded as illustrative and not restrictive. For purposes of illustration, the methods have been described in a particular order. It should be understood that in alternative embodiments, the methods may be performed in an order different from that described.

[0094] Those skilled in the art will understand that the less than ("<") and greater than (">") symbols or terms used herein may be replaced with the less than ("≦") and greater than or equal to ("≧") symbols, respectively, without departing from the scope of this description.

[0095] Where a component is described as being "configured" to perform a particular operation, such configuration may be achieved, for example, by designing electronic circuitry or other hardware to perform the operation, by programming a programmable electronic circuit (e.g., a microprocessor or other suitable electronic circuitry) to perform the operation, or by any combination thereof.

[0096] The phrase "coupled to" refers to any component that is physically connected, either directly or indirectly, to another component and / or any component that is in communication, either directly or indirectly, with another component (e.g., connected to the other component via a wired or wireless connection and / or other suitable communication interface).

[0097] Claim language or other language reciting "at least one" of a set and / or "one or more" of a set indicates that one element of the set or multiple elements of the set (in any combination) satisfy the claim. For example, a claim language reciting "at least one of A and B" means A, B, or A and B. In another example, a claim language reciting "at least one of A, B, and C" means A, B, C, or A and B, or A and C, or B and C, or A and B and C. The language "at least one" of a set and / or "one or more" of a set does not limit the set to the items listed in the set. For example, a claim language reciting "at least one of A and B" can mean A, B, or A and B, and can additionally include items not listed in the set of A and B.

[0098] As used herein, the terms "about" and "approximately" in reference to numerical values ​​are used herein to include numerical values ​​that fall within a range of 10%, 5%, or 1% in either direction (greater or less) of the numerical value, unless otherwise stated or clearly indicated by context (except where such numerical value exceeds 100% of its possible value).

[0099] Working Example The invention is further illustrated by the following non-limiting examples.

[0100] Example 1 High-intensity lighting for crop fields This example describes high-intensity illumination of a crop field for autonomous weed detection. An autonomous vehicle, as shown in Figures 1A and 1B, equipped with a high-intensity illumination system and a detection system was deployed in a crop field. The autonomous vehicle navigated the crop rows while the high-intensity illumination system illuminated an area of ​​interest in the field below the vehicle and the detection system imaged the area of ​​interest. The high-intensity illumination system illuminated the area of ​​interest using an array of light emitters, such as light-emitting diodes (LEDs), arranged to provide uniform brightness across the area of ​​interest. A voltage of 92V was applied to each LED, resulting in the high-intensity illumination system providing approximately 600,000 lumens / m 2 (lux). The applied voltage was well above the maximum voltage of 69.4 V that the LEDs were designed to operate at. To avoid overheating due to the high voltage, the LEDs were operated at a 7% duty cycle. The LED on / off state was synchronized to the detection system's camera exposure, with the LEDs on while the camera was exposed and off while the camera was not exposed. The camera had a resolution of 200 pixels per inch (78.7 pixels per cm), an exposure time of 300 μs, and a depth of field of approximately 5 inches (12.7 cm), providing a field of view of approximately 0.58 m. 2 An area of ​​a field was imaged. The vehicle was traveling at a speed of 0.5 mph (0.224 m / s) during imaging. As can be seen in the example image provided in Figure 2, the plants were clearly identifiable in the captured images, with no areas over- or under-saturated. Images were collected at various times during the night and day, without significant changes in lighting.

[0101] In contrast, a similar autonomous vehicle without a high-intensity lighting system was used to image an area of ​​interest in a crop field. The autonomous vehicle without a high-intensity lighting system was equipped with a protective shroud surrounding the imaging system to block stray light from the sun. An example of an image collected without a high-intensity lighting system while the autonomous vehicle was stationary is shown in FIG. 3. Even with the light-blocking shroud, stray light reached surfaces within the area of ​​interest, causing uneven illumination and oversaturation of parts of the image. The oversaturated areas caused by stray light glare are indicated by arrows in FIG. 3. Glare from stray light was particularly problematic for the autonomous vehicle without a high-intensity lighting system when the sun was at a low angle (e.g., just after sunrise or just before sunset).

[0102] Example 2 Reducing Motion Blur Using High-Brightness Lighting Systems This example illustrates the reduction of motion blur using a high-intensity lighting system. Illuminating an area of ​​interest with high-intensity lighting reduces motion blur due to camera movement relative to the area of ​​interest during the frame exposure time. A camera located on a vehicle moving along a surface at 2 miles per hour (0.894 m / s) images an area of ​​the surface. Under standard lighting conditions (approximately 60,000 lux), the camera exposure time is set to 3 ms to capture enough light for high-resolution (200 pixels per inch) imaging. The resulting image contains substantial motion blur due to the vehicle's movement during the relatively long 3 ms exposure time. An image simulating a 3 ms exposure time with 60,000 lux illumination is shown in FIG. 4C. The vehicle moves approximately 2.68 mm relative to the surface during the 3 ms exposure. As can be seen in FIG. 4C, the motion blur obscures the detection of objects such as weeds in the image.

[0103] Images are collected from a vehicle traveling at 2 mph equipped with a lighting system. With illumination comparable to bright daylight conditions (approximately 120,000 lux), the camera exposure time is set to 1.5 ms to capture enough light for high resolution imaging (200 pixels per inch). The resulting image contains some motion blur, but is substantially less blurred than an image taken under 60,000 lux with a 3 ms exposure. An image simulating a 1.5 ms exposure time with 120,000 lux illumination is shown in FIG. 4B. The vehicle moves approximately 1.34 mm relative to the surface during the 1.5 ms exposure. Although some blur is still visible in FIG. 4B, objects such as weeds can be detected in the image.

[0104] Finally, images are collected from a vehicle traveling at 2 miles per hour equipped with a high-intensity lighting system. With illumination comparable to 5 times the brightness of sunlight (approximately 600,000 lux), the camera exposure time is set to 0.3 ms (300 μs) to capture enough light for high-resolution (200 pixels per inch) imaging. The resulting images contain little to no detectable motion blur. An image collected with 600,000 lux illumination and a 0.3 ms exposure time is shown in FIG. 4A. The vehicle moves only 0.27 mm relative to the surface during the 0.3 ms exposure. As can be seen in FIG. 4A, objects such as weeds can be detected and identified in the image.

[0105] Experimental Example 3 Light Emitting Diode Array This example describes a light emitting diode (LED) array configured to generate uniform illumination over an area of ​​interest on a surface. The LEDs are positioned on the underside of an autonomous vehicle, as shown in FIG. 5B and FIG. 6B, and are configured to illuminate a surface below the vehicle as the vehicle moves over the surface to collect images of the area of ​​interest. Examples of LED arrays configured to generate uniform illumination on a surface are shown in FIG. 5A and FIG. 6A. The vehicle may include multiple LED arrays. The LED placement is adjusted to generate uniform illumination of the surface of interest, such as a field with rows of crops. The LED placement is determined using computer simulation to minimize variation in the sum of the luminance from the multiple LEDs over the area of ​​interest of the surface. The computer simulation considers parameters including the number of LEDs, the presence and type of reflector, the geometric constraints of the device on which the lighting array is placed, the distance from the surface, and the field of view of a camera placed to image the area of ​​interest. The computer simulation varies parameters including the position of the LEDs, the number of LEDs, the angle of the LEDs, the presence of a reflector, and the type of reflector.

[0106] Example 4 Electrical configuration of high brightness lighting system This example describes the electrical configuration of a high-brightness lighting system. The high-brightness lighting system includes a light-emitting diode (LED) array and one or more cameras. The LED array and cameras are controlled by a computer-operated strobe printed circuit board (PCB) as shown in FIG. 7. The strobe PCB provides a strobe signal to the LED array to turn the LEDs on and off. The LED on / off state is synchronized with the camera trigger so that the LEDs are on while the camera is collecting data and / or exposing an image. The strobe PCB is designed to provide a voltage to the LEDs that is approximately twice the designed operating voltage of the LEDs. The higher than recommended voltage allows the LED array to emit 600,000 lumens / m, approximately five times brighter than peak daylight on a sunny day. 2(lux) of illumination. The LEDs are operated at a 7% duty cycle to prevent overheating due to the high voltage. A heat sink is added to the LEDs to further prevent overheating.

[0107] While preferred embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous variations, changes, and substitutions will now occur to those skilled in the art without departing from the invention. It is understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of the invention. It is intended that the following claims define the scope of the invention, and that methods and structures within the scope of these claims, and their equivalents, be covered thereby.

Claims

1. A system for damaging or killing a target plant, said system comprising: a movable platform configured to move over an area of ​​interest on a surface; a camera carried by the movable platform; an illumination array carried by the movable platform, the illumination array configured to illuminate the area of ​​interest thereby reducing or eliminating shadows within the area of ​​interest; and an emitter carried by the movable platform, the emitter configured to emit a beam toward a target; one or more processors carried by the mobile platform; Equipped with The one or more processors: illuminating the region of interest by activating the illumination array; acquiring an image of the region of interest from the camera while the region of interest is illuminated by the illumination array; identifying a target plant within the image of the region of interest, wherein the identifying includes distinguishing between the target plant and non-target plants within the image of the region of interest; determining a target location of the target plant within the region of interest; causing the emitter to emit the beam toward the target location of the target plant, thereby damaging or killing the target plant; 10. A system configured to perform operations including:

2. The system described in claim 1, wherein the illumination from the lighting array is directed downward toward the area of ​​interest, thereby reducing or eliminating the shadow within the area of ​​interest.

3. The system described in claim 2, wherein the lighting array is configured to generate an illuminance within the region of interest that varies by no more than 50% across the region of interest.

4. The system of claim 3, wherein the region of interest has an area of ​​at least 0.1 m 2 .

5. The system described in claim 1, wherein the movable platform is configured to move while the camera acquires the image of the area of ​​interest, and the lighting from the lighting array is configured to reduce or eliminate motion blur in the image.

6. The system of claim 1, wherein the illumination from the lighting array is configured to reduce or eliminate variations in illuminance within the region of interest due to variable ambient light.

7. The system described in claim 1, wherein the lighting array comprises a plurality of light-emitting diodes (LEDs).

8. The system described in claim 1, wherein the lighting array is coupled to the movable platform such that the area of ​​interest illuminated by the lighting array is below the movable platform.

9. The system described in claim 1, wherein the target plants are weeds and the non-target plants are crops.

10. The system described in claim 9, wherein the distinguishing is performed using a neural network trained on images of weeds and crops.

11. The system of claim 1, further comprising: stopping the lighting array after the image of the area of ​​interest is acquired.

12. The system of claim 2, further comprising a reflector configured to redirect light toward the surface.

13. The system of claim 2, further comprising a heat sink configured to dissipate heat.

14. The system described in claim 1, wherein the beam is a laser beam configured to burn the target plant.

15. A method for damaging or killing a target plant, said method comprising: moving a movable platform over an area of ​​interest; activating a lighting array carried by the movable platform to illuminate the area of ​​interest, thereby reducing or eliminating shadows within the area of ​​interest; acquiring an image of the region of interest using a camera carried by the movable platform while the region of interest is illuminated by the illumination array; identifying a target plant within the image of the region of interest; determining a target location of the target plant within the region of interest; activating an emitter carried by the movable platform to emit a beam toward the target location of the target plant, thereby damaging or killing the target plant; A method comprising:

16. The method of claim 15, wherein the illumination from the lighting array is directed downward toward the area of ​​interest, thereby reducing or eliminating the shadow within the area of ​​interest.

17. The method described in claim 16, wherein the lighting array is configured to generate an illuminance within the region of interest that varies by no more than 50% across the region of interest.

18. The method of claim 17, wherein the region of interest has an area of ​​at least 0.1 m 2 .

19. The method of claim 15, wherein the movable platform is moving while the camera is acquiring the image of the area of ​​interest, and the lighting from the lighting array is configured to reduce or eliminate motion blur in the image.

20. The method of claim 15, wherein the illumination from the lighting array is configured to reduce or eliminate variations in illuminance within the region of interest due to variable ambient light.

21. The method of claim 15, wherein the lighting array comprises a plurality of light-emitting diodes (LEDs).

22. The method of claim 15, wherein the lighting array is coupled to the movable platform such that the area of ​​interest illuminated by the lighting array is below the movable platform.

23. The method described in claim 15, further comprising distinguishing between the target plants and non-target plants in the image of the area of ​​interest.

24. The method described in claim 23, wherein the target plant is a weed and the non-target plant is a crop.

25. The method described in claim 24, wherein the distinguishing is performed using a neural network trained on images of weeds and crops.

26. The method of claim 15, further comprising stopping the illumination array after the image of the area of ​​interest is acquired.

27. The method of claim 15, further comprising using a reflector to redirect light toward the surface.

28. The method of claim 15, further comprising dissipating heat using a heat sink.

29. The method described in claim 15, wherein the beam is a laser beam configured to burn the target plant.

30. The system described in claim 1, wherein the surface is the ground of a field.

31. A system for illuminating and targeting plants in a field, said system comprising: a lighting array comprising a plurality of light emitters, the lighting array configured to illuminate a region of interest within the field to reduce or eliminate shadows within the region of interest, the region of interest including the plant; and Detection system and Equipped with The detection system comprises: a camera configured to acquire an image of the area of ​​interest, the image depicting the plant; and one or more processors configured to determine a target location of the plant within the area of ​​interest based on the image of the area of ​​interest acquired by the camera; a light source configured to emit a light beam toward the target location of the plant, thereby damaging or killing the plant; and A system comprising:

32. The system described in claim 31, further comprising a computer and a strobe circuit, the computer configured to control the strobe circuit, and the strobe circuit configured to activate and deactivate the lighting array and synchronize the exposure time of the camera with the activation state of the lighting array.

33. The system described in claim 32, wherein the strobe circuit is configured to activate the lighting array when the exposure time of the camera begins and to deactivate the lighting array when the exposure time of the camera ends.

34. The system described in claim 32, wherein the strobe circuit further comprises a capacitor, the capacitor configured to charge while the lighting array is stopped.

35. The system described in claim 34, wherein discharging the capacitor is configured to activate the lighting array.

36. The system described in claim 32, wherein the strobe circuit is configured to activate and deactivate the lighting array with a duty cycle of 15% or less.

37. The system of claim 31, further comprising a heat sink configured to dissipate heat from the lighting array.

38. The system described in claim 31, wherein the illuminance within the region of interest varies by no more than 50% across the region of interest when the lighting array is activated.

39. The system of claim 31, wherein the light emitter is a light-emitting diode (LED).

40. The system of claim 31, wherein the lighting array is configured to generate an illuminance of 120,000 lumens / m 2 (lux) or greater.

41. The system described in claim 31, wherein the lighting array is configured to generate an illuminance of greater than 200,000 lux and less than 700,000 lux.

42. The system described in claim 31, wherein the system is coupled to a vehicle, and the vehicle is configured to move relative to the field.

43. The system described in claim 42, wherein the detection system is coupled to the vehicle such that the area of ​​interest imaged by the camera is beneath the vehicle.

44. The system described in claim 42, wherein the lighting array is coupled to the vehicle such that the area of ​​interest illuminated by the lighting array is beneath the vehicle.

45. The system described in claim 31, wherein the plant is a weed.

46. The system described in claim 31, wherein the light beam is a laser beam.

47. The system described in claim 46, wherein the laser beam is configured to burn the plant.

48. The system described in claim 31, wherein the one or more processors are configured to determine the target location of the plant by inputting the image of the area of ​​interest into a deep learning neural network.

49. The system described in claim 48, wherein the deep learning neural network is trained to distinguish between crops and weeds.

50. The system described in claim 31, wherein the illumination from the lighting array is directed downward toward the area of ​​interest, thereby reducing or eliminating the shadow within the area of ​​interest.

51. The system described in claim 42, wherein the vehicle is configured to move relative to the field while the camera is acquiring the image of the area of ​​interest, and the lighting from the lighting array is configured to reduce or eliminate motion blur in the image.

52. A system for illuminating and targeting weeds in a field, the system comprising: a movable platform configured to move across the field; a camera carried by the movable platform, the camera configured to capture an image of an area of ​​interest within the field; and a lighting array carried by the movable platform, the lighting array comprising a plurality of light emitters, the lighting array configured to illuminate the area of ​​interest within the field to reduce or eliminate shadows in the image of the area of ​​interest acquired by the camera; and a light source carried by the movable platform, the light source configured to emit a beam of light toward a target; one or more processors carried by the mobile platform; Equipped with The one or more processors: illuminating the region of interest by activating the illumination array; acquiring an image of the region of interest from the camera while the region of interest is illuminated; deactivating the lighting array; identifying weeds in the image of the region of interest, wherein the identifying is performed using a neural network configured to distinguish between weeds and crops; determining a target location of the weed within the region of interest based on the image; causing the light source to emit the light beam toward the target location of the weed, thereby killing or damaging the weed; 10. A system configured to perform operations including:

53. The system described in claim 52, wherein the illumination from the lighting array is directed downward toward the area of ​​interest, thereby reducing or eliminating the shadow in the image of the area of ​​interest.

54. The system described in claim 52, wherein the lighting array is configured to generate an illuminance within the region of interest that varies by no more than 50% across the region of interest.

55. The system of claim 52, wherein the lighting array is configured to generate an illuminance within the area of ​​interest of at least 120,000 lumens / m 2 (lux).

56. The system described in claim 52, wherein the movable platform is configured to move across the field while the camera acquires the image of the area of ​​interest, and the illumination from the lighting array is configured to reduce or eliminate motion blur in the image.

57. The system described in claim 52, wherein the illumination from the lighting array is configured to reduce or eliminate variations in illuminance within the region of interest due to variable ambient light.

58. The system described in claim 52, wherein the neural network includes a convolutional neural network trained on images of weeds and crops.

59. The system described in claim 52, wherein the starting and stopping of the lighting array is synchronized with the exposure time of the camera.

60. The system described in Claim 59, wherein the lighting array is activated when the exposure time of the camera begins and is deactivated when the exposure time of the camera ends.

61. The system described in claim 60, further comprising a strobe circuit configured to activate and deactivate the lighting array.

62. The system described in claim 52, wherein the light beam is a laser beam.

63. The light source comprising: a control system configured to direct a path of the laser beam; The control system includes: a first actuator and a first mirror; a second actuator and a second mirror; Equipped with 63. The system of claim 62, wherein the operations further include using the control system to direct the path of the laser beam toward the target location of the weed.

Images